Route speed measurement point position recognition method and device, electronic equipment and storage medium

Abstract

Embodiments of the application disclose a method and device for identifying speed measurement points along a route, electronic equipment and a storage medium. The method comprises: obtaining, from a server, a set of speed measurement points corresponding to a driving route of a navigation plan, the set of speed measurement points comprising identification strategy information of a plurality of speed measurement points, the identification strategy information comprising target position information, a speed measurement road section range and a target radar wave band; when a vehicle reaches the speed measurement road section range, identifying a target image obtained by a camera to obtain a speed measurement point device identification result and a flash effect identification result; determining a radar wave band identification result of the speed measurement point according to the speed measurement point device identification result, radar wave band information sensed by a radar wave sensing device and the target radar wave band; and taking the speed measurement point device identification result, the flash effect identification result and the radar wave band identification result as identification result data of the speed measurement point. The embodiments of the application achieve identification of speed measurement point devices and help to improve driving safety.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of image processing, in particular to a method and device for identifying speed measurement points along a route, electronic equipment and a storage medium. BACKGROUND

[0002] In a vehicle navigation scenario, when a vehicle passes through a speed measurement section, a language message such as "how many meters ahead of speed measurement" will be broadcast. The camera data of the speed measurement points along the route in the navigation software map is generally obtained from an official platform. However, in fact, many cameras in the speed measurement point camera data are not really enabled. Frequent voice broadcast for all speed measurement points will distract the driver's attention, which may cause the driver to brake suddenly to deal with the speed measurement on the road, thereby affecting driving safety. SUMMARY

[0003] Embodiments of the present application provide a method and device for identifying speed measurement points along a route, electronic equipment and a storage medium, which can identify speed measurement point devices and help improve driving safety.

[0004] To solve the above problems, in a first aspect, embodiments of the present application provide a method for identifying speed measurement points along a route, comprising:

[0005] Obtain a set of speed measurement points corresponding to a navigation planned driving route from a server, the set of speed measurement points comprising identification strategy information of a plurality of speed measurement points on the driving route, and the identification strategy information of each speed measurement point comprising target position information, speed measurement section range and target radar wave band;

[0006] When the vehicle reaches the speed measurement section range of the speed measurement point according to the target position information, perform speed measurement point device identification and flash effect identification on the target image obtained by the camera through a speed measurement point identification model to obtain speed measurement point device identification results and flash effect identification results;

[0007] According to the speed measurement point device identification results, radar wave band information sensed by a radar wave sensing device and the target radar wave band, determine a radar wave band identification result of the speed measurement point;

[0008] Take the speed measurement point device identification results, the flash effect identification results and the radar wave band identification result as identification result data of the speed measurement point.

[0009] In a second aspect, embodiments of the present application provide a device for identifying speed measurement points along a route, comprising:

[0010] The point information acquisition module is configured to acquire, from a server, a set of speed measurement points corresponding to a driving route of a navigation plan, the set of speed measurement points including identification strategy information of a plurality of speed measurement points on the driving route, and the identification strategy information of each speed measurement point including target position information, a speed measurement section range, and a target radar wave band.

[0011] The first identification module is configured to, when the vehicle reaches the speed measurement section range of the speed measurement point according to the target position information, perform speed measurement point device identification and flash effect identification on the target image obtained by the camera through a speed measurement point identification model, to obtain a speed measurement point device identification result and a flash effect identification result.

[0012] The second identification module is configured to determine a radar wave band identification result of the speed measurement point according to the speed measurement point device identification result, radar wave band information sensed by the radar wave sensing device, and the target radar wave band.

[0013] The identification result determination module is configured to take the speed measurement point device identification result, the flash effect identification result, and the radar wave band identification result as identification result data of the speed measurement point.

[0014] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for identifying speed measurement points along a route when executing the computer program.

[0015] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program executable by a processor, and the program implements the steps of the method for identifying speed measurement points along a route when executed by the processor.

[0016] The method and device for identifying speed measurement points along a route provided by the embodiments of the present application, by obtaining a set of speed measurement points corresponding to a driving route of navigation planning from a server, the set of speed measurement points including identification strategy information of a plurality of speed measurement points, when a speed measurement section range of a speed measurement point reached by a vehicle is determined according to target position information in the identification strategy information, speed measurement point device identification and flash effect identification are performed on a target image obtained by a camera through a speed measurement point identification model to obtain speed measurement point device identification results and flash effect identification results, a radar wave band identification result of the speed measurement point is determined according to the speed measurement point identification result, radar wave band information sensed by a radar sensing device, and a target radar wave band, the speed measurement point device identification result, the flash effect identification result, and the radar wave band identification result are taken as identification result data of the speed measurement point, which facilitates determining whether the speed measurement point is in an enabled state based on the identification result data, realizes identification of the speed measurement point device, and can perform voice broadcast based on the determined state, and voice broadcast can not be performed for a speed measurement point that is not enabled, which can avoid distracting the attention of a driver and help improve driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 The flowchart of a method for identifying speed measurement points along a route provided by the embodiments of the present application is shown in FIG. 1.

[0019] Figure 2 The flowchart of determining a radar wave band identification result of a speed measurement point in the embodiments of the present application is shown in FIG. 3.

[0020] Figure 3 The structural schematic diagram of a device for identifying speed measurement points along a route provided by the embodiments of the present application is shown in FIG. 4.

[0021] Figure 4 The structural schematic diagram of an electronic device provided by the embodiments of the present application is shown in FIG. 5. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] Figure 1 An embodiment of the present application provides a flowchart of a speed measurement point position recognition method, the speed measurement point position recognition method can be executed by a navigation client, as shown in the figure, the method comprises steps 110 to 140. Figure 1

[0024] Step 110, obtain, from a server, a speed measurement point position set corresponding to a driving route of navigation planning, the speed measurement point position set comprises identification strategy information of a plurality of speed measurement point positions on the driving route, and the identification strategy information of each speed measurement point position comprises target position information, a speed measurement road section range and a target radar wave band.

[0025] The target position information is position information, i.e. latitude and longitude information, of the speed measurement point position. The speed measurement road section range is a road section range in which speed measurement point position recognition needs to be performed, for example, the recognition is started when the distance to the speed measurement point position is 100 meters, and the recognition is ended when the distance to the speed measurement point position is 100 meters. The target radar wave band is a radar wave band of a speed measurement radar device at the speed measurement point position. Hardware devices of the speed measurement point position comprise a speed measurement camera, a speed measurement flash and a speed measurement radar device, and the three devices jointly complete speed measurement on a passing vehicle.

[0026] The vehicle terminal device or the electronic device such as a mobile phone starts a vehicle navigation client, the navigation client plans a driving route based on a given starting point and an ending point, the server generates speed measurement recognition strategies of all speed measurement point positions on the planned driving route according to a map source of a traffic control department, and the speed measurement recognition strategies are delivered to the navigation client (navigation software) in an array form at a time, and the navigation client receives the speed measurement point position set corresponding to the driving route delivered by the server. The server is a navigation cloud server, and is used for providing navigation services.

[0027] For example, the speed measurement point position set delivered by the server can be represented as follows:

[0028]

[0029] The start recognition distance represents the speed measurement road section range, i.e. the distance between the vehicle and the speed measurement point position is the start recognition distance, and then the speed measurement point position recognition is started.

[0030] ​The navigation client parses the identification strategy information of each speed measurement point in the speed measurement point set issued by the server. The Location field is parsed to obtain the target position information of the speed measurement point device; the Distance field is parsed to obtain the target position information, and the identification of the speed measurement point is started in advance when the distance from the target position information is a certain distance, and the identification is stopped after leaving the target position information; the NeedRadarBand field is parsed to obtain the target radar band of the speed measurement radar device on the speed measurement point, and the speed measurement radar device is identified, and the radar device conforming to the target radar band needs to be identified.

[0031] In step 120, when the vehicle reaches the speed measurement road section range of the speed measurement point according to the target position information, the speed measurement point device identification and the flash effect identification of the target image obtained by the camera are performed through the speed measurement point identification model to obtain the speed measurement point device identification result and the flash effect identification result.

[0032] The navigation client listens to the change of the vehicle-mounted GPS (Global Positioning System) and waits to drive to the speed measurement road section range in the identification strategy information. When the navigation client determines that the distance between the vehicle and the target position information in the identification strategy information is in the speed measurement road section range based on the position feedback of the GPS, the vehicle-mounted identification module is started and the speed measurement point identification model is input to the vehicle-mounted identification module, the radar wave sensing device is started to identify the radar band, the vehicle-mounted identification module loads the speed measurement point identification model, and each frame of target image obtained by the vehicle-mounted camera is identified through the speed measurement point identification model using a deep learning target detection algorithm to identify the speed measurement point device and the flash effect, and the identification result is returned to the navigation client (navigation software). The speed measurement point identification model is generated by training image data based on an image training algorithm, and then the identification algorithm is added to the identification model to perform image recognition processing. In addition, the speed measurement point identification model can be continuously imported into real images and optimized through a training algorithm to improve the identification accuracy.

[0033] The speed measurement point device identification result includes the identification result of each speed measurement device (speed measurement camera, speed measurement flash and speed measurement radar device) and the corresponding image data, and the flash effect identification result includes the flash effect identification result and the flash effect image. The flash effect identification result includes identification success or identification failure, which refers to the result of whether there is a flash effect. When the flash effect image includes a flash on image, a flash expansion image and a flash light pen image, the flash effect identification result is identification success, otherwise, the flash effect is identification failure. The identification result can be a text form identification result.

[0034] The speed measurement point device recognition result and the flash effect recognition result can adopt the following data structure:

[0035]

[0036]

[0037] In the above data structure, the latitude and longitude refer to the target position information of the recognized speed measurement point. When a speed measurement flash is recognized from the image, the speed measurement flash recognition result is successful recognition; otherwise, the speed measurement flash recognition result is failed recognition. When a speed measurement radar device is recognized from the image, the speed measurement radar device recognition result is successful recognition; otherwise, the speed measurement radar device recognition result is failed recognition. When a speed measurement camera is recognized from the image, the speed measurement camera recognition result is successful recognition; otherwise, the speed measurement camera recognition result is failed recognition.

[0038] When identifying the flash effect, three images need to be recognized, namely the flash-on image, the flash-expansion image and the flash-light pen image. Among them, the flash-on image is to use image recognition object tracking algorithm to identify the light from the recognized flash device; the flash-expansion image is to identify the image completely brightened when the flash is fully on; and the flash-light pen image is to use image recognition object tracking algorithm to identify the light from the recognized flash device.

[0039] Among them, the speed measurement point recognition model is based on the model of the depth image recognition algorithm and the target detection algorithm. The depth image recognition algorithm refers to an algorithm that uses deep learning methods to analyze and recognize depth images. Depth images are images that contain distance information of objects, usually composed of RGB images and depth maps (or distance maps). The target image obtained by the camera in the embodiment of the application is a depth image.

[0040] The target detection algorithm is used to locate and identify objects in depth images. Common target detection algorithms include deep learning-based algorithms (such as Faster R-CNN, YOLO, etc.) and traditional computer vision-based algorithms (such as edge, texture and shape feature-based methods).

[0041] The model training of the target detection algorithm usually needs the following steps 1 to 8:

[0042] 1. Data collection and labeling: collect image data sets containing target objects (including speed measurement cameras, speed measurement flashes and speed measurement radar devices), and label them. The labeling information should include the position and category of the object. Usually, enough labeled data is needed to train an accurate model.

[0043] 2. Data preprocessing: Preprocess the collected image data, including resizing, cropping, augmentation, etc., to improve the performance and robustness of the model. At the same time, it is also necessary to convert the image data into the input format acceptable by the model.

[0044] 3. Model selection: Select an algorithm model suitable for the target detection task. Common target detection algorithms include Faster R-CNN, YOLO, SSD, etc., which can be selected according to task requirements and computational resource limitations.

[0045] 4. Model initialization: According to the selected algorithm model, initialize based on the pre-trained model weight. The pre-trained model is usually trained on a large-scale image dataset and can be used as the starting point for model initialization.

[0046] 5. Loss function definition: According to the characteristics of the target detection task, define a suitable loss function. Common loss functions include target classification loss and bounding box regression loss. The definition of the loss function is crucial for the training and optimization of the model.

[0047] 6. Model training: Use the labeled image dataset to train the selected model. During training, the model will learn how to automatically extract features from images and perform target classification and location positioning. The training process usually uses gradient descent and other optimization algorithms for parameter update.

[0048] 7. Model evaluation: Use another test dataset to evaluate the trained model, including calculating accuracy, recall, precision, etc. to evaluate the performance of the model. Model tuning and parameter adjustment can be performed according to the evaluation results.

[0049] 8. Model deployment: Apply the trained model to actual target detection tasks to predict and identify new images. Target detection can be achieved through model inference and prediction.

[0050] Step 130, according to the speed point position device identification result, the radar wave band information sensed by the radar wave sensing device, and the target radar wave band, determine the radar wave band identification result of the speed point position.

[0051] Among them, the radar wave sensing device is a device installed on the vehicle, used to sense the surrounding radar wave band.

[0052] When the speed measurement radar device is identified in the speed measurement point device identification result, it is further needed to determine whether the speed measurement radar device is in an enabled state, at this time, the radar wave induction device can be used to sense the radar wave band information around, the radar wave band information same as the target radar wave band is screened out from the radar wave band information as the candidate radar wave band information, and the position of the speed measurement radar device is identified from the image, if the position corresponding to each candidate radar wave band information exists the candidate radar wave band information same as or similar to (the distance is less than or equal to the distance threshold) the position identified from the image, at this time, the radar wave band identification result is identification success, if the position corresponding to each candidate radar wave band information does not exist the candidate radar wave band information same as or similar to (the distance is less than or equal to the distance threshold) the position identified from the image, at this time, the radar wave band identification result is identification failure.

[0053] In step 140, the speed measurement point device identification result, the flash effect identification result and the radar wave band identification result are taken as the identification result data of the speed measurement point.

[0054] The speed measurement point device identification result, the flash effect identification result and the radar wave band identification result are taken as the identification result data of the speed measurement point, which facilitates determining whether the speed measurement device of the speed measurement point is enabled based on the identification result data.

[0055] The method provided by the embodiment of the present application comprises the following steps: obtaining, from a server, a speed measurement point set corresponding to a driving route of a navigation plan, the speed measurement point set comprising identification strategy information of a plurality of speed measurement points; determining, according to target position information in the identification strategy information, a speed measurement section range of a speed measurement point reached by a vehicle; performing, by a speed measurement point identification model, speed measurement point device identification and flash effect identification on a target image acquired by a camera to obtain speed measurement point device identification result and flash effect identification result; determining, according to the speed measurement point device identification result, radar wave band information sensed by a radar induction device and a target radar wave band, a radar wave band identification result of the speed measurement point; and taking the speed measurement point device identification result, the flash effect identification result and the radar wave band identification result as identification result data of the speed measurement point, which facilitates determining whether the speed measurement point is in an enabled state based on the identification result data, realizes identification of the speed measurement point device, and can perform voice broadcast based on the determined state, so that voice broadcast is not performed for the speed measurement point in the disabled state, the attention of the driver is avoided from being distracted, and the driving safety is improved.

[0056] Figure 2 is a flowchart for determining the radar wave band identification result of the speed measurement point in the embodiment of the present application, which needs to be determined in combination with the speed measurement point device identification result, the radar wave band information sensed by the radar induction device and the target radar wave band. For example, Figure 2As shown, according to the speed point position device identification result, the radar wave band information sensed by the radar wave sensing device, and the target radar wave band, a radar wave band identification result of the speed point position is determined, including the following steps:

[0057] Step 131, when the identification success result of the speed radar device is included in the speed point position device identification result, identifying the first relative position information between the speed radar device and the vehicle from the target image.

[0058] When the identification success result of the speed radar device is included in the speed point position device identification result, it means that the speed radar device on the speed point position is successfully identified from the target image. At this time, it is necessary to further determine whether the speed radar device is transmitting radar signals, so as to determine whether the speed radar device is in an enabled state.

[0059] When the speed radar device is identified from the target image by the speed point position identification model, the speed point position identification model can simultaneously identify the first relative position information between the speed radar device and the vehicle from the target image. The first relative position information can be represented in the form of three-dimensional coordinates.

[0060] Specifically, the vehicle-mounted identification module can perform real-time identification by the speed point position identification model, and use an image recognition object tracking algorithm to return the coordinate information (first relative position information) of the speed radar device to the navigation software (navigation client) in real time. The data structure of the first relative position information is as follows:

[0061] {

[0062] RadarBandPath: [x, y, z] / / three-dimensional coordinates

[0063] }

[0064] In the above three-dimensional coordinates, z represents the distance between the speed radar device in the speed point position and the vehicle, that is, the depth information, and x and y represent the coordinate information corresponding to the target image coordinates.

[0065] Step 132, obtaining at least one radar wave band sensed by the radar wave sensing device and second relative position information corresponding to each radar wave band.

[0066] The radar wave sensing device on the vehicle returns the radar identification result (radar wave band and corresponding second relative position information) to the navigation client in real time. The second relative position information can be in the form of three-dimensional coordinates. The second relative position information in the radar identification result returned by the radar wave sensing device can be the angle and distance identified, and the navigation client can calculate the second relative position information in the form of three-dimensional coordinates based on the angle and distance.

[0067] The data structure of each radar wave band and the second relative position information determined based on the radar recognition result returned by the radar wave sensing device can be as follows:

[0068]

[0069] In the three-dimensional coordinates, the coordinate z represents the distance between the radar device and the vehicle, and the coordinates x and y represent the coordinate information corresponding to the target image coordinates calculated based on the angle sensed by the radar wave sensing device.

[0070] Step 133, comparing the at least one radar wave band with the target radar wave band respectively to obtain a first comparison result, and comparing the second relative position information with the first relative position information to obtain a second comparison result.

[0071] The first comparison result can include the same radar wave band as the target radar wave band. The second comparison result can include the same or similar second relative position information as the first relative position information, and the second comparison result can also be the distance between the second relative position information and the first relative position information.

[0072] Step 134, determining the radar wave band recognition result according to the first comparison result and the second comparison result.

[0073] From the first comparison result, the radar wave band identical to the target radar wave band is screened out. For these radar wave bands, it is determined from the second comparison result whether the second relative position information of these radar wave bands is identical or similar to the first relative position information. If there is second relative position information identical or similar to the first relative position information in the second relative position information of the screened radar wave band, it is determined that the radar wave band corresponding to the second relative position information is the radar wave band emitted by the speed measurement radar device, and it is determined that the radar wave band recognition result is successful. If there is no second relative position information identical or similar to the first relative position information in the second relative position information of the screened radar wave band, it is determined that the radar wave band recognition result is failed.

[0074] In an embodiment of the present application, the determination of the radar wave band recognition result according to the first comparison result and the second comparison result includes: for the radar wave band identical to the target radar wave band in the first comparison result, if there is second comparison result in which the distance between the first relative position information and the second relative position information of the radar wave band is less than or equal to a distance threshold, it is determined that the radar wave band recognition result is successful; if the distances in the second comparison result corresponding to the radar wave band are all greater than the distance threshold, it is determined that the radar wave band recognition result is failed.

[0075] For the radar wave bands same as the target radar wave band in the first comparison result, the distance between the second relative position information and the first relative position information of these radar wave bands is obtained from the second comparison result, if there is a second comparison result with a distance less than or equal to the distance threshold in the second comparison result, it is determined that the radar wave band failure result is a recognition success, that is, the speed measurement radar device of the speed measurement point position is in an enabled state, if the distance in the second comparison result is all greater than the distance threshold, it is determined that the radar wave band recognition result is a recognition failure, that is, the speed measurement radar device of the speed measurement point position is in a disabled state. The distance threshold is a smaller distance, for example, 1 meter, 0.5 meters, 0.1 meters, etc.

[0076] By combining the speed measurement radar device recognized in the target image and the first relative position information of the vehicle, the radar wave bands that meet the target radar wave band and the radar wave bands same as or similar to the first relative position information are screened from the radar wave bands sensed by the induction wave induction device, which can prevent the interference of other radar devices on the road surface.

[0077] Optionally, on the basis of the above technical solution, the method further comprises: ending the identification of the speed measurement point position when the identification of the speed measurement point position is completed or the vehicle drives out of the speed measurement road section range.

[0078] The identification of the speed measurement point position is completed, which means that the speed measurement point position device recognition result, the flash light effect recognition result, and the radar wave band recognition result are successfully obtained.

[0079] When the identification of the speed measurement point position is completed or the vehicle drives out of the test road section range in the identification strategy information, the navigation client ends the identification, ends the vehicle-mounted identification module, and ends the induction of the radar induction device. The final identification result data is saved to the local client.

[0080] The data structure of the identification result data maintained locally is as follows:

[0081]

[0082]

[0083] By ending the identification of the speed measurement point position when the identification of the speed measurement point position is completed or the vehicle drives out of the speed measurement road section range, the computing resources can be released in time.

[0084] On the basis of the above technical solution, the method further comprises: sending the identification result data of each speed measurement point position in the driving route to the server when the navigation is ended. The identification result data is used as the basic data for the server to determine the enabled state of the speed measurement point position.

[0085] At the end of navigation, the client uploads all the recognition result data saved locally to the navigation cloud server, and the navigation cloud server can determine the state information of the speed measurement point based on the recognition result data of each speed measurement point. The state information can include enabled, disabled, or false point, etc.

[0086] If the speed measurement camera, speed measurement flash, speed measurement radar device, flash effect three frames of graphics are recognized in the recognition result data, and the target radar band matched in the identification strategy information is recognized, it is determined that the state information of the speed measurement point is enabled, and the recognition result of the speed measurement point is recorded as enabled.

[0087] If the speed measurement camera, speed measurement flash, speed measurement radar device are recognized in the recognition result data; the flash effect or the target radar band is not recognized, it is determined that the state information of the speed measurement point is disabled, and the recognition result of the speed measurement point is recorded as disabled. All hardware devices are completely recognized, which means that the speed measurement point exists, but the speed measurement flash and the speed measurement radar device are not started, which means that the speed measurement point device is not in the open state, so it is determined as disabled.

[0088] If at least one of the speed measurement camera, speed measurement flash, and speed measurement radar device is not recognized in the recognition result data, it is determined that the state information of the speed measurement point is a false point, and the recognition result of the speed measurement point is recorded as a false point. Because all hardware devices are not completely recognized, it means that the hardware devices of the speed measurement point are incomplete, and there is actually no speed measurement device, so it is determined as a false point.

[0089] After the server receives the recognition result data sent by the navigation client, the recognition result data is stored in the database. The server extracts the image data successfully recognized (i.e. all speed measurement devices, flash effect, and target radar band are successfully recognized) from the recognition result data, optimizes and trains the original speed measurement point recognition model using the deep learning image recognition training algorithm, and generates a new speed measurement point recognition model with higher recognition accuracy.

[0090] By sending the recognition result data to the server, the server can determine the state information of the speed measurement point based on the recognition result data, facilitate voice broadcast of the truly enabled speed measurement point, and optimize the speed measurement point recognition model based on the successful recognition result data to improve the recognition accuracy of the speed measurement point recognition model.

[0091] On the basis of the above technical solutions, after the speed measurement point position device recognition result, the flash effect recognition result and the radar wave band recognition result are taken as the recognition result data of the speed measurement point position, the method further comprises: determining state information of the speed measurement point position according to the speed measurement point position device recognition result, the flash effect recognition result and the radar wave band recognition result.

[0092] The state information can include enabled, disabled, false point position and the like.

[0093] The client can also determine the state information of the speed measurement point position and send the state information and the recognition result data to the server together, and the server stores and processes subsequently. Of course, the operation of determining the state information of the speed measurement point position can also be performed by the server, that is, after the server receives the recognition result data sent by the client, the state information of the speed measurement point position is determined based on the speed measurement point position device recognition result, the flash effect recognition result and the radar wave band recognition result in the recognition result data.

[0094] Optionally, the determining the state information of the speed measurement point position according to the speed measurement point position device recognition result, the flash effect recognition result and the radar wave band recognition result comprises:

[0095] In the case that the speed measurement camera, the speed measurement flash and the speed measurement radar device are identified in the speed measurement point position device recognition result, if the flash effect recognition result is successful and the radar wave band recognition result is successful, the state information is determined as enabled.

[0096] In the case that the speed measurement camera, the speed measurement flash and the speed measurement radar device are identified in the speed measurement point position device recognition result, if at least one of the flash effect recognition result and the radar wave band recognition result is failed, the state information is determined as disabled.

[0097] If at least one of the speed measurement camera, the speed measurement flash and the speed measurement radar device is not identified in the speed measurement point position device recognition result, the state information is determined as a false point position.

[0098] The complete recognition of all hardware devices indicates that the speed measurement point exists, and the recognition of the flash effect and the radar band indicates that the hardware device of the speed measurement point is in an open state, so the state information is determined to be enabled. The complete recognition of all hardware devices indicates that the speed measurement point exists, but the flash effect and the radar band are not recognized, and it is determined that the speed measurement flash and the speed measurement radar device are not started, which indicates that the device of the speed measurement point is not in an open state, so it is determined to be not enabled. The incomplete recognition of all hardware devices indicates that the hardware device of the speed measurement point is incomplete, and the speed measurement device actually does not exist, so it is determined to be a false point.

[0099] By determining the state information of each speed measurement point, only the truly enabled speed measurement points can be broadcast in subsequent voice broadcast, and the speed measurement points that are not enabled or false points are not broadcast in voice, which can prevent frequent voice broadcast from interfering with the attention of the driver and help improve driving safety.

[0100] On the basis of the above technical solutions, before the speed measurement point device recognition and the flash effect recognition of the target image obtained by the camera are performed through the speed measurement point recognition model, the method further comprises:

[0101] The speed measurement point recognition model is obtained from the server, and the speed measurement point recognition model is obtained by the server based on historical image data of successful speed measurement point recognition to update the original speed measurement point recognition model.

[0102] The historical image data of successful recognition is uploaded to the server by the client or other clients before the client obtains the speed measurement point recognition model, and the server updates the original speed measurement point recognition model based on the historical image data to obtain the updated speed measurement point recognition model, so that when the client requests the speed measurement point recognition model, the server returns the latest speed measurement point recognition model to the client.

[0103] When the navigation client is started, the latest speed measurement point recognition model is downloaded from the server, and the latest speed measurement point recognition model is saved locally.

[0104] When the server receives the recognition result data uploaded by the client, the speed measurement point recognition model is optimized and trained based on the image data of successful recognition in the recognition result data, so that when the client requests the speed measurement point recognition model from the server, the server returns the latest speed measurement point recognition model to the client.

[0105] By updating the speed measurement point recognition model based on the historical image data of successful recognition, the speed measurement point recognition model is continuously upgraded based on a large number of real images, and the recognition efficiency and accuracy are improved.

[0106] On the basis of the above technical solutions, the set of speed measurement points further comprises statistical state information of each speed measurement point in the plurality of speed measurement points, the statistical state information is state information with a proportion greater than a proportion threshold in the same speed measurement point, and the statistical state information comprises enabled, disabled, or a virtual point.

[0107] The method further comprises: when the vehicle travels to a speed measurement point with the statistical state information being enabled, performing voice broadcast prompting.

[0108] When the amount of data of the recognition result of the same speed measurement point received by the server reaches a preset data amount (for example, 1000, and the greater the amount of data, the lower the probability of calculation error of the statistical result), the state information in the recognition result of the same speed measurement point is counted, and if a state information has a proportion greater than a proportion threshold in all state information, the state information is taken as the statistical state information of the speed measurement point. The same state information can be enabled, disabled, or a virtual point. Similarly, the statistical state information comprises enabled, disabled, or a virtual point. The proportion threshold is a relatively high proportion threshold, so that the statistical state information determined has a relatively high credibility. The proportion threshold can be 90% or the like.

[0109] When the client starts navigation, the set of speed measurement points obtained from the server comprises, in addition to the recognition strategy information of each speed measurement point on the travel route, the statistical state information of each speed measurement point, so that when the vehicle travels to a speed measurement point with the statistical state information being enabled, voice broadcast prompting is performed, and when the vehicle travels to a speed measurement point with the statistical state information being disabled or a virtual point, voice broadcast prompting is not performed. Therefore, only the enabled speed measurement points can be broadcasted and prompted, and the disabled or virtual points are not broadcasted and prompted, so that frequent voice broadcast can be avoided to disperse the attention of the driver, and driving safety can be improved.

[0110] Figure 3 is a structural schematic diagram of a speed measurement point recognition device provided by an embodiment of the present application, as shown in Figure 3 The device comprises:

[0111] A point information acquisition module 310 is configured to acquire, from a server, a set of speed measurement points corresponding to a travel route planned by navigation, the set of speed measurement points comprising recognition strategy information of a plurality of speed measurement points on the travel route, and the recognition strategy information of each speed measurement point comprising target position information, a speed measurement road section range, and a target radar wave band.

[0112] The first identification module 320 is configured to, when the vehicle reaches the speed measurement road section range of the speed measurement point according to the target position information, perform speed measurement point device identification and flash effect identification on the target image obtained by the camera through a speed measurement point identification model, to obtain speed measurement point device identification results and flash effect identification results.

[0113] The second identification module 330 is configured to determine a radar wave band identification result of the speed measurement point according to the speed measurement point device identification result, radar wave band information sensed by the radar wave sensing device, and the target radar wave band.

[0114] The identification result determination module 340 is configured to take the speed measurement point device identification result, the flash effect identification result, and the radar wave band identification result as identification result data of the speed measurement point.

[0115] Optionally, the second identification module includes:

[0116] The first position identification unit is configured to, when the speed measurement radar device identification success result is included in the speed measurement point device identification result, identify first relative position information of the speed measurement radar device and the vehicle from the target image.

[0117] The radar sensing information acquisition unit is configured to acquire at least one radar wave band sensed by the radar wave sensing device and second relative position information corresponding to each radar wave band.

[0118] The comparison unit is configured to compare the at least one radar wave band with the target radar wave band respectively to obtain a first comparison result, and compare the second relative position information with the first relative position information to obtain a second comparison result.

[0119] The radar identification result determination unit is configured to determine the radar wave band identification result according to the first comparison result and the second comparison result.

[0120] Optionally, the radar identification result determination unit is specifically configured to:

[0121] For the radar wave band that is the same as the target radar wave band in the first comparison result, if the second comparison result in which the distance between the first relative position information and the second relative position information of the radar wave band is less than or equal to a distance threshold exists, it is determined that the radar wave band identification result is identification success.

[0122] If the distances in the second comparison result corresponding to the radar wave band are all greater than the distance threshold, it is determined that the radar wave band identification result is identification failure.

[0123] Optionally, the device further includes:

[0124] A point recognition ending module, configured to end the recognition of the speed measurement point when the speed measurement point recognition is completed or the vehicle drives out of the speed measurement road section.

[0125] Optionally, the device further comprises:

[0126] An identification result uploading module, configured to send the identification result data of each speed measurement point in the driving route to a server when the navigation ends, the identification result data being used as basic data for the server to determine the activation state of the speed measurement point.

[0127] Optionally, the device further comprises:

[0128] A point state determining module, configured to determine state information of the speed measurement point according to the speed measurement point device identification result, the flash light effect identification result and the radar wave band identification result.

[0129] Optionally, the point state determining module is specifically configured to:

[0130] In the case that the speed measurement point device identification result identifies the speed measurement camera, the speed measurement flash light and the speed measurement radar device, if the flash light effect identification result is identification success and the radar wave band identification result is identification success, the state information is determined to be activated.

[0131] In the case that the speed measurement point device identification result identifies the speed measurement camera, the speed measurement flash light and the speed measurement radar device, if at least one of the flash light effect identification result and the radar wave band identification result is identification failure, the state information is determined to be not activated.

[0132] If at least one of the speed measurement camera, the speed measurement flash light and the speed measurement radar device is not identified in the speed measurement point device identification result, the state information is determined to be a false point.

[0133] Optionally, the device further comprises:

[0134] An identification module obtaining module, configured to obtain the speed measurement point identification model from the server, the speed measurement point identification model being obtained by the server based on historical image data of successful speed measurement point identification to update an original speed measurement point identification model.

[0135] Optionally, the set of speed measurement points further comprises statistical state information of each speed measurement point in the plurality of speed measurement points, the statistical state information being state information with a proportion greater than a proportion threshold in the same speed measurement point, and the statistical state information comprising activation, non-activation or false point.

[0136] The device further comprises:

[0137] The broadcast prompt module is configured to perform voice broadcast prompting when the vehicle travels to the speed measurement point for which the statistical state information is enabled.

[0138] Optionally, the flash effect recognition result includes a flash effect recognition result and a flash effect image.

[0139] When the flash effect image includes a flash-on image, a flash-expanding image and a flash-light pen image, the flash effect recognition result is a successful recognition.

[0140] The on-route speed measurement point recognition device provided in the embodiments of the present application is used to implement each step of the on-route speed measurement point recognition method provided in the embodiments of the present application, and the specific implementation manners of each module of the device are described in the corresponding steps, which will not be repeated here.

[0141] The on-route speed measurement point recognition device provided in the embodiments of the present application acquires a set of speed measurement points corresponding to a driving route of a navigation plan from a server, the set of speed measurement points includes identification strategy information of a plurality of speed measurement points, when a target position information in the identification strategy information determines that a vehicle reaches a speed measurement range of a speed measurement point, a speed measurement point device recognition and a flash effect recognition are performed on a target image acquired by a camera through a speed measurement point recognition model to obtain a speed measurement point device recognition result and a flash effect recognition result, a radar band recognition result of the speed measurement point is determined according to the speed measurement point recognition result, radar band information sensed by a radar sensing device and a target radar band, the speed measurement point device recognition result, the flash effect recognition result and the radar band recognition result are taken as recognition result data of the speed measurement point, which facilitates determining whether the speed measurement point is enabled based on the recognition result data, realizes the recognition of the speed measurement point device, and can perform voice broadcast based on the determined state, and the voice broadcast can not be performed for the speed measurement point that is not enabled, which can avoid distracting the attention of the driver and help improve the driving safety.

[0142] Figure 4 is a structural schematic diagram of an electronic device provided in the embodiments of the present application, as Figure 4 shown, the electronic device 400 can include one or more processors 410 and one or more memories 420 connected with the processors 410. The electronic device 400 can further include an input interface 430 and an output interface 440 for communicating with another device or system. Program codes executed by the processor 410 can be stored in the memory 420.

[0143] The processor 410 in the electronic device 400 calls program codes stored in the memory 420 to execute the on-route speed measurement point recognition method in the above-described embodiments.

[0144] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the along-the-way speed measurement point position identification method.

[0145] The embodiment of the present application further provides a computer program product, which is executed by a processor to realize the steps of the along-the-way speed measurement point position identification method.

[0146] Each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0147] The along-the-way speed measurement point position identification method, device, electronic equipment and storage medium provided by the embodiments of the present application are described in detail above, and the principle and implementation manner of the present application are described by applying specific examples in this paper. The above embodiment is only used to help understand the method and core idea of the present application; at the same time, for the general technical personnel in the art, according to the idea of the present application, the specific implementation manner and application range can be changed, and the above is not understood as the limitation of the present application.

[0148] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and necessary general hardware platform, and of course it can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software product, and the computer software product can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

Claims

1. A method for identifying speed measurement points along a route, characterized by The method comprises the following steps: obtain a set of speed measurement points corresponding to a driving route of a navigation plan from a server, the set of speed measurement points comprising identification strategy information of a plurality of speed measurement points on the driving route, and the identification strategy information of each speed measurement point comprising target position information, speed measurement road section range, and target radar wave band; when the vehicle reaches the speed measurement road section range of the speed measurement point according to the target position information, perform speed measurement point device identification and flash effect identification on a target image obtained by a camera through a speed measurement point identification model to obtain speed measurement point device identification results and flash effect identification results; determine a radar wave band identification result of the speed measurement point according to the speed measurement point device identification results, radar wave band information sensed by a radar wave sensing device, and the target radar wave band; use the speed measurement point device identification results, the flash effect identification results, and the radar wave band identification result as identification result data of the speed measurement point.

2. The method of claim 1, wherein, The method further comprises the following steps: when the speed measurement point device identification results include a successful identification result of a speed measurement radar device, identify first relative position information of the speed measurement radar device and the vehicle from the target image; obtain at least one radar wave band sensed by the radar wave sensing device and second relative position information corresponding to each radar wave band; compare the at least one radar wave band with the target radar wave band respectively to obtain first comparison results, and compare the second relative position information with the first relative position information to obtain second comparison results; determine the radar wave band identification result according to the first comparison results and the second comparison results.

3. The method of claim 2, wherein, The method further comprises the following steps: for a radar wave band that is the same as the target radar wave band in the first comparison results, if the radar wave band has second comparison results in which the distance between the first relative position information and the second relative position information is less than or equal to a distance threshold, determine that the radar wave band identification result is successful identification; if the distance in the second comparison results corresponding to the radar wave band is greater than the distance threshold, determine that the radar wave band identification result is failed identification.

4. The method of claim 1, wherein, The method further comprises the following steps: end the identification of the speed measurement point when the identification of the speed measurement point is completed or the vehicle drives out of the speed measurement road section range.

5. The method of claim 1, wherein, The method further comprises the following steps: send identification result data of each speed measurement point in the driving route to the server when the navigation is completed, and use the identification result data as basic data for the server to determine the activation state of the speed measurement point.

6. The method of claim 1, wherein, The method further comprises the following steps: determine state information of the speed measurement point according to the speed measurement point device identification results, the flash effect identification results, and the radar wave band identification result.

7. The method of claim 6, wherein, The state information of the speed measurement point is determined according to the speed measurement point position device identification result, the flash effect identification result and the radar wave band identification result, and the state information of the speed measurement point includes: In the case that the speed measurement camera, the speed measurement flash and the speed measurement radar device are identified in the speed measurement point position device identification result, if the flash effect identification result is identification success and the radar wave band identification result is identification success, it is determined that the state information is enabled; In the case that the speed measurement camera, the speed measurement flash and the speed measurement radar device are identified in the speed measurement point position device identification result, if at least one of the flash effect identification result and the radar wave band identification result is identification failure, it is determined that the state information is not enabled; If at least one of the speed measurement camera, the speed measurement flash and the speed measurement radar device is not identified in the speed measurement point position device identification result, it is determined that the state information is a false point.

8. The method of claim 1, wherein, Before the speed measurement point position device identification and the flash effect identification of the target image obtained by the camera are performed through the speed measurement point identification model, the method further includes: The speed measurement point identification model is obtained from the server, and the speed measurement point identification model is obtained by updating the original speed measurement point identification model based on historical image data of successful speed measurement point identification.

9. The method of claim 1, wherein, The speed measurement point set further includes statistical state information of each speed measurement point in the plurality of speed measurement points, the statistical state information is state information with a proportion greater than a proportion threshold in the same speed measurement point, and the statistical state information includes enabled, not enabled or false point; The method further includes: When the vehicle travels to the speed measurement point with the statistical state information of enabled, voice broadcast prompt is performed.

10. The method of claim 1, wherein, The flash effect identification result includes flash effect identification result and flash effect image; When the flash effect image includes flash on image, flash expansion image and flash light pen image, the flash effect identification result is identification success.

11. A device for identifying speed measurement points along a route, characterized in that It includes: The point information acquisition module is configured to obtain, from a server, a speed measurement point set corresponding to a driving route of navigation planning, the speed measurement point set including identification strategy information of a plurality of speed measurement points on the driving route, and the identification strategy information of each speed measurement point including target position information, speed measurement road section range and target radar wave band. The first identification module is configured to determine, according to the target position information, that the vehicle reaches the speed measurement road section range of the speed measurement point, and perform speed measurement point position device identification and flash effect identification on a target image obtained by a camera through a speed measurement point identification model, to obtain speed measurement point position device identification result and flash effect identification result. The second identification module is configured to determine, according to the speed measurement point position device identification result, radar wave band information sensed by a radar wave sensing device and the target radar wave band, a radar wave band identification result of the speed measurement point. The identification result determination module is configured to take the speed measurement point position device identification result, the flash effect identification result and the radar wave band identification result as identification result data of the speed measurement point.

12. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method for identifying the speed measurement point along the route according to any one of claims 1 to 10 when executing the computer program.

13. A computer readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the steps of the method for identifying the speed measurement point along the route according to any one of claims 1 to 10.

Images