CN110458136B - Traffic sign identification method, device and equipment - Google Patents

Abstract

The present application discloses a traffic sign recognition method, device and device, wherein the method includes: acquiring an image of a traffic sign to be recognized; inputting the image of the traffic sign to be recognized into a trained deep belief network model for feature extraction to obtain the traffic sign to be recognized Mark the first feature vector corresponding to the image; convert the first feature vector into a first pulse sequence; input the first pulse sequence into the trained spiking neural network, and obtain the recognition result output by the trained spiking neural network. This application uses the combination of the deep belief network model and the spiking neural network for traffic sign recognition, which does not require manual feature extraction, greatly reduces manual intervention, and improves the recognition speed. By making full use of the deep belief network model and the spiking neural network The invention has the advantages of improving the recognition result and solving the technical problems of low accuracy and slow speed of the existing traffic sign recognition.

Description

A traffic sign recognition method, device and equipment

technical field

The present application relates to the technical field of image recognition, and in particular, to a traffic sign recognition method, device and device.

Background technique

Traffic signs are an important source of information obtained during vehicle driving. Accurate and rapid identification of traffic signs is of great significance for ensuring traffic safety, traffic order, and improving traffic efficiency.

The traditional traffic sign recognition method uses image matching, feature extraction and classifier combination for recognition, which requires more human intervention, and has the problems of low recognition accuracy and slow speed.

SUMMARY OF THE INVENTION

The present application provides a traffic sign recognition method, device and device, which are used to solve the technical problems of low accuracy and slow speed of existing traffic sign recognition.

In view of this, a first aspect of the present application provides a traffic sign recognition method, including:

Obtain the image of the traffic sign to be recognized;

Inputting the traffic sign image to be recognized into the trained deep belief network model for feature extraction to obtain a first feature vector corresponding to the traffic sign image to be recognized;

converting the first feature vector into a first pulse sequence;

The first pulse sequence is input into the trained spiking neural network, and the recognition result output by the trained spiking neural network is obtained.

Preferably, it also includes:

Obtain the traffic sign image set to be trained;

Inputting the to-be-trained traffic-sign images in the to-be-trained traffic-sign image set into the trained deep belief network model for feature extraction to obtain a second feature vector corresponding to the to-be-trained traffic sign images;

Converting the second eigenvector based on time-delay phase coding to obtain a second pulse sequence;

inputting the second pulse sequence into a spiking neural network to train the spiking neural network;

Calculate the recognition accuracy rate of the spiking neural network for the traffic sign image to be trained, when the recognition accuracy rate is higher than a threshold, the training is completed, and a trained spiking neural network is obtained.

Preferably, the to-be-trained traffic sign images in the to-be-trained traffic sign image set are input into the trained deep belief network model to perform feature extraction, and the second feature vector corresponding to the to-be-trained traffic sign images is obtained. Also includes:

Perform preprocessing on the traffic sign image to be trained.

Preferably, the preprocessing includes:

The size of the traffic sign image to be trained is normalized based on the bilinear interpolation algorithm, and the normalized traffic sign image to be trained is obtained.

Preferably, inputting the second pulse sequence into a spiking neural network, and training the spiking neural network, includes:

The second pulse sequence is input into a spiking neural network, and the spiking neural network is trained based on a learning method combining three-pulse STDP and threshold plasticity.

A second aspect of the present application provides a traffic sign recognition device, comprising:

a first image acquisition module, configured to acquire an image of a traffic sign to be recognized;

a first feature extraction module, configured to input the traffic sign image to be recognized into the trained deep belief network model for feature extraction, and obtain a first feature vector corresponding to the traffic sign image to be recognized;

a first conversion module for converting the first feature vector into a first pulse sequence;

The identification module is configured to input the first pulse sequence into the trained spiking neural network, and obtain the recognition result output by the trained spiking neural network.

Preferably, it also includes:

The second image acquisition module is used to acquire the traffic sign image set to be trained;

The second feature extraction module is used to input the to-be-trained traffic sign images in the to-be-trained traffic sign image set into the trained deep belief network model for feature extraction to obtain the second feature corresponding to the to-be-trained traffic sign images vector;

a second conversion module, configured to convert the second eigenvector based on time-delay phase coding to obtain a second pulse sequence;

a training module, configured to input the second pulse sequence into the spiking neural network, and train the spiking neural network;

The calculation module is used for calculating the recognition accuracy rate of the spiking neural network for the traffic sign image to be trained. When the recognition accuracy rate is higher than a threshold, the training is completed and a trained spiking neural network is obtained.

Preferably, it also includes:

The preprocessing module is used for preprocessing the traffic sign image to be trained.

A third aspect of the present application provides a traffic sign recognition device, characterized in that: the device includes a processor and a memory;

the memory is used to store program code and transmit the program code to the processor;

The processor is configured to execute the traffic sign recognition method according to any one of the first aspects according to the instructions in the program code.

A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, and the program codes are used to execute the traffic sign according to any one of the first aspect recognition methods.

As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

In this application, a traffic sign recognition method is provided, which includes: acquiring an image of a traffic sign to be recognized; inputting the image of the traffic sign to be recognized into a trained deep belief network model for feature extraction, and obtaining a corresponding image of the traffic sign to be recognized. The first feature vector; converting the first feature vector into a first pulse sequence; inputting the first pulse sequence into the trained spiking neural network to obtain the recognition result output by the trained spiking neural network. This application uses the trained deep belief network model to perform feature extraction on traffic sign images, and does not require manual feature extraction. The deep belief network model is used to perform feature dimension reduction and feature selection on the input traffic sign images, which greatly reduces manual intervention. High-level features are extracted from the original traffic sign image, and redundant noise information is filtered out, which helps to improve the recognition results of the subsequent spiking neural network. The combination of the deep belief network model and the spiking neural network is used to conduct traffic. Sign recognition improves the recognition speed. By making full use of the advantages of the deep belief network model and the spiking neural network, the recognition results are improved, and the existing technical problems of low accuracy and slow speed of traffic sign recognition are solved.

Description of drawings

1 is a schematic flowchart of an embodiment of a traffic sign recognition method provided by the application;

2 is a schematic flowchart of another embodiment of a traffic sign recognition method provided by the present application;

FIG. 3 is a schematic structural diagram of an embodiment of a traffic sign recognition device provided by the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

For ease of understanding, please refer to FIG. 1, an embodiment of a traffic sign recognition method provided by the present application, including:

Step 101, acquiring an image of a traffic sign to be recognized.

It should be noted that, since there may be images that do not meet the requirements in the acquired images, that is, there are images that do not contain traffic signs, in order not to affect the recognition results, the acquired images of traffic signs can be screened and filtered out. For some images that do not contain traffic signs and some blurred and unclear traffic sign images, the traffic sign images that meet the requirements are used as the final acquired traffic sign images to be recognized.

Step 102: Input the traffic sign image to be recognized into the trained deep belief network model for feature extraction, and obtain a first feature vector corresponding to the traffic sign image to be recognized.

It should be noted that the deep belief network (DBN) in this embodiment is composed of a two-layer deep Boltzmann machine (DBM) model and a two-layer DBN model, wherein the DBM model Both the Restricted Boltzmann Machine (RBM) model and the DBN model are based on the basic unit, the difference is that the DBM layers are undirected connections, while the DBN layers are directed connections.

The lower layer in the deep belief network model adopts the two-layer DBM with strong information reduction degree to perform preliminary dimensionality reduction on the traffic sign image to be recognized, and obtains the features after denoising and high integrity, and uses the obtained features as the input of the two-layer DBN. , and then extract higher-level features through a two-layer DBN. Through unsupervised training and supervised fine-tuning of DBM and DBN, respectively, a trained deep belief network model is finally obtained. Through the trained deep belief network model, the high-level features of the traffic sign image to be recognized are extracted, which helps to improve the subsequent pulse rate. The recognition result of the neural network.

Step 103: Convert the first feature vector into a first pulse sequence.

It should be noted that the input of the spiking neural network is represented by a pulse sequence, so it is necessary to convert the extracted first feature vector into a first pulse sequence, so as to be compatible with the subsequent use of the spiking neural network for traffic sign recognition, so that the spiking neural network can be used for traffic sign recognition. better identification.

Step 104: Input the first pulse sequence into the trained spiking neural network, and obtain the recognition result output by the trained spiking neural network.

It should be noted that the traditional artificial neural network encodes the pulse firing frequency of biological neurons. The output of the neuron is generally a simulation of a given interval, and its computing power and biological authenticity are weaker than those of the pulse neural network. A good spiking neural network for traffic sign recognition is beneficial to improve the recognition result. Therefore, in this embodiment, a trained spiking neural network is used for traffic sign recognition.

The applicant found that the method of combining image matching, feature extraction and classifier in the prior art requires a lot of manual intervention, and has the problems of low recognition accuracy and slow speed. Therefore, in order to solve these problems existing in the prior art, the applicant proposes the traffic sign recognition method provided in the embodiment of the present application, and the method achieves the following technical effects:

The traffic sign recognition method provided by the embodiment of the present application uses the trained deep belief network model to perform feature extraction on the traffic sign image without manual feature extraction, and performs feature dimension reduction and summation on the input traffic sign image through the deep belief network model. Feature selection, which greatly reduces manual intervention, extracts high-level features from the original traffic sign image, and filters out redundant noise information, which helps to improve the recognition results of subsequent spiking neural networks, using a deep belief network model The method of combining with the spiking neural network for traffic sign recognition improves the recognition speed. By making full use of the advantages of the deep belief network model and the spiking neural network, the recognition results are improved, and the existing traffic sign recognition accuracy is low and the speed is improved. Slow technical issues.

For ease of understanding, please refer to FIG. 2, another embodiment of a traffic sign recognition method provided by the present application, including:

Step 201: Obtain a traffic sign image set to be trained.

It should be noted that the to-be-trained traffic sign images of the to-be-trained traffic sign image set in this embodiment come from a German traffic sign recognition benchmark (GTSRB).

Step 202, preprocessing the to-be-trained traffic sign images in the to-be-trained traffic sign image set.

It should be noted that, in order to facilitate the feature extraction of the deep belief network, the size of the to-be-trained traffic sign images in the training traffic sign image set can be normalized, and the bilinear interpolation algorithm can be used to normalize the size of the to-be-trained traffic sign images. The normalized traffic sign images to be trained are of the same size, for example, the size is 48×48 or 28×28 pixels.

There are some blurred and large-area watermarked traffic sign images in the GTSRB database, which can be screened to filter out low-quality traffic sign images, leaving high-quality traffic sign images, which is conducive to the deep belief network to extract useful feature information , so as to improve the recognition results of the spiking neural network.

Step 203: Input the preprocessed traffic sign image to be trained into the trained deep belief network model for feature extraction to obtain a second feature vector corresponding to the traffic sign image to be trained.

Step 204: Convert the second eigenvector based on the time-delay phase encoding to obtain a second pulse sequence.

It should be noted that the commonly used encoding methods are time-delay encoding and phase encoding. In this embodiment, a combination of time-delay encoding and phase encoding is used to encode the extracted second eigenvector, namely, time-delay phase encoding, using time-delay phase encoding. Encoding can generate better spike trains, helping to improve the traffic sign recognition results of spiking neural networks.

Step 205 , input the second pulse sequence into the spiking neural network, and train the spiking neural network.

It should be noted that the spiking neural network in this embodiment uses LIF (Leaky Integrate-and-Fire) neurons, wherein the first layer is a competition layer, which is composed of multiple LIF neurons, and the neurons in the competition layer are The purpose of competitive learning is achieved by lateral inhibition. The lateral inhibition process is as follows: whenever a neuron bursts an action potential, the neuron will immediately reset to the initial state and enter the refractory period, while all other neurons Reset to the resting membrane potential and enter the inhibitory phase. Whenever a neuron emits a pulse, all neurons will reset, and then start to compete again, and learn through competition, so as to train the spiking neural network; the second layer of the spiking neural network is the output layer, and the output layer outputs the output of each category. Similarity value, the smaller the similarity value, the higher the similarity. The label of the class with the smallest similarity value is the final recognition result. The specific steps for calculating the similarity value are:

Assuming that the input image matrix is I=x _ij ∈R ^n×n , normalize the input image matrix, namely:

x′ _ij =(x _ij -x _min )/(x _max -x _min )

Among them, x _max and x _min are the maximum and minimum pixel values in I respectively, and x′ _ij is the input image after normalization.

其中，

为标签为L的第m个神经元，M_L为神经元的个数，L＝0,1,…,9；标签为L的第m个神经元对输入图像对应的脉冲序列发放的脉冲个数为

标签为L的第m个神经元对应的感受野权值矩阵为

将标签为L的M_L个神经元的脉冲个数与感受野权值进行乘累加，得到标签为L的神经元对输入图像的重构图像，即：Suppose that the neurons labeled L are denoted as

in,

is the mth neuron labelled L, _ML is the number of neurons, L=0,1,...,9; the number of pulses emitted by the mth neuron labelled L to the pulse sequence corresponding to the input image number is

The receptive field weight matrix corresponding to the mth neuron labeled L is:

Multiply and accumulate the number of pulses of the M _L neurons labeled L and the weight of the receptive field to obtain the reconstructed image of the input image by the neuron labeled L, namely:

Suppose R _L =r _ij ∈R ^n×n , perform normalization processing on it as well to obtain the reconstructed image r′ _ij after normalization processing, and calculate the similarity value between the input image after normalization processing and the reconstructed image after normalization processing S _L , the specific similarity value calculation formula is as follows:

Obtain 10 similarity values S ₀ , S ₁ ,…, S ₉ , compare the sizes of S ₀ , S ₁ ,…, S ₉ , the label of the class with the smallest similarity value is the final recognition result, assuming S ₆ is the smallest, Then the category represented by label 6 is the final recognition result.

The spiking neural network is trained by a learning method combining three-pulse STDP and threshold plasticity. The three-pulse STDP learning method is for synapses, while the threshold plasticity learning method is based on the threshold potential of neurons. Three-pulse STDP combined with threshold plasticity is used for training. The learning method limits the firing frequency of neurons.

Step 206: Calculate the recognition accuracy rate of the traffic sign image to be trained by the spiking neural network. When the recognition accuracy rate is higher than the threshold, the training is completed, and the trained spiking neural network is obtained.

It should be noted that the recognition accuracy is calculated by the ratio of the number of correctly identified traffic sign images to be trained to the number of all images to be trained. When the recognition accuracy is higher than the preset threshold, the training is considered complete and the training is stopped. Get the trained spiking neural network.

Step 207, acquiring the image of the traffic sign to be recognized.

Step 208: Input the traffic sign image to be recognized into the trained deep belief network model for feature extraction to obtain a first feature vector corresponding to the traffic sign image to be recognized.

Step 209: Convert the first feature vector into a first pulse sequence.

Step 210: Input the first pulse sequence into the trained spiking neural network, and obtain the recognition result output by the trained spiking neural network.

It should be noted that, steps 207 to 210 in this embodiment of the present application are consistent with steps 101 to 104 in the previous embodiment, and details are not repeated here.

For ease of understanding, please refer to FIG. 3 , an embodiment of a traffic sign recognition device provided by the present invention includes:

a first image acquisition module 301, configured to acquire an image of a traffic sign to be recognized;

The first feature extraction module 302 is configured to input the traffic sign image to be recognized into the trained deep belief network model for feature extraction to obtain the first feature vector corresponding to the traffic sign image to be recognized;

a first conversion module 303, configured to convert the first feature vector into a first pulse sequence;

The identification module 304 is configured to input the first pulse sequence into the trained spiking neural network, and obtain the recognition result output by the trained spiking neural network.

Further, it also includes:

The second image acquisition module 305 is configured to acquire the traffic sign image set to be trained;

The second feature extraction module 306 is configured to input the to-be-trained traffic sign images in the to-be-trained traffic sign image set into the trained deep belief network model for feature extraction, and obtain a second feature vector corresponding to the to-be-trained traffic sign images;

The second conversion module 307 is configured to convert the second eigenvector using time-delay phase coding to obtain a second pulse sequence;

A training module 308, configured to input the second pulse sequence into the spiking neural network to train the spiking neural network;

The calculation module 309 is used to calculate the recognition accuracy rate of the traffic sign image to be trained by the spiking neural network. When the recognition accuracy rate is higher than the threshold, the training is completed and the trained spiking neural network is obtained.

Further, it also includes:

The preprocessing module 310 is used for preprocessing the traffic sign images to be trained.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for executing all or part of the steps of the methods described in the various embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage media include: U disk, mobile hard disk, read-only memory (full English name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks Or various media such as optical discs that can store program codes.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (10)

1. A traffic sign recognition method, comprising:

acquiring a traffic sign image to be identified;

inputting the traffic sign image to be recognized into a trained deep belief network model for feature extraction to obtain a first feature vector corresponding to the traffic sign image to be recognized;

converting the first feature vector into a first pulse sequence;

inputting the first pulse sequence into a trained pulse neural network, obtaining a recognition result output by the trained pulse neural network, specifically, inputting the first pulse sequence into the trained pulse neural network, issuing pulses to the first pulse sequence through neurons corresponding to each label in the trained pulse neural network, multiplying and accumulating the number of pulses issued by the neurons of the same label and a corresponding receptive field weight matrix to obtain a reconstructed image of the traffic sign image to be recognized by the neurons corresponding to each label, and calculating similarity values of the traffic sign image to be recognized after the standardization processing and the reconstructed image after the standardization processing, wherein the label with the smallest similarity value is the final recognition result;

wherein, the acquisition formula of the reconstructed image is as follows:

；

in the formula,R _L is a label ofLThe neurons of the image data to be identified are reconstructed images of the traffic sign image,

is a label ofLTo (1) amThe number of the nerve cells is one,

is a label ofLThe number of the neurons of (a) is,

is a label of

To (1)

The number of pulses issued by the first pulse sequence corresponding to the traffic sign image to be recognized by each neuron,

is a label of

To (1) a

A receptive field weight matrix corresponding to each neuron;

the calculation formula of the similarity value is as follows:

；

in the formula,S _L for standardized traffic sign images to be recognized

And a label ofLThe reconstructed image after the normalization processing corresponding to the neuron

The similarity value of (a) is calculated,nfor the row number and the column number of the traffic sign image to be identified or the reconstructed image after the standardization processing,i、jrespectively the row coordinate value and the column coordinate value of the pixel points in the traffic sign image to be recognized or the reconstructed image after the standardization treatment.

2. The traffic sign recognition method of claim 1, further comprising:

acquiring a traffic sign image set to be trained;

inputting the traffic sign images to be trained in the traffic sign image set to be trained into a trained deep belief network model for feature extraction to obtain second feature vectors corresponding to the traffic sign images to be trained;

converting the second eigenvector based on time-lag phase coding to obtain a second pulse sequence;

inputting the second pulse sequence into a pulse neural network, and training the pulse neural network;

and calculating the recognition accuracy rate of the impulse neural network to the traffic sign image to be trained, and finishing training when the recognition accuracy rate is higher than a threshold value to obtain the trained impulse neural network.

3. The method for recognizing a traffic sign according to claim 2, wherein the step of inputting the traffic sign image to be trained in the traffic sign image set to be trained into a trained deep belief network model for feature extraction to obtain a second feature vector corresponding to the traffic sign image to be trained further comprises:

and preprocessing the traffic sign image to be trained.

4. The traffic sign recognition method of claim 3, wherein the preprocessing comprises:

and carrying out size normalization processing on the traffic sign image to be trained based on a bilinear interpolation algorithm to obtain the traffic sign image to be trained after normalization processing.

5. The method of claim 2, wherein the inputting the second pulse sequence into a spiking neural network, training the spiking neural network, comprises:

inputting the second pulse sequence into a pulse neural network, and training the pulse neural network based on a learning method of combining three-pulse STDP and threshold plasticity.

6. A traffic sign recognition apparatus, comprising:

the first image acquisition module is used for acquiring a traffic sign image to be identified;

the first feature extraction module is used for inputting the traffic sign image to be recognized into a trained deep belief network model for feature extraction to obtain a first feature vector corresponding to the traffic sign image to be recognized;

a first conversion module for converting the first feature vector into a first pulse sequence;

the identification module is configured to input the first pulse sequence into the trained impulse neural network, obtain an identification result output by the trained impulse neural network, specifically, input the first pulse sequence into the trained impulse neural network, issue pulses to the first pulse sequence through neurons corresponding to each label in the trained impulse neural network, multiply and accumulate the number of pulses issued by neurons of the same label and a corresponding receptive field weight matrix to obtain a reconstructed image of the to-be-identified traffic sign image by the neurons corresponding to each label, and calculate similarity values of the to-be-identified traffic sign image after the normalization processing and the reconstructed images after the normalization processing, where a label with a smallest similarity value is a final identification result;

wherein, the acquisition formula of the reconstructed image is as follows:

；

in the formula,R _L is a label ofLThe neuron of (2) reconstructs an image of the traffic sign image to be recognized,

is a label ofLTo (1) amThe number of the nerve cells is one,

is a label ofLThe number of the neurons in the neural network,

is a label of

To (1) a

The number of pulses emitted by the first pulse sequence corresponding to the traffic sign image to be identified by each neuron,

is a label of

To (1) a

A receptive field weight matrix corresponding to each neuron;

the calculation formula of the similarity value is as follows:

；

in the formula,S _L for standardized traffic sign images to be recognized

And a label ofLThe reconstructed image after the normalization processing corresponding to the neuron

The similarity value of (a) is calculated,nthe number of rows and columns of the traffic sign images to be identified or the reconstructed images after the standardization processing,i、jrespectively the row coordinate value and the column coordinate value of the pixel points in the traffic sign image to be recognized or the reconstructed image after the standardization treatment.

7. The traffic sign recognition device of claim 6, further comprising:

the second image acquisition module is used for acquiring a traffic sign image set to be trained;

the second feature extraction module is used for inputting the traffic sign images to be trained in the traffic sign image set to be trained into the trained deep belief network model for feature extraction to obtain second feature vectors corresponding to the traffic sign images to be trained;

the second conversion module is used for converting the second characteristic vector based on time-lag phase coding to obtain a second pulse sequence;

the training module is used for inputting the second pulse sequence into a pulse neural network and training the pulse neural network;

and the calculation module is used for calculating the recognition accuracy of the impulse neural network on the traffic sign image to be trained, and when the recognition accuracy is higher than a threshold value, the training is completed to obtain the trained impulse neural network.

8. The traffic sign recognition device of claim 7, further comprising:

and the preprocessing module is used for preprocessing the traffic sign image to be trained.

9. A traffic sign recognition apparatus, comprising: the apparatus includes a processor and a memory;

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to execute the traffic sign recognition method according to any one of claims 1 to 5 according to instructions in the program code.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium is configured to store a program code for executing the traffic sign recognition method according to any one of claims 1-5.

Images