CN111435565A - Road traffic state detection method, road traffic state detection device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the application provides a road traffic state detection method, a road traffic state detection device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring target image data of a road to be detected; determining the image position of each vehicle in the target image data by using a computer vision technology; determining the actual geographic position of each vehicle in the road to be detected according to the image position of each vehicle in the target image data; and determining the traffic state of the road to be detected according to the actual geographical position of each vehicle. In the road traffic state detection method of the embodiment of the application, the actual geographic position of each vehicle in the road to be detected is determined by using the image data of the road to be detected, and each vehicle in the road to be detected can be counted, so that the traffic state of the road to be detected is evaluated.

Description

Road traffic state detection method, device, electronic device and storage medium

technical field

The present application relates to the technical field of traffic monitoring, and in particular, to a road traffic state detection method, device, electronic device and storage medium.

Background technique

With the increase in car ownership, traffic congestion and other situations also occur frequently, especially during the rush hour, and the problem of traffic congestion is becoming more and more serious. Detecting road traffic conditions can help people avoid congested routes and relieve traffic congestion pressure.

In the related art, road traffic conditions are detected by detecting the speed of vehicles on the road. Specifically, a detection point is set on a designated road, and the average driving speed of vehicles passing through the detection point within a period of time is checked. When the average driving speed of the vehicle is lower than a certain threshold, it is determined that the designated road is congested.

However, with the above method, under special environmental conditions, such as rainy days or heavy fog, the vehicle's driving speed may also be lower than the set threshold, but the road congestion is not congested at this time, so the above method will generate traffic. False alarms of congestion and low accuracy of road traffic state detection.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a road traffic state detection method, device, electronic device, and storage medium, so as to increase the accuracy of traffic state detection. The specific technical solutions are as follows:

In a first aspect, an embodiment of the present application provides a method for detecting a road traffic state, the method comprising:

Obtain the target image data of the road to be detected;

Using computer vision technology, determine the image position of each vehicle in the target image data;

Determine the actual geographic location of each vehicle on the road to be detected according to the image position of each vehicle in the target image data;

According to the actual geographic location of each vehicle, the traffic state of the road to be detected is determined.

Optionally, the acquiring image data of the road to be detected includes:

Obtain the images of each section of the road to be detected collected by each lens;

The images of each of the road sections are spliced to obtain target image data of the road to be detected.

Optionally, determining the actual geographic location of each vehicle on the road to be detected according to the image position of each vehicle in the target image data includes:

According to the predetermined correspondence between each position in the image data and the latitude and longitude on the actual road, the image position of the vehicle in the target image data is mapped to the latitude and longitude of each vehicle on the actual road to obtain each The actual geographic location of the vehicle on the road to be detected.

Optionally, the step of predetermining the correspondence between each position in the image data and the latitude and longitude of the actual road includes:

Obtain the latitude and longitude of multiple specified calibration points in the actual road;

determining the position of each of the designated calibration points in the image data;

According to the latitude and longitude of each designated calibration point and the position of the designated calibration point in the image data, the corresponding relationship between each position in the image data and the latitude and longitude in the actual road is determined.

Optionally, determining the traffic state of the road to be detected according to the actual geographic location of each vehicle includes:

According to the actual geographic location of each vehicle, the traffic state of each lane in the road to be detected is determined.

Optionally, the road traffic state detection method in the embodiment of the present application further includes:

The actual geographic location of each vehicle is displayed on the electronic map according to a preset display frequency, wherein the preset display frequency is not greater than the frame rate of the target image data.

Optionally, the road traffic state detection method in the embodiment of the present application further includes:

separately marking each of said vehicles with a unique identification;

Each of the vehicles is tracked according to the identification of each of the vehicles.

In a second aspect, an embodiment of the present application provides a road traffic state detection device, the device comprising:

The target image acquisition module is used to acquire the target image data of the road to be detected;

a target image analysis module, used for determining the image position of each vehicle in the target image data by using computer vision technology;

a vehicle position determination module, configured to determine the actual geographic location of each vehicle on the road to be detected according to the image position of each vehicle in the target image data;

The traffic condition analysis module is used for determining the traffic condition of the road to be detected according to the actual geographic location of each vehicle.

Optionally, the target image acquisition module includes:

The road segment image acquisition sub-module is used to acquire the images of each road segment in the road to be detected collected by each lens respectively;

The target image synthesis sub-module is used for splicing the images of each road section to obtain target image data of the road to be detected.

Optionally, the vehicle position determination module is specifically used for:

According to the predetermined correspondence between each position in the image data and the latitude and longitude on the actual road, the image position of the vehicle in the target image data is mapped to the latitude and longitude of each vehicle on the actual road to obtain each The actual geographic location of the vehicle on the road to be detected.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

The calibration point position acquisition module is used to obtain the latitude and longitude of multiple designated calibration points in the actual road;

an image data analysis module for determining the position of each designated calibration point in the image data;

The second correspondence determination module is configured to determine the correspondence between each position in the image data and the latitude and longitude in the actual road according to the latitude and longitude of each designated calibration point and the position of the designated calibration point in the image data.

Optionally, the traffic condition analysis module is specifically used for:

According to the actual geographic location of each vehicle, the traffic state of each lane in the road to be detected is determined.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

The vehicle position display module is configured to display the actual geographic location of each vehicle on the electronic map according to a preset display frequency, wherein the preset display frequency is not greater than the frame rate of the target image data.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

a vehicle calibration module for marking each vehicle with a unique identifier;

A vehicle tracking module, configured to track each of the vehicles according to the identifiers of the vehicles.

In a third aspect, an embodiment of the present application further provides an electronic device, including a processor and a memory;

the memory for storing computer programs;

The processor is configured to implement the road traffic state detection method according to any one of the first aspect above when executing the program stored in the memory.

In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the above-mentioned first aspect is implemented The road traffic state detection method.

The road traffic state detection method, device, electronic device, and storage medium provided by the embodiments of the present application acquire target image data of the road to be detected; use computer vision technology to determine the image position of each vehicle in the target image data; The image location in the image data determines the actual geographic location of each vehicle on the road to be detected; the traffic state of the road to be detected is determined according to the actual geographic location of each vehicle. Using the image data of the road to be detected, the actual geographical location of each vehicle on the road to be detected can be determined, and the statistics of each vehicle on the road to be detected can be counted, so as to evaluate the traffic status of the road to be detected, compared to the speed of a single detection point. Analysis can increase the accuracy of traffic state detection. At the same time, the actual geographical location of each vehicle can be obtained. When a traffic problem occurs, the location of the traffic problem can be reported to help the relevant departments manage the traffic order. The vehicle flow on the road to be detected can be known in detail, which is beneficial to formulate a more reasonable traffic plan. Of course, implementing any product or method of the present application does not necessarily require achieving all of the advantages described above at the same time.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

1 is a schematic diagram of a road traffic state detection method according to an embodiment of the present application;

2 is a schematic diagram of an image captured by a dual-lens camera according to an embodiment of the present application;

3 is a schematic diagram of calculating a latitude and longitude distance according to an embodiment of the application;

4 is another schematic diagram of a road traffic state detection method according to an embodiment of the present application;

5 is a schematic diagram of a road traffic state detection device according to an embodiment of the present application;

6 is a schematic diagram of an electronic device according to an embodiment of the application;

FIG. 7 is a schematic diagram of an electronic map according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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.

In order to improve the accuracy of traffic state detection, an embodiment of the present application provides a road traffic state detection method, see FIG. 1 , the method includes:

S101, acquiring target image data of a road to be detected.

The road traffic state detection method in the embodiment of the present application may be implemented by a detection device, and specifically, the detection device may be a camera or a server.

The detection device obtains the target image data of the road to be detected through the camera, and the target image data may be a video stream. For the road to be detected, in order to improve the identifiability of the image data, a multi-lens camera can be used to collect image data, of course, a single-lens camera with high resolution performance can also be used, or the road to be detected can be set at a specified distance every interval A single-lens camera. The detection device acquires the target image data of the road to be detected, for example, collects images of each segment of the road to be detected through a plurality of single-lens cameras, and splices the images to obtain the target image data. Of course, the detection device can also directly use the image collected by the high-resolution monocular camera as the target image data.

Optionally, obtaining the image data of the road to be detected above includes:

S1011 , acquiring images of each road section in the road to be detected that are collected by each lens respectively.

S1012, splicing the images of the above road sections to obtain the target image data of the road to be detected.

The detection device can separately collect images of different sections of the road to be detected through each lens of the multi-lens camera, or can separately collect images of different sections of the road to be detected through the lenses of multiple single-lens cameras. The detection device splices the images of each road section according to the position of the actual road (the actual road to be detected) to obtain image data of the road to be detected. Or the multi-lens camera transmits the collected images of each road section to the server, and the server completes the splicing of the target image data. In a possible implementation, as shown in FIG. 2, the multi-lens camera can be a dual-lens camera, which can cover the detection area of L+N meters on the road, and the detection distance is long; the dual-lens camera can be set up in the middle of the road. On the pole, the pole height is M meters. The two lenses of the dual-lens camera have different focal lengths and resolutions. The lens with a large focal length and a relatively low resolution covers N meters in the near distance, and the other lens is responsible for the distance L meters, so that (L +N) Seamless detection of meters. Wherein, L, N, and M can be set according to the actual collection scene, and their values are not limited here. The use of binocular lenses, one fixed focus and one zoom, not only ensures ultra-long distance detection, but also ensures the pixel size and clarity of distant vehicle targets.

S102, using a computer vision technology, determine the image position of each vehicle in the target image data.

The detection device uses computer vision technology to analyze the target image data, detects each vehicle in the target image data, and calibrates the position of each vehicle in the target image data, thereby determining the position of each vehicle in the target image data. The computer vision technology is any related technology that utilizes a computer to calibrate the vehicle position, for example, it can be a convolutional neural network used for vehicle position calibration, and the like.

S103: Determine the actual geographic location of each of the above-mentioned vehicles on the above-mentioned road to be detected according to the image positions of each of the above-mentioned vehicles in the above-mentioned target image data.

The detection device obtains the actual geographic location of each vehicle on the road to be detected according to the position of each vehicle in the target image. For example, the detection device converts the coordinates of each vehicle in the image data coordinate system (that is, the coordinate system of the image acquisition device that collects the target image data) into the coordinates of each vehicle in the coordinate system of the road to be detected, so as to determine whether each vehicle is in the to-be-detected road coordinate system. Detect the actual geographic location in the road.

The coordinates of the target image data can be converted into coordinates in the actual road according to the device parameters of the camera that collects the target image data. Obtain the GPS (Global Positioning System, global positioning system) positioning information of the camera that collects the target image data. In order to ensure the calculation accuracy, the accuracy of the GPS positioning information is within decimeters, and the camera GPS positioning information can be obtained through the GPS device in the camera. Obtain the pitch angle of the camera (which can be detected by the built-in gyroscope of the camera) and erection height, and calculate the camera image coordinate system to the actual road (real world) through GPS, pitch angle, field of view, erection height and focal length and other information. ) coordinate system conversion formula. Coordinate transformation can also be performed by manual calibration, that is, selecting multiple reference points in the image, and measuring the GPS information of these reference points in the actual road, establishing the positional relationship between the GPS information and the reference points in the image, and determining according to the relationship. GPS information for each location in the image. The above method is aimed at the scene where the target image data is collected by a single camera. When the target image data is spliced from multiple images, it is necessary to perform the coordinate system conversion calculation for each image separately, and the calculation method for each image to perform the coordinate system conversion. The calculation method of the coordinate system transformation is the same as or similar to the above, and will not be repeated here.

S104: Determine the traffic state of the road to be detected according to the actual geographic location of each vehicle.

The detection equipment analyzes the actual geographic location of each vehicle, and determines the number of vehicles on the road to be detected, the length of the vehicle queue, and the road space occupancy rate, so as to obtain the traffic status of the road to be detected.

In the embodiment of the present application, the image data of the road to be detected is used to determine the actual geographic location of each vehicle on the road to be detected, and the statistics of each vehicle on the road to be detected can be counted, so as to evaluate the traffic state of the road to be detected. Analysis of the vehicle speed at a single detection point can increase the accuracy of traffic state detection. At the same time, the actual geographical location of each vehicle can be obtained. When a traffic problem occurs, the location of the traffic problem can be reported to help the relevant departments manage the traffic order. The vehicle flow on the road to be detected can be known in detail, which is beneficial to formulate a more reasonable traffic plan.

Optionally, the above-mentioned determining the traffic state of the above-mentioned road to be detected according to the actual geographical location of each of the above-mentioned vehicles includes:

The traffic state of each lane in the road to be detected is determined according to the actual geographic location of each vehicle.

In the embodiment of the present application, data such as the traffic flow, lane congestion degree, vehicle queue length, lane space occupancy rate of each lane on the road to be detected can also be determined according to the actual geographical location of the vehicle, so as to obtain each lane on the road to be detected. traffic status. Compared with the traffic state of the road, the traffic state of each lane is more precise and can be used to formulate a more reasonable traffic plan.

Optionally, the road traffic state detection method in the embodiment of the present application further includes:

The actual geographic location of each vehicle is displayed on the electronic map according to a preset display frequency, wherein the preset display frequency is not greater than the frame rate of the target image data.

The detection device periodically displays the actual geographic location of each vehicle on the electronic map according to the preset display frequency. The preset display frequency can be set according to actual requirements. The display frequency should not be greater than the frame rate of the target image data. This is because when the display frequency is greater than the frame rate of the target image data, it will cause the actual geographic location of the vehicle with the same frame of target image data. Repeated display in the electronic map wastes display performance. In one embodiment, the preset display frequency may be the same as the frame rate of the target image data, and the detection device sends the GPS information of the vehicle in each frame of the target image data to the electronic map for display. The message displays a preset emblem at the corresponding location, which represents the vehicle. The data of each frame is sent in real time, the electronic map displays the simulated vehicle position in real time, and the dynamic animation effect is displayed on the platform. The animation effect simulates the movement changes of the vehicle in the real environment.

The electronic map of the embodiment of the present application may be shown in FIG. 7 , in which the position of each vehicle is marked in real time in the two-dimensional plane map of the road to be detected; the electronic map may be a three-dimensional three-dimensional map, and the road and the vehicle to be detected are displayed in three-dimensional three-dimensional, In order to facilitate the operation, the existing map software, such as Baidu Map or AutoNavi Map, can be combined to display the position of each vehicle in the existing map software. Of course, the electronic map can also be surveyed and mapped by itself according to the actual scene of the road to be detected, which will not be repeated here.

Specifically, the detection device can be a platform server. The platform server can obtain the traffic status of the road to be detected, and can also obtain traffic data such as the traffic status of each lane on the road to be detected and the tracking results of each vehicle, and import the traffic data into the electronic map. . Therefore, the traffic conditions of various roads in the city can be seen through the electronic map, including the specific GPS information of road congestion points and the specific vehicles that cause congestion.

Optionally, the road traffic state detection method in the embodiment of the present application further includes:

In step 1, each of the above vehicles is marked with a unique identifier.

In the process of determining the position of each vehicle in the target image data using computer vision technology, each vehicle can also be marked, and a unique identifier is assigned to each vehicle.

In step 2, each of the above-mentioned vehicles is tracked according to the identification of each of the above-mentioned vehicles.

The vehicle identification can facilitate the tracking of the vehicle, for example, click the logo of a certain vehicle on the platform, and then display the driving track of the vehicle. The identification can be assigned a unique identification of the vehicle by the camera by identifying the characteristics of the vehicle and associating the unique identification with the GPS location information of the vehicle. Based on the identification of each vehicle, in the subsequent monitoring video stream, each vehicle is tracked, and parameters such as the speed and driving route of each vehicle are determined, thereby facilitating traffic management and planning.

Optionally, determining the actual geographic location of each of the above-mentioned vehicles on the above-mentioned road to be detected according to the image position of each of the above-mentioned vehicles in the above-mentioned target image data, including:

Step 1: Determine the image coordinates of each of the above-mentioned vehicles in the above-mentioned target image data according to the image position of each of the above-mentioned vehicles in the above-mentioned target image data.

Step 2: According to the image coordinates and the field of view angle of the image acquisition device, determine the PT coordinates when the image acquisition device is facing the vehicle as the first P coordinate and the first T coordinate.

The image acquisition device is a device that collects target image data. Here, the target image data is captured by a single lens as an example for illustration. (When the target image data consists of multiple sub-images, the calculation can be performed for each sub-image respectively, and for each sub-image The calculation method is the same as the calculation method when the target image data is acquired by a single lens). Specifically, in this embodiment, the image acquisition device is a dome camera with an adjustable monitoring range, and the dome camera coordinate system is usually PTZ (Pan/Tilt/ Zoom, PTZ left/right movement and lens zoom, zoom control) coordinate system. For the convenience of description, the P coordinate when the dome camera shoots the vehicle is called the first P coordinate, and the T coordinate when the dome camera shoots the vehicle is called the first T coordinate.

Step 3: Obtain the P coordinate when the image acquisition device points in the specified direction, as the second P coordinate.

Through the electronic compass of the dome camera, you can obtain the dome camera P coordinates when the dome camera points to the north, south, east, west and other directions. In order to distinguish the description, the dome camera P coordinate is called the second P coordinate.

Step 4: Calculate the difference between the first P coordinate and the second P coordinate as the horizontal angle between the vehicle and the designated direction.

Step 5: Calculate the horizontal distance between the vehicle and the image capture device based on the first T coordinate and the installation height of the image capture device.

The product of the tangent value of the first T coordinate and the height of the dome camera can be calculated as the horizontal distance between the vehicle and the dome camera. Among them, tanT*h=L, h represents the height of the dome camera, and L represents the horizontal distance between the vehicle and the dome camera. The horizontal distance is the distance between the dome camera and the vehicle, assuming the height of the dome camera and the vehicle is the same.

Step 6: Calculate the latitude and longitude distance between the vehicle and the image acquisition device by using a trigonometric function according to the horizontal angle and the horizontal distance.

In one embodiment, the designated direction in the above-mentioned step 3 is true north, and the product of the sine value of the above-mentioned horizontal angle and the above-mentioned horizontal distance is calculated at this time as the longitude distance between the above-mentioned monitoring target and the above-mentioned ball camera; calculate the above-mentioned horizontal clip. The product of the cosine value of the angle and the above-mentioned horizontal distance is used as the latitude distance between the above-mentioned monitoring target and the above-mentioned dome camera. For example, as shown in Figure 3, the height of the dome camera is not reflected in Figure 3. It can be seen from Figure 3 that L*sinθ=L _lon , L*cosθ=L _lat , L represents the above-mentioned horizontal distance, and θ represents the level between the vehicle and the true north direction. Included angle, L _lon represents the longitude distance between the monitoring target and the dome camera, and L _lat represents the latitude distance between the monitoring target and the dome camera.

Or, the specified direction in the above step 3 is due east, at this time, calculate the product of the cosine value of the horizontal angle and the horizontal distance as the longitude distance between the monitoring target and the dome camera; calculate the horizontal distance The product of the sine of the included angle and the horizontal distance is used as the latitude distance between the monitoring target and the dome camera. The horizontal included angle between the vehicle and the due east direction is α in FIG. 3 , L*sinα=L _lon , and L*cosα=L _lat .

The specified direction is due west or due south. The specific calculation process is similar and will not be repeated here.

Step 7: Calculate the longitude and latitude position of the vehicle based on the longitude and latitude of the image acquisition device and the longitude and latitude distance.

In the embodiment of the present application, a method for determining the actual geographic location of each vehicle on the road to be detected according to the position of each vehicle in the target image data is given when the image acquisition device is a dome camera, so as to facilitate the determination of the actual location of each vehicle. geographic location.

Optionally, determining the actual geographic location of each of the above-mentioned vehicles on the above-mentioned road to be detected according to the image position of each of the above-mentioned vehicles in the above-mentioned target image data, including:

According to the predetermined correspondence between each position in the image data and the latitude and longitude on the actual road, the image position of the above vehicle in the above target image data is mapped to the latitude and longitude of each above vehicle on the actual road. Detect the actual geographic location in the road.

It is also possible to pre-establish the correspondence between each position in the image data and the latitude and longitude of the actual road. For example, when the image acquisition device that collects the image is a gun, in view of the fixed shooting angle of the gun, the positions in the image data and the latitude and longitude of the actual road are pre-established. The corresponding relationship can be directly converted according to the corresponding relationship when conversion is required, which can save computing resources.

Optionally, the step of predetermining the correspondence between each position in the image data and the latitude and longitude of the actual road includes:

Step 1: Obtain the device parameters of the image capture device, wherein the device parameters of the image capture device include the focal length, lens angle, field angle, installation height, and latitude and longitude of the image capture device.

Step 2, according to the focal length, lens angle, field of view and erection height of the image capturing device, calculate the target distance between the target road area where the image capturing device collects image data and the image capturing device.

Step 3: Calculate the longitude and latitude of the target road area according to the longitude and latitude of the image acquisition device and the target distance.

Step 4: Map the latitude and longitude of the target road area to the image data to obtain the correspondence between each position in the image data and the latitude and longitude of the actual road.

In this embodiment of the present application, the distance between each position in the monitoring area of the image acquisition device (that is, the target road area) from the image acquisition device (that is, the target distance) can be calculated by mathematical methods, and then according to the latitude and longitude of the image acquisition device and the target distance , determine the latitude and longitude of each position in the target road area, map the latitude and longitude of each position in the target road area with the image data coordinate system, and obtain the corresponding relationship between each position in the image data and the latitude and longitude in the actual road.

Optionally, the step of predetermining the correspondence between each position in the image data and the latitude and longitude of the actual road includes:

Step 1: Obtain the longitude and latitude of multiple designated calibration points in the actual road.

Select a highly recognizable object in the actual road as the designated calibration point, and measure the latitude and longitude of each designated calibration point.

Step 2: Determine the position of each of the above-mentioned designated calibration points in the image data.

The image data of the actual road is collected by the gun, wherein the image data includes the images of each designated calibration point. The position of each designated calibration point is calibrated in the image data.

Step 3: According to the latitude and longitude of each designated calibration point and the position of the designated calibration point in the image data, determine the correspondence between the positions in the image data and the latitude and longitude in the actual road.

According to the corresponding relationship between the actual road and each designated calibration point in the image data, according to the longitude and latitude of each designated calibration point through affine transformation and other methods, the longitude and latitude of each point in the image data are calculated, so as to obtain the position in the image data and the actual road. Correspondence between latitude and longitude.

In the embodiment of the present application, when the camera is used to collect images, the corresponding relationship between each position in the image data and the latitude and longitude of the actual road is established by the method of calibration point mapping, and the calculation is simple.

An embodiment of the present application further provides a road traffic state detection system, see FIG. 4 , including a camera and a server.

The camera is used to: collect image data of the road to be detected; it is helpful for computer vision technology to detect the vehicle position in the image data; calculate the GPS information of the vehicle according to the vehicle position in the image data; according to the GPS information of each vehicle, count the lanes on the road to be detected According to the traffic conditions of each lane, determine whether the lane is congested; for the congested lane, send the GPS location of the congested lane, the congestion length and the queue length to the server. etc.; send GPS information of each vehicle to the server.

The server is used to: receive the GPS information of each vehicle, the GPS position of the congested lane, the length of the congestion, the length of the queue, etc., and display the received data in the electronic map.

The embodiment of the present application also provides a road traffic state detection device, see FIG. 5 , the device includes:

A target image acquisition module 501, configured to acquire target image data of the road to be detected;

A target image analysis module 502, configured to use computer vision technology to determine the image positions of each vehicle in the above target image data;

a vehicle position determination module 503, configured to determine the actual geographic location of each of the above-mentioned vehicles on the above-mentioned road to be detected according to the image positions of each of the above-mentioned vehicles in the above-mentioned target image data;

The traffic condition analysis module 504 is configured to determine the traffic condition of the road to be detected according to the actual geographic location of each vehicle.

Optionally, the above-mentioned target image acquisition module 501 includes:

The road section image acquisition sub-module is used to collect the images of each road section in the road to be detected through each lens of the multi-lens camera;

The target image synthesis sub-module is used for splicing the images of the above-mentioned road sections to obtain the above-mentioned target image data of the road to be detected.

Optionally, the above-mentioned vehicle position determination module 503 includes:

a first coordinate determination sub-module, configured to determine the image coordinates of each of the above-mentioned vehicles in the above-mentioned target image data according to the position of each of the above-mentioned vehicles in the above-mentioned target image data;

The second coordinate determination submodule is configured to determine the PT coordinates when the image acquisition device is facing the vehicle according to the image coordinates and the field of view angle of the image acquisition device, as the first P coordinate and the first T coordinate;

The third coordinate determination submodule is used to obtain the P coordinate when the above-mentioned image acquisition device points to the specified direction, as the second P coordinate;

a horizontal included angle determination submodule, configured to calculate the difference between the first P coordinate and the second P coordinate as the horizontal included angle between the vehicle and the specified direction;

a horizontal distance determination submodule, configured to calculate the horizontal distance between the vehicle and the image capture device based on the first T coordinate and the installation height of the image capture device;

a latitude and longitude distance determination submodule, configured to calculate the latitude and longitude distance between the vehicle and the image acquisition device through trigonometric functions according to the horizontal angle and the horizontal distance;

The latitude and longitude position determination sub-module is configured to calculate the latitude and longitude position of the vehicle based on the latitude and longitude of the image acquisition device and the latitude and longitude distance.

Optionally, the above-mentioned vehicle position determination module 503 is specifically used for:

According to the predetermined correspondence between each position in the image data and the latitude and longitude on the actual road, the image position of the above vehicle in the above target image data is mapped to the latitude and longitude of each above vehicle on the actual road. Detect the actual geographic location in the road.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

a device parameter acquisition module, configured to acquire device parameters of an image capture device that collects the target image data, wherein the device parameters of the image capture device include the focal length, lens angle, field of view, installation height, and latitude and longitude of the image capture device;

a target distance determination module, configured to calculate the target distance between the target road area where the image capture device collects image data and the image capture device according to the focal length, lens angle, field of view and erection height of the image capture device;

an area longitude and latitude determination module, configured to calculate the longitude and latitude of the target road area according to the longitude and latitude of the image acquisition device and the target distance;

The first correspondence determination module is used to map the latitude and longitude of the target road area to the image data, and obtain the correspondence between each position in the image data and the latitude and longitude of the actual road.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

The calibration point position acquisition module is used to obtain the latitude and longitude of multiple designated calibration points in the actual road;

an image data analysis module for determining the position of each of the above-mentioned designated calibration points in the image data;

The second correspondence determination module is configured to determine the correspondence between each position in the image data and the latitude and longitude in the actual road according to the latitude and longitude of each designated calibration point and the position of the designated calibration point in the image data.

Optionally, the above-mentioned traffic condition analysis module 504 is specifically used for:

The traffic state of each lane in the road to be detected is determined according to the actual geographic location of each vehicle.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

The vehicle location display module is used for displaying the actual geographic location of each vehicle on the electronic map according to a preset display frequency, wherein the preset display frequency is not greater than the frame rate of the target image data.

Optionally, the device for detecting a road traffic state in this embodiment of the present application further includes:

a vehicle calibration module for marking each of the above vehicles with a unique identifier;

The vehicle tracking module is used for tracking each of the above-mentioned vehicles according to the identification of each of the above-mentioned vehicles.

Embodiments of the present application also provide an electronic device, including a processor and a memory;

The above-mentioned memory is used to store computer programs;

When the above-mentioned processor is used to execute the program stored in the above-mentioned memory, the following steps are implemented:

Obtain the target image data of the road to be detected;

Using computer vision technology, determine the position of each vehicle in the above target image data;

Determine the actual geographic location of each of the above-mentioned vehicles on the above-mentioned road to be detected according to the position of each of the above-mentioned vehicles in the above-mentioned target image data;

The traffic state of the road to be detected is determined according to the actual geographic location of each vehicle.

Optionally, when the above-mentioned processor is configured to execute the program stored in the above-mentioned memory, any one of the above-mentioned road traffic state detection methods may also be implemented. Specifically, the above electronic device is a camera or a server.

Optionally, as shown in FIG. 6 , the electronic device in the embodiment of the present application further includes: a communication interface 602 , a storage and communication bus 604 , wherein the processor 601 , the communication interface 602 , and the memory 603 complete the communication between each other through the communication bus 604 . communication.

The communication bus mentioned in the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the above electronic device and other devices.

The memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; may also be a digital signal processor (Digital Signal Processing, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the above-mentioned road traffic state detection methods is implemented.

It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

Each embodiment in this specification is described in a related manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. Especially, for the embodiments of the apparatus, the electronic device and the storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application are included in the protection scope of this application.

Claims (16)

1. A method of road traffic condition detection, the method comprising:

acquiring target image data of a road to be detected;

determining the image position of each vehicle in the target image data by using a computer vision technology;

determining the actual geographic position of each vehicle in the road to be detected according to the image position of each vehicle in the target image data;

and determining the traffic state of the road to be detected according to the actual geographical position of each vehicle.

2. The method according to claim 1, wherein the acquiring target image data of the road to be detected comprises:

acquiring images of all road sections in a road to be detected, which are acquired by all lenses respectively;

and splicing the images of the road sections to obtain target image data of the road to be detected.

3. The method of claim 1, wherein determining the actual geographic position of each vehicle in the road to be detected according to the image position of each vehicle in the target image data comprises:

and mapping the image positions of the vehicles in the target image data into the longitude and latitude of the vehicles in the actual road according to the corresponding relation between the positions in the predetermined image data and the longitude and latitude in the actual road to obtain the actual geographic positions of the vehicles in the road to be detected.

4. The method of claim 3, wherein the step of predetermining the correspondence of each location in the image data to the latitude in the actual road comprises:

acquiring the longitude and latitude of a plurality of specified calibration points in an actual road;

determining the position of each designated index point in the image data;

and determining the corresponding relation between each position in the image data and the longitude and latitude in the actual road according to the longitude and latitude of each designated index point and the position of the designated index point in the image data.

5. The method according to claim 1, wherein said determining the traffic status of said road to be detected according to the actual geographical position of each of said vehicles comprises:

and determining the traffic state of each lane in the road to be detected according to the actual geographic position of each vehicle.

6. The method of claim 1, wherein after determining the actual geographic location of each of the vehicles in the road to be detected according to its image location in the target image data, the method further comprises:

and displaying the actual geographical position of each vehicle on an electronic map according to a preset display frequency, wherein the preset display frequency is not more than the frame rate of the target image data.

7. The method of claim 1, further comprising:

respectively marking a unique identifier for each vehicle;

tracking each of the vehicles based on the identity of each of the vehicles.

8. A road traffic condition detection apparatus, characterized in that the apparatus comprises:

the target image acquisition module is used for acquiring target image data of a road to be detected;

the target image analysis module is used for determining the image position of each vehicle in the target image data by utilizing a computer vision technology;

the vehicle position determining module is used for determining the actual geographic position of each vehicle in the road to be detected according to the image position of each vehicle in the target image data;

and the traffic condition analysis module is used for determining the traffic state of the road to be detected according to the actual geographic position of each vehicle.

9. The apparatus of claim 8, wherein the target image acquisition module comprises:

the road section image acquisition submodule is used for acquiring images of all road sections in the road to be detected, which are acquired by all the lenses respectively;

and the target image synthesis submodule is used for splicing the images of all the road sections to obtain the target image data of the road to be detected.

10. The apparatus of claim 8, wherein the vehicle position determination module is specifically configured to:

and mapping the image positions of the vehicles in the target image data into the longitude and latitude of the vehicles in the actual road according to the corresponding relation between the positions in the predetermined image data and the longitude and latitude in the actual road to obtain the actual geographic positions of the vehicles in the road to be detected.

11. The apparatus of claim 10, further comprising:

the calibration point position acquisition module is used for acquiring the longitude and latitude of a plurality of specified calibration points in an actual road;

the image data analysis module is used for determining the position of each designated calibration point in the image data;

and the second corresponding relation determining module is used for determining the corresponding relation between each position in the image data and the longitude and latitude in the actual road according to the longitude and latitude of each designated calibration point and the position of the designated calibration point in the image data.

12. The apparatus of claim 8, wherein the traffic condition analysis module is specifically configured to:

and determining the traffic state of each lane in the road to be detected according to the actual geographic position of each vehicle.

13. The apparatus of claim 8, further comprising:

and the vehicle position display module is used for displaying the actual geographic position of each vehicle on the electronic map according to a preset display frequency, wherein the preset display frequency is not more than the frame rate of the target image data.

14. The apparatus of claim 8, further comprising:

the vehicle calibration module is used for marking each vehicle with a unique identifier;

and the vehicle tracking module is used for tracking each vehicle according to the identification of each vehicle.

15. An electronic device comprising a processor and a memory;

the memory is used for storing a computer program;

the processor, when executing the program stored in the memory, implementing the method steps of any of claims 1-7.

16. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.

Images