WO2019051941A1 - Method, apparatus and device for identifying vehicle type, and computer-readable storage medium - Google Patents

Abstract

Provided are a method, apparatus and device for identifying a vehicle type based on a convolutional neural network, and a computer-readable storage medium. The method comprises: pre-processing an acquired picture to be detected (S101); inputting the pre-processed picture to be detected to a first pre-set detection model to determine whether the picture to be detected contains vehicle feature information (S102); if the picture to be detected contains vehicle feature information, inputting the pre-processed picture to be detected to a second pre-set detection model (S103); carrying out calculation by means of the second pre-set detection model to obtain a probability value of the picture to be detected corresponding to each category of vehicle types (S104); and determining the maximum probability value in all probability values, and taking a vehicle type corresponding to the maximum probability value as a vehicle type of the picture to be detected (S105), wherein the first pre-set detection model and the second pre-set detection model are respectively acquired through corresponding training performed on a convolutional neural network by means of pre-set picture data. The method can realize high-accuracy vehicle type identification, and also enables an identification process to be high-efficiency and stable.

Description

Application Name: Vehicle identification method, device, device and computer readable storage medium

This application claims to be filed on September 15, 2017 in the Chinese Patent Office, the application number is CN 2017108336368, and the application is entitled "Convolutional Neural Network-Based Vehicle Identification Method, Apparatus, Equipment, and Computer-Readable Storage Media" Priority is hereby incorporated by reference in its entirety.

Technical field

The present application relates to the field of computer technology, and in particular, to a vehicle identification method, apparatus, device, and computer readable storage medium based on a convolutional neural network.

Background technique

Automobile model identification plays a key role in vehicle management, vehicle violation and escape, vehicle inspection and control, and accidental vehicle loss compensation. The vehicle type has the advantage of being difficult to change, and becomes a very important feature in vehicle identification. In the case of cars and deck cars, it is impossible to obtain effective vehicle information through license plate recognition and image sharpening processing technology, especially in the case of car damage claims, the model has a great influence on the amount of compensation, and the vehicle type identification is similar to other traffic monitoring and control. Traffic accident liability determination and other scenarios also play a very important role.

Traditional vehicle identification methods often only design different features such as scale-invariant feature conversion (SIFT) for different tasks, and then use the support vector machine (SVM) or random forest (Random Forest) classifiers for training. However, it can only be applied to the scene of vehicle type and license plate recognition. For thousands of models with many similar types, it is difficult to manually identify the targeted features. In addition, although there is a vehicle identification method based on multi-sensor fusion, the principle and recognition of the method are very simple, and there are disadvantages of being sensitive to the external environment and having a high failure rate.

Application content

The embodiment of the present application provides a vehicle identification method, device, device and computer readable storage medium based on a convolutional neural network, which can realize high-precision vehicle type recognition and make the identification process efficient and stable.

In one aspect, an embodiment of the present application provides a vehicle identification method based on a convolutional neural network, the method comprising:

Pre-processing the acquired picture to be tested; inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information; if the picture to be tested contains vehicle feature information, The pre-processed picture to be tested is input to a second preset detection model; the second preset detection model is used to calculate a probability value of the picture to be tested corresponding to each type of vehicle type; determining a maximum probability among all probability values a value, and the vehicle corresponding to the maximum probability value is used as the model of the picture to be tested; wherein the first preset detection model and the second preset detection model respectively use a preset picture data to convolutional neural network Get it by training accordingly.

On the other hand, the embodiment of the present application further provides a vehicle identification device based on a convolutional neural network, the device comprising:

a processing unit, configured to: perform pre-processing on the acquired image to be tested; and the determining unit is configured to input the pre-processed image to be tested into the first preset detection model to determine whether the image to be tested includes vehicle feature information; And if the picture to be tested contains the vehicle feature information, the pre-processed picture to be tested is input to the second preset detection model; and the calculating unit is configured to calculate the to-be-waited by the second preset detection model The measured picture corresponds to a probability value of each type of vehicle type; the determining unit is configured to determine a maximum probability value of all the probability values, and the vehicle type corresponding to the maximum probability value is used as the model of the picture to be tested; wherein The first preset detection model and the second preset detection model are respectively acquired by performing corresponding training on the convolutional neural network by using preset image data.

In another aspect, the embodiment of the present application further provides a vehicle identification device based on a convolutional neural network, the device comprising:

a memory for storing a program for realizing vehicle type recognition; and a processor for running a program for realizing vehicle type identification stored in the memory to perform the following operations:

Pre-processing the acquired picture to be tested; inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information; if the picture to be tested contains vehicle feature information, The pre-processed picture to be tested is input to a second preset detection model; the second preset detection model is used to calculate a probability value of the picture to be tested corresponding to each type of vehicle type; determining a maximum probability among all probability values a value, and the vehicle corresponding to the maximum probability value is used as the model of the picture to be tested; wherein the first preset detection model and the second preset detection model respectively use a preset picture data to convolutional neural network Get it by training accordingly.

In still another aspect, an embodiment of the present application further provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors Execute to implement the following steps:

Pre-processing the acquired picture to be tested; inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information; if the picture to be tested contains vehicle feature information, The pre-processed picture to be tested is input to a second preset detection model; the second preset detection model is used to calculate a probability value of the picture to be tested corresponding to each type of vehicle type; determining a maximum probability among all probability values a value, and the vehicle corresponding to the maximum probability value is used as the model of the picture to be tested; wherein the first preset detection model and the second preset detection model respectively use a preset picture data to convolutional neural network Get it by training accordingly.

The embodiment of the present application determines whether the picture to be tested contains vehicle feature information by inputting the pre-processed picture to be tested into a first preset detection model; if the picture to be tested contains vehicle feature information, the pre-processed to-be-processed Inputting a second preset detection model; calculating, by the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle; determining a maximum probability value among all probability values, and The vehicle model corresponding to the maximum probability value is used as the model of the picture to be tested; specifically, the vehicle is first classified according to the picture to be measured, and then the picture containing the vehicle characteristic information is found according to the second classification result of the vehicle, and the classification and recognition of the vehicle type are performed again. Thereby, the application embodiment can realize the classification and recognition of the fine vehicle type of the vehicle, for example, achieving high-precision vehicle type recognition of up to 92.48%, and at the same time making the recognition process more efficient and stable.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are some embodiments of the present application. For the ordinary technicians, other drawings can be obtained based on these drawings without paying creative labor.

1 is a schematic flow chart of a vehicle identification method based on a convolutional neural network according to an embodiment of the present application;

2 is another schematic flowchart of a method provided by an embodiment of the present application;

FIG. 3 is another schematic flowchart of a method provided by an embodiment of the present application;

4 is another schematic diagram of a method provided by an embodiment of the present application;

FIG. 5 is a schematic block diagram of a vehicle identification device based on a convolutional neural network according to an embodiment of the present application; FIG.

6 is another schematic block diagram of an apparatus provided by an embodiment of the present application;

FIG. 7 is another schematic block diagram of an apparatus provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a vehicle identification device based on a convolutional neural network according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

The use of the terms "comprising", "comprising", "","," The presence or addition of a plurality of other features, integers, steps, operations, elements, components, and/or collections thereof.

The terminology used herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in the specification and the appended claims, the claims

Please refer to FIG. 1. FIG. 1 is a schematic flow chart of a vehicle identification method based on a convolutional neural network according to an embodiment of the present application. The method can be run on devices such as smart phones (such as Android phones, IOS phones, etc.), tablets, laptops, and smart devices. The method of the present application can automatically analyze the input picture to be tested, thereby realizing the classification and recognition of the fine vehicle type of the vehicle, for example, achieving high-precision vehicle identification up to 92.48%, and also making the identification process more efficient and stable. As shown in FIG. 1, the method includes steps S101 to S105.

S101 preprocesses the obtained picture to be tested.

In the embodiment of the present application, after obtaining the picture to be tested, it is required to perform certain processing on it. The picture to be tested may be a regular picture, or may be a picture obtained by extracting a video key frame from the video data. In order to improve the accuracy of the classification detection, it is necessary to perform corresponding processing on the picture to be tested. In particular, it is necessary to perform feature enhancement on the picture to be measured, that is, to unify the image to a size of 227*227.

S102. Input the pre-processed picture to be tested into the first preset detection model to determine whether the picture to be tested contains vehicle feature information.

In the embodiment of the present application, the pre-processed picture to be tested needs to be input into the first preset detection model to perform two classifications, thereby determining whether the picture to be tested contains vehicle feature information. The first preset detection model may be a vehicle binary classification model trained based on a deep convolutional neural network and a large number of vehicle related picture data sets.

Specifically, as shown in FIG. 2, as a preferred embodiment, step S102 includes steps S201 to S202.

S201: Input the pre-processed picture to be tested into the first preset detection model to obtain a confidence.

In the embodiment of the present application, after the pre-processed picture to be tested is input into the first preset detection model, a corresponding confidence level may be obtained, because the first preset detection model is based on a deep convolutional neural network. The training is obtained, so the confidence can be outputted by the connection layer for the two classifications in the deep convolutional neural network.

S202. Determine whether the confidence level is greater than a preset threshold.

In the embodiment of the present application, if the confidence is not greater than the pre-set reliability, it can be known that the picture to be tested does not contain the vehicle feature information, that is, the picture does not contain the vehicle, and subsequent vehicle type identification is not required. The pre-set reliability may be correspondingly set according to actual conditions. For example, when the pre-set reliability is 0.6, if the confidence is less than or equal to 0.6, the picture to be tested is a picture containing vehicle characteristic information. That is, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information.

S103. If the picture to be tested contains vehicle feature information, input the pre-processed picture to be input into the second preset detection model.

In the embodiment of the present application, when the image to be tested includes the vehicle feature information, the pre-processed image to be tested is input into the second preset detection model, and the second preset detection model may be based on A model classification model trained by deep convolutional neural networks and a large number of vehicle-related image data sets.

S104. Calculate, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type.

In the embodiment of the present application, after the processed picture to be tested is input to the second preset detection model, the probability value of each type of vehicle corresponding to the picture to be tested may be calculated. The model in the embodiment of the present application may include information such as a brand name, a manufacturer name, and a model of the vehicle, and is of course not limited to the above information. In general, each probability value of the output can be calculated by the second preset detection model. Corresponding to a model.

For example, the model may include a model as shown in Table 1 below.

Serial number Brand name Vendor name Car model 1 Land Rover Land Rover (import) Range Rover 2 Land Rover Land Rover (import) Third generation discovery 3 Land Rover Land Rover (import) Freelander 2 4 Land Rover Land Rover (import) Range Rover Aurora (Import) 5 Land Rover Land Rover (import) Fourth generation discovery 6 Land Rover Land Rover (import) Range Rover Sport Edition 7 Land Rover Land Rover (import) Series I 8 Land Rover Land Rover (import) Freelander 9 Land Rover Land Rover (import) First generation discovery 10 Land Rover Land Rover (import) Second generation discovery 11 Land Rover Land Rover (import) Range Rover Aurora 12 Land Rover Land Rover (import) Discover the gods

Table 1

Among them, each of the serial numbers 1 to 12 has a probability. If the probability of the model indicated by the serial number 9 is the largest, then the model of the vehicle in the picture to be tested is the brand name Land Rover. The manufacturer is called Land Rover (import), and the model number of the car is the model found in the first generation.

S105. Determine a maximum probability value among all the probability values, and use a vehicle type corresponding to the maximum probability value as a model of the picture to be tested.

In the embodiment of the present application, all the probability values are compared and analyzed to obtain the maximum probability value. At this time, the model corresponding to the probability value is the model of the picture to be tested.

In addition, as a preferred embodiment, as shown in FIG. 3, the preset picture data includes preset first picture data, and the steps in the vehicle identification method based on the convolutional neural network provided by the embodiment of the present application are provided. Step S301 to S305 are also included before S101:

S301. The preset first picture data is divided into a first training set and a first verification set.

In the embodiment of the present application, the preset first picture data may include a preset image including a picture of the vehicle and a picture not including the vehicle, which may be manually classified and filtered, and the two types of data are used as two scenes, and Input data is provided to the convolutional neural network for learning classification, so that it can be judged Whether the picture is a vehicle two-category model containing a picture of the vehicle.

Specifically, the given classification of the picture without the vehicle may be marked as 0, the given classification of the picture containing the vehicle is marked as 1, and the preset picture data marked with the label is assigned as the first ratio of 4:1. The training set and the first verification set may include a picture containing the vehicle and a picture not containing the vehicle, and the first verification set may include a picture containing the vehicle and a picture not containing the vehicle.

The first training set is used for regular training of the convolutional neural network, and the first verification set is used for performing corresponding classification detection on the model obtained by the trained convolutional neural network. In order to improve the accuracy of the identification, the The first training set and the first verification set are first subjected to corresponding preprocessing, such as feature enhancement, etc., before the convolutional neural network can be input for training.

S302. Train the first convolutional neural network by using the first training set to obtain a corresponding first intermediate model.

In the embodiment of the present application, the Convolutional Neural Network (CNN) is a feedforward neural network, and the artificial neurons can respond to surrounding units in a part of the coverage, and have excellent performance for large image processing. Different convolutional neural networks include different hierarchical structures. Specifically, the embodiment of the present application can train the first intermediate model by using the first training set to select the deep convolutional neural network.

As a preferred embodiment, the first convolutional neural network may comprise an eight-layer structure, wherein the first convolutional neural network comprises five convolutional layers, two fully connected layers, and one probability for two classifications Statistical layer. The first five layers are convolutional layers for feature extraction and dimensionality reduction, the latter two layers are fully connected layers, and finally the probability and statistics layer for binary classification. Each convolutional layer in the first convolutional neural network can filter the input image data into a two-dimensional vector through the convolution kernel, and calculate its parameters separately during the training phase, while the fully connected layer will input and weight the vector. The dot multiplication is performed, so that the neurons of the latter layer are all connected with the neurons of the previous layer, all neurons are accelerated by the activation function, and the probability statistical layer is used for judging whether the picture includes vehicle characteristic information.

S303. Verify the first intermediate model by using the first verification set to obtain a corresponding first error set, where the first error set includes at least one first error sample.

In the embodiment of the present application, the picture in the first verification set is input into the first intermediate model for classification detection to obtain a classification detection result, and when the classification detection result is inconsistent with the preset classification of the picture, the picture is identified as a first A wrong sample. Specifically, the image in which all the classification detection results are inconsistent with the pre-classification of the picture can be classified into the first error set. In summary, each first error set can be included to One less first error sample.

S304. If the number of the first error samples in the first error set is greater than or equal to the first preset threshold, the first intermediate model is trained by using the first error set to obtain a new first intermediate model.

In the embodiment of the present application, if the number of the first error concentration error samples is greater than or equal to the preset threshold, it indicates that the error rate of the result of the classification detection is within an unacceptable range, and the first error needs to be utilized. The first intermediate model is trained to obtain a corresponding new first intermediate model, thereby further improving the accuracy of the classification detection of the first intermediate model.

S305. Verify the new first intermediate model again by using the first verification set, until the number of the first error samples in the first error set is less than a preset threshold, and determine a new first at this time. The intermediate model is the corresponding first preset detection model.

In the embodiment of the present application, after obtaining the new first intermediate model, the first verification set needs to be used again to perform verification to obtain a new classification detection result, and at the same time, it is determined whether the number of error samples in the first error set at this time is less than The preset threshold, when the number of error samples in the first error set is less than the preset threshold, then it may be determined that the new first intermediate model at this time is the corresponding first preset detection model. And if the number of error samples in the first error set is greater than or equal to the preset threshold, then step S304 may be returned.

Therefore, when the processed image to be tested is classified into two by the first preset detection model, the first layer of the convolution layer is taken as an example, and the image is unified to a size of 227*227, and the convolution kernel size is 11 *11, the step size is 4, the number of convolution kernels is 96, and the size of the feature map after convolution is 55 after the edge is subtracted. The feature map is normalized by the ReLu activation function and Norm normalized by the pooling operation. The feature map with the size of 27*27*96 is output, and then input into the subsequent convolution layer and the fully connected layer for binary classification.

As a preferred embodiment, as shown in FIG. 4, the preset picture data further includes preset second picture data, and step S101 in the vehicle identification method based on the convolutional neural network provided by the embodiment of the present application is provided. It may also include steps S401 to S405 before:

S401. The preset second picture data is divided into a second training set and a second verification set.

In the embodiment of the present application, the preset second picture data may include a preset classified picture of the vehicle having various vehicle types, which may be manually classified to filter the corresponding vehicle type, and each picture is used as a scene and used as input data. It is provided to a convolutional neural network for learning classification, so as to obtain a vehicle classification model that can determine the vehicle model in the picture.

Wherein, the second training set is used for regular training on the convolutional neural network, and the second verification set is used for the second training set. The model obtained by the trained convolutional neural network is classified and detected. In order to improve the accuracy of the recognition, the second training set and the second verification set may be pre-processed, such as feature enhancement, before inputting. Convolutional neural networks are trained.

S402. Train the second convolutional neural network by using the second training set to obtain a corresponding second intermediate model.

In the embodiment of the present application, the Convolutional Neural Network (CNN) is a feedforward neural network, and the artificial neurons can respond to surrounding units in a part of the coverage, and have excellent performance for large image processing. Different convolutional neural networks include different hierarchical structures. Specifically, the embodiment of the present application can train the second deep model by using the second deep training convolution neural network.

S403. Verify the second intermediate model by using the second verification set to obtain a corresponding second error set, where the second error set includes at least one second error sample.

In the embodiment of the present application, the picture in the second verification set is input into the second intermediate model for classification detection to obtain the classification detection result, and when the classification detection result is inconsistent with the preset classification of the picture, the picture is identified as a first Two wrong samples. Specifically, the image in which all the classification detection results are inconsistent with the pre-classification of the picture can be classified as the second error set. In summary, each second error set can include at least one second error sample.

S404. If the number of the second error samples in the second error set is greater than or equal to the second preset threshold, the second intermediate model is trained by using the second error set to obtain a new second intermediate model.

In the embodiment of the present application, if the number of the second error concentration error samples is greater than or equal to the preset threshold, it indicates that the error rate of the result of the classification detection is within an unacceptable range, and the second error needs to be utilized. The second intermediate model is trained to obtain a corresponding new second intermediate model, thereby further improving the accuracy of the classification detection of the second intermediate model.

S405. Verify the new second intermediate model again by using the second verification set, until the number of second error samples in the second error set is less than a preset threshold, and determine a new second at this time. The intermediate model is a corresponding second preset detection model.

In the embodiment of the present application, after obtaining the new second intermediate model, the second verification set needs to be used again to perform verification to obtain a new classification detection result, and at the same time, it is determined whether the number of error samples in the second error set at this time is smaller than The preset threshold, when the number of error samples in the second error set is less than the preset threshold, then it may be determined that the new second intermediate model at this time is the corresponding second preset detection model. And if If the number of error samples in the second error set is greater than or equal to the preset threshold, then step S404 may be returned.

Wherein, the second convolutional neural network may comprise a twenty-layer structure, as shown in Table 2.

Table 2

The second convolutional neural network uses a large number of 1*1 convolution kernels to enhance the fitting of nonlinearities for dimensionality reduction, while adding the initial module (Inception), using different scale filters to solve the scale. problem. At the same time, the other layers are similar, except that the number of filters is changed. In addition, the second convolutional neural network may include three output layers, wherein the structure of the last output layer is optimal, and the story uses the result of the output layer of the last layer as an output. Therefore, by training the hundreds of thousands of vehicle images of the determined vehicle in the second convolutional neural network, it is possible to generate a vehicle classification model that retains the vehicle characteristic parameters.

It can be seen that, in the embodiment of the present application, the pre-processed picture to be tested is input into the first preset detection model to determine whether the picture to be tested contains vehicle feature information; And collecting the pre-processed picture to be input into the second preset detection model; calculating, by using the second preset detection model, the probability value of the picture to be tested corresponding to each type of vehicle type; determining all probability values The maximum probability value in the middle, and the vehicle corresponding to the maximum probability value is used as the model of the picture to be tested; specifically, the vehicle is first classified according to the picture to be measured, and then the picture containing the vehicle characteristic information is found according to the vehicle classification result. And the classification identification of the vehicle model is performed again, so that the application embodiment can realize the classification and recognition of the fine vehicle type of the vehicle, that is, realize the vehicle identification with high precision of up to 92.48%, and at the same time, make the identification process more efficient and stable.

Referring to FIG. 5 , corresponding to the above-described method for identifying a vehicle type based on a convolutional neural network, the embodiment of the present application further provides a vehicle identification device based on a convolutional neural network, where the device 100 includes: a processing unit 101, a determining unit 102, The input unit 103, the calculation unit 104, and the determination unit 105.

The processing unit 101 is configured to perform pre-processing on the acquired picture to be tested.

The determining unit 102 is configured to input the pre-processed picture to be tested into a first preset detection model to determine whether the picture to be tested contains vehicle feature information.

The input unit 103 is configured to input the pre-processed picture to be tested into the second preset detection model if the picture to be tested contains vehicle feature information.

The calculating unit 104 is configured to calculate, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type.

The determining unit 105 is configured to determine a maximum probability value among all the probability values, and use the vehicle type corresponding to the maximum probability value as the vehicle type of the picture to be tested.

As shown in FIG. 6 , as a preferred embodiment, the preset picture data includes preset first picture data, and the apparatus 100 further includes a classification unit 201, a training unit 202, a verification unit 203, an adjustment unit 204, Decision unit 205.

The classification unit 201 is configured to divide the preset first picture data into a first training set and a first verification set;

The training unit 202 is configured to train the first convolutional neural network by using the first training set to obtain a corresponding first intermediate model;

The verification unit 203 is configured to verify the first intermediate model by using the first verification set to obtain a corresponding first error set, where the first error set includes at least one first error sample;

The adjusting unit 204 is configured to: if the number of the first error samples in the first error set is greater than or equal to the first preset threshold, use the first error set to train the first intermediate model to obtain a new first Intermediate model

The determining unit 205 is configured to verify the new first intermediate model again by using the first verification set until the number of the first error samples in the first error set is less than a preset threshold, and determine that the new time is The first intermediate model is a corresponding first preset detection model.

Preferably, the preset picture data further includes preset second picture data, wherein the classification unit 201 is further configured to divide the preset second picture data into the second training set and the second verification set.

The training unit 202 is further configured to train the second convolutional neural network by using the second training set to obtain a corresponding second intermediate model.

The verification unit 203 is further configured to verify the second intermediate model by using the second verification set to obtain a corresponding second error set, wherein the second error set includes at least one second error sample.

The adjusting unit 204 is further configured to: if the number of the second error samples in the second error set is greater than or equal to the second preset threshold, use the second error set to train the second intermediate model to obtain a new second Intermediate model.

The determining unit 205 is further configured to use the second verification set to verify the new second intermediate model again, until the number of the second error samples in the second error set is less than a preset threshold, and determine the current time The new second intermediate model is a corresponding second preset detection model.

As shown in FIG. 7, the determining unit 102 includes a confidence acquiring unit 301 and a confidence determining unit 302.

The confidence acquiring unit 301 is configured to input the pre-processed picture to be tested into the first preset detection model to obtain a confidence.

The confidence determination unit 302 is configured to determine whether the confidence level is greater than a preset threshold.

Wherein, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information.

The above-described convolutional neural network based vehicle identification device can be implemented in the form of a computer program that can be run on a device as shown in FIG.

FIG. 8 is a schematic structural diagram of a vehicle type identification device based on a convolutional neural network according to the present application. As shown in FIG. 8, the device 800 can include an input device 801, an output device 802, a transceiver device 803, a memory 804, and a processor 805, where:

The input device 801 is configured to receive input data of an external access control device. In a specific implementation, the input device 801 in the embodiment of the present application may include a keyboard, a mouse, a photoelectric input device, a sound input device, a touch input device, a scanner, and the like.

The output device 802 is configured to output output data of the access control device to the outside. In a specific implementation, the output device 802 described in this embodiment of the present application may include a display, a speaker, a printer, and the like.

The transceiver device 803 is configured to send data to or receive data from other devices through a communication link. In a specific implementation, the transceiver 803 of the embodiment of the present application may include a transceiver device such as a radio frequency antenna.

The memory 804 is used to store program data with various functions. In a specific implementation, the memory 804 of the embodiment of the present application includes a non-volatile storage medium and an internal memory. Wherein, the non-volatile storage medium can store an operating system and program data. When the program data is executed, the processor 805 can be caused to perform a vehicle type identification method. The internal memory provides an environment for the operation of program data in a non-volatile storage medium that, when executed by the processor 805, causes the processor 805 to perform a vehicle type identification method.

The processor 805 is configured to run a program for realizing vehicle type identification stored in the memory 804, to perform the following operations: pre-processing the acquired image to be tested; and inputting the pre-processed image to be tested into the first preset Detecting a model to determine whether the image to be tested contains vehicle feature information; if the image to be tested contains vehicle feature information, inputting the pre-processed image to be input into a second preset detection model; The model calculates that the picture to be tested corresponds to a probability value of each type of vehicle type; determines a maximum probability value among all the probability values, and uses the vehicle type corresponding to the maximum probability value as the model of the picture to be tested.

Further, the preset picture data includes preset first picture data, and the pre-processing of the obtained picture to be tested includes:

Dividing the preset first picture data into a first training set and a first verification set; training the first convolutional neural network by using the first training set to obtain a corresponding first intermediate model; Verifying, by the verification set, the first intermediate model to obtain a corresponding first error set, wherein the first error set includes at least one first error sample; and if the first error set is the number of first error samples Greater than or equal to the first preset threshold, training the first intermediate model with the first error set to obtain a new first intermediate model; using the first verification set to the new first intermediate model The verification is performed again until the number of the first error samples in the first error set is less than the preset threshold, and it is determined that the new first intermediate model at this time is the corresponding first preset detection model.

Further, the preset picture data further includes preset second picture data, the method further includes: dividing the preset second picture data into a second training set and a second verification set; Two The training set trains the second convolutional neural network to obtain a corresponding second intermediate model; and the second intermediate model is verified by the second verification set to obtain a corresponding second error set, wherein the The second error set includes at least one second error sample; if the number of the second error samples in the second error set is greater than or equal to the second preset threshold, the second intermediate model is trained by using the second error set Obtaining a new second intermediate model; verifying, by the second verification set, the new second intermediate model again, until the number of second error samples in the second error set is less than a preset threshold, and determining The new second intermediate model at this time is the corresponding second preset detection model.

Further, the first convolutional neural network comprises an eight-layer structure, and the second convolutional neural network comprises a twenty-layer structure, wherein the first convolutional neural network comprises five convolutional layers, two full The connection layer and a probabilistic layer for the two classifications.

Further, the inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains the vehicle feature information comprises: inputting the pre-processed picture to be input into the first preset detection model Obtaining a confidence level; determining whether the confidence level is greater than a preset threshold; wherein, if the confidence level is greater than a preset threshold, the picture to be tested includes vehicle feature information.

It will be understood by those skilled in the art that the embodiment of the convolutional neural network based vehicle type identification device shown in FIG. 8 does not constitute a limitation on the specific configuration of the convolutional neural network based vehicle type identification device. In other embodiments, based on The vehicle type identification device of the convolutional neural network may include more or fewer components than those illustrated, or some components may be combined, or different component arrangements. For example, in some embodiments, the convolutional neural network based vehicle identification device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are consistent with the embodiment shown in FIG. This will not be repeated here. The application provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the following steps: The image to be tested is preprocessed; the preprocessed picture to be tested is input into the first preset detection model to determine whether the picture to be tested contains vehicle feature information; if the picture to be tested contains vehicle feature information, the preprocessing is performed The second picture to be tested is input to the second preset detection model; the probability value of the picture to be tested corresponding to each type of vehicle type is calculated by the second preset detection model; and the maximum probability value among all the probability values is determined, And the model corresponding to the maximum probability value is used as the model of the picture to be tested.

Further, the preset picture data includes preset first picture data, and the pre-processing of the acquired picture to be tested includes: dividing the preset first picture data into the first training set and a first verification set; training the first convolutional neural network with the first training set to obtain a corresponding first intermediate model; and verifying the first intermediate model by using the first verification set to obtain Corresponding first error set, wherein the first error set includes at least one first error sample; if the number of the first error samples in the first error set is greater than or equal to a first preset threshold, using the first The error set trains the first intermediate model to obtain a new first intermediate model; the new first intermediate model is again verified using the first verification set until the first error sample in the first error set The number is less than the preset threshold, and it is determined that the new first intermediate model at this time is the corresponding first preset detection model.

Further, the preset picture data further includes preset second picture data, the method further includes: dividing the preset second picture data into a second training set and a second verification set; The second training set trains the second convolutional neural network to obtain a corresponding second intermediate model; and uses the second verification set to verify the second intermediate model to obtain a corresponding second error set, where The second error set includes at least one second error sample; if the number of the second error samples in the second error set is greater than or equal to a second preset threshold, training the second intermediate model with the second error set Obtaining a new second intermediate model; verifying the new second intermediate model again by using the second verification set until the number of second error samples in the second error set is less than a preset threshold, and It is determined that the new second intermediate model at this time is the corresponding second preset detection model.

Further, the first convolutional neural network comprises an eight-layer structure, and the second convolutional neural network comprises a twenty-layer structure, wherein the first convolutional neural network comprises five convolutional layers, two full The connection layer and a probabilistic layer for the two classifications.

Further, the inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information includes: pre-processing the obtained picture to be tested; Entering a first preset detection model to obtain a confidence level; determining whether the confidence level is greater than a preset threshold; wherein, if the confidence level is greater than a preset threshold, the image to be tested includes vehicle feature information .

The foregoing storage medium of the present application includes: a magnetic disk, an optical disk, a read-only memory (ROM), and the like, which can store various program codes. The units in all the embodiments of the present application may be implemented by a general-purpose integrated circuit, such as a CPU (Central Processing Unit), or by an ASIC (Application Specific Integrated Circuit).

The steps in the method of the embodiment of the present application may be sequentially adjusted, merged, and deleted according to actual needs. The units in the apparatus of the embodiment of the present application may be combined, divided, and deleted according to actual needs. A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the device, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

The foregoing is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any equivalents can be easily conceived by those skilled in the art within the technical scope disclosed in the present application. Modifications or substitutions are intended to be included within the scope of the present application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims (20)

A vehicle type identification method based on a convolutional neural network, characterized in that the method comprises: Preprocessing the acquired picture to be tested; Inputting the pre-processed picture to be tested into a first preset detection model to determine whether the picture to be tested contains vehicle feature information; If the picture to be tested contains vehicle feature information, input the pre-processed picture to be input into the second preset detection model; Calculating, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type; Determining a maximum probability value among all the probability values, and using the vehicle model corresponding to the maximum probability value as the model of the picture to be tested; The first preset detection model and the second preset detection model are respectively obtained by performing corresponding training on the convolutional neural network by using preset image data. The method of claim 1, wherein the preset picture data comprises preset first picture data, and before the pre-processing of the obtained picture to be tested, the method comprises: Dividing the preset first picture data into a first training set and a first verification set; Training the first convolutional neural network with the first training set to obtain a corresponding first intermediate model; Verifying the first intermediate model by using the first verification set to obtain a corresponding first error set, wherein the first error set includes at least one first error sample; If the number of the first error samples in the first error set is greater than or equal to the first preset threshold, the first intermediate model is trained by using the first error set to obtain a new first intermediate model; Verifying the new first intermediate model again by using the first verification set until the number of first error samples in the first error set is less than a preset threshold, and determining a new first intermediate model at this time The first preset detection model is corresponding. The method of claim 2, wherein the preset picture data further comprises preset second picture data, the method further comprising: Dividing the preset second picture data into a second training set and a second verification set; Training the second convolutional neural network with the second training set to obtain a corresponding second Model Verifying the second intermediate model by using the second verification set to obtain a corresponding second error set, wherein the second error set includes at least one second error sample; If the number of the second error samples in the second error set is greater than or equal to the second preset threshold, training the second intermediate model with the second error set to obtain a new second intermediate model; Using the second verification set to verify the new second intermediate model again, until the number of second error samples in the second error set is less than a preset threshold, and determining a new second intermediate model at this time The model is detected for the corresponding second preset. The method of claim 3 wherein said first convolutional neural network comprises an eight-layer structure, said second convolutional neural network comprises a twenty-layer structure, wherein said first convolutional neural network It includes five convolutional layers, two fully connected layers, and one probabilistic layer for two classifications. The method according to claim 1, wherein the inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information comprises: Inputting the pre-processed picture to be tested into the first preset detection model to obtain a confidence level; Determining whether the confidence level is greater than a preset threshold; Wherein, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information. A vehicle type identification device based on a convolutional neural network, characterized in that the device comprises: a processing unit, configured to preprocess the obtained picture to be tested; a determining unit, configured to input the pre-processed picture to be tested into a first preset detection model to determine whether the picture to be tested contains vehicle feature information; The input unit is configured to: if the picture to be tested contains vehicle feature information, input the pre-processed picture to be tested into a second preset detection model; a calculating unit, configured to calculate, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type; a determining unit, configured to determine a maximum probability value of all the probability values, and using the vehicle model corresponding to the maximum probability value as a model of the picture to be tested; The first preset detection model and the second preset detection model are respectively obtained by performing corresponding training on the convolutional neural network by using preset image data. The device of claim 6, wherein the preset picture data comprises preset first picture data, the device further comprising: a classifying unit, configured to divide the preset first picture data into a first training set and a first verification set; a training unit, configured to train the first convolutional neural network by using the first training set to obtain a corresponding first intermediate model; a verification unit, configured to verify, by using the first verification set, the first intermediate model to obtain a corresponding first error set, where the first error set includes at least one first error sample; And an adjusting unit, configured to: if the number of the first error samples in the first error set is greater than or equal to the first preset threshold, use the first error set to train the first intermediate model to obtain a new first intermediate model; a determining unit, configured to verify the new first intermediate model again by using the first verification set, until the number of the first error samples in the first error set is less than a preset threshold, and determining that the new time is The first intermediate model is a corresponding first preset detection model. The device according to claim 7, wherein the preset picture data further comprises preset second picture data, wherein The classifying unit is further configured to divide the preset second picture data into a second training set and a second verification set; The training unit is further configured to train the second convolutional neural network by using the second training set to obtain a corresponding second intermediate model; The verification unit is further configured to verify, by using the second verification set, the second intermediate model to obtain a corresponding second error set, where the second error set includes at least one second error sample; The adjusting unit is further configured to: if the number of second error samples in the second error set is greater than or equal to a second preset threshold, use the second error set to train the second intermediate model to obtain a new Second intermediate model; The determining unit is further configured to use the second verification set to verify the new second intermediate model again, until the number of the second error samples in the second error set is less than a preset threshold, and determine the The new second intermediate model is the corresponding second preset detection model. The apparatus according to claim 8, wherein said first convolutional neural network comprises an eight-layer structure, said second convolutional neural network comprises a twenty-layer structure, wherein said first convolutional neural network It includes five convolutional layers, two fully connected layers, and one probabilistic layer for two classifications. The apparatus according to claim 6, wherein said determining unit comprises: a confidence acquisition unit, configured to input the pre-processed picture to be input into the first preset detection model To a confidence level; a confidence determination unit, configured to determine whether the confidence level is greater than a preset threshold; Wherein, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information. A vehicle identification device based on a convolutional neural network, comprising: a memory for storing a program for realizing vehicle type recognition; a processor for running a program for realizing vehicle type identification stored in the memory to perform the following operations: Preprocessing the acquired picture to be tested; Inputting the pre-processed picture to be tested into a first preset detection model to determine whether the picture to be tested contains vehicle feature information; If the picture to be tested contains vehicle feature information, input the pre-processed picture to be input into the second preset detection model; Calculating, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type; Determining a maximum probability value among all the probability values, and using the vehicle model corresponding to the maximum probability value as the model of the picture to be tested; The first preset detection model and the second preset detection model are respectively obtained by performing corresponding training on the convolutional neural network by using preset image data. The device according to claim 11, wherein the preset picture data comprises preset first picture data, and before the pre-processing of the obtained picture to be tested, the method comprises: Dividing the preset first picture data into a first training set and a first verification set; Training the first convolutional neural network with the first training set to obtain a corresponding first intermediate model; Verifying the first intermediate model by using the first verification set to obtain a corresponding first error set, wherein the first error set includes at least one first error sample; If the number of the first error samples in the first error set is greater than or equal to the first preset threshold, the first intermediate model is trained by using the first error set to obtain a new first intermediate model; Verifying the new first intermediate model again by using the first verification set until the number of first error samples in the first error set is less than a preset threshold, and determining a new first intermediate model at this time The first preset detection model is corresponding. The device according to claim 12, wherein the preset picture data further includes preset second picture data, and the pre-processing of the acquired picture to be tested further includes: Dividing the preset second picture data into a second training set and a second verification set; Training the second convolutional neural network with the second training set to obtain a corresponding second intermediate model; Verifying the second intermediate model by using the second verification set to obtain a corresponding second error set, wherein the second error set includes at least one second error sample; If the number of the second error samples in the second error set is greater than or equal to the second preset threshold, training the second intermediate model with the second error set to obtain a new second intermediate model; Using the second verification set to verify the new second intermediate model again, until the number of second error samples in the second error set is less than a preset threshold, and determining a new second intermediate model at this time The model is detected for the corresponding second preset. The apparatus according to claim 13, wherein said first convolutional neural network comprises an eight-layer structure, said second convolutional neural network comprises a twenty-layer structure, wherein said first convolutional neural network It includes five convolutional layers, two fully connected layers, and one probabilistic layer for two classifications. The device according to claim 11, wherein the inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information comprises: Inputting the pre-processed picture to be tested into the first preset detection model to obtain a confidence level; Determining whether the confidence level is greater than a preset threshold; Wherein, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information. A computer readable storage medium, characterized in that the computer readable storage medium stores one or more programs, the one or more programs being executable by one or more processors to implement the following steps: Preprocessing the acquired picture to be tested; Inputting the pre-processed picture to be tested into a first preset detection model to determine whether the picture to be tested contains vehicle feature information; If the picture to be tested contains vehicle feature information, input the pre-processed picture to be input into the second preset detection model; Calculating, by using the second preset detection model, a probability value of the picture to be tested corresponding to each type of vehicle type; Determining a maximum probability value among all the probability values, and using the vehicle model corresponding to the maximum probability value as the model of the picture to be tested; The first preset detection model and the second preset detection model are respectively obtained by performing corresponding training on the convolutional neural network by using preset image data. The computer-readable storage medium according to claim 16, wherein the preset picture data comprises preset first picture data, and before the pre-processing of the acquired picture to be tested, the method comprises: Dividing the preset first picture data into a first training set and a first verification set; Training the first convolutional neural network with the first training set to obtain a corresponding first intermediate model; Verifying the first intermediate model by using the first verification set to obtain a corresponding first error set, wherein the first error set includes at least one first error sample; If the number of the first error samples in the first error set is greater than or equal to the first preset threshold, the first intermediate model is trained by using the first error set to obtain a new first intermediate model; Verifying the new first intermediate model again by using the first verification set until the number of first error samples in the first error set is less than a preset threshold, and determining a new first intermediate model at this time The first preset detection model is corresponding. The computer-readable storage medium according to claim 17, wherein the preset picture data further includes preset second picture data, and the pre-processing of the acquired picture to be tested further includes: Dividing the preset second picture data into a second training set and a second verification set; Training the second convolutional neural network with the second training set to obtain a corresponding second intermediate model; Verifying the second intermediate model by using the second verification set to obtain a corresponding second error set, wherein the second error set includes at least one second error sample; If the number of the second error samples in the second error set is greater than or equal to the second preset threshold, training the second intermediate model with the second error set to obtain a new second intermediate model; Using the second verification set to verify the new second intermediate model again, until the number of second error samples in the second error set is less than a preset threshold, and determining a new second intermediate model at this time The model is detected for the corresponding second preset. The computer readable storage medium of claim 18, wherein the first convolutional neural network comprises an eight-layer structure, and the second convolutional neural network comprises a twenty-layer structure, wherein the first The convolutional neural network consists of five convolutional layers, two fully connected layers, and one probabilistic layer for the two classifications. The computer readable storage medium according to claim 16, wherein the inputting the pre-processed picture to the first preset detection model to determine whether the picture to be tested contains vehicle feature information comprises: Inputting the pre-processed picture to be tested into the first preset detection model to obtain a confidence level; Determining whether the confidence level is greater than a preset threshold; Wherein, if the confidence level is greater than a preset threshold, the picture to be tested contains vehicle feature information.

Images