Methods, devices, vehicles and storage media for detecting obstructed vehicles

Abstract

This application relates to the field of vehicle technology, and in particular to a method, apparatus, vehicle, and storage medium for detecting obstructed vehicles. The method includes: acquiring echo data along the vehicle's travel direction; performing time-frequency analysis on the echo data to obtain a time-frequency map; extracting micro-Doppler features from the time-frequency map; and identifying whether the micro-Doppler features are preset features. If the micro-Doppler features are preset features, it is determined that there is an obstructing vehicle crossing the vehicle's travel direction; otherwise, it is determined that there is no obstructing vehicle crossing the vehicle's travel direction. This solves the problems of limited scanning range and accuracy of detectors in related technologies, which prevent accurate detection of obstructed vehicles crossing the vehicle, leading to difficulties in identification and poor security.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, vehicle, and storage medium for detecting obstructed vehicles. Background Technology

[0002] Currently, integrated adaptive cruise control systems are widely used on highways and expressways, effectively avoiding collisions with vehicles and pedestrians directly in front within a certain speed range. However, their application in urban road conditions is limited, and their use in unmanned parking is constrained by the complex parking environment and the limitations of the sensors themselves.

[0003] In related technologies, detectors in the vehicle typically scan the environment around the vehicle, and if a hidden danger is detected in front of the vehicle, a warning is issued to the driver.

[0004] However, the scanning range and accuracy of detectors in related technologies are limited, especially in ramp and underground parking scenarios where the detection requirements of sensors are higher, making it impossible to completely and effectively detect obstacles such as vehicles that are obscured around the vehicle. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for detecting obstructed vehicles, in order to solve the problems of limited scanning range and accuracy of detectors in related technologies, which make it impossible to detect obstructed vehicles crossing the road, resulting in difficulties in identification and poor security.

[0006] The first aspect of this application provides a method for detecting obstructed vehicles, comprising the following steps: acquiring echo data in the direction of vehicle travel; performing time-frequency analysis on the echo data to obtain a time-frequency map, extracting micro-Doppler features from the time-frequency map, and identifying whether the micro-Doppler features are preset features; if the micro-Doppler features are the preset features, determining that there is an obstructing vehicle crossing in the direction of vehicle travel, otherwise determining that there is no obstructing vehicle crossing in the direction of vehicle travel.

[0007] Based on the above technical means, the embodiments of this application can perform time-frequency analysis on the echo data in the vehicle's driving direction and extract micro-Doppler features. By using the micro-Doppler features to output the marker position of vehicles crossing the road, the accurate identification of vehicles that are obstructed and crossing the road can be achieved. When there are vehicles crossing the road and obstructing the road in the vehicle's driving direction, collisions can be avoided in advance, sudden braking can be avoided, the driving safety and ride comfort of the vehicle can be improved, and the probability of traffic accidents can be effectively reduced.

[0008] Optionally, in one embodiment of this application, the step of determining that there is a vehicle crossing and obstructing the vehicle's direction of travel if the micro-Doppler feature is the preset feature includes: identifying whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all the preset features; if the micro-Doppler features corresponding to multiple consecutive frames of echo data are the preset features, then determining that there is a vehicle crossing and obstructing the vehicle's direction of travel.

[0009] Based on the above technical means, the embodiments of this application can avoid false detections and improve the accuracy of identifying vehicles that cross the road while obstructed by comparing whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all preset features.

[0010] Optionally, in one embodiment of this application, after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the method further includes: identifying the longitudinal distance between the vehicle and the vehicle crossing and obstructing the vehicle based on echo data from multiple consecutive frames, and identifying the actual position of the vehicle crossing and obstructing the vehicle based on point cloud data in the vehicle's direction of travel; and controlling the vehicle to perform a preset reminder action and / or a preset safety action when the vehicle meets preset conditions based on the longitudinal distance and / or the actual position.

[0011] Based on the above-mentioned technical means, the embodiments of this application can determine the possibility of a collision based on the longitudinal distance between the current vehicle and the vehicle crossing the obstruction and the actual position of the vehicle crossing the obstruction, and promptly control the vehicle to issue warnings and take corresponding safety actions to avoid sudden braking and improve the driving safety and ride comfort of the vehicle.

[0012] Optionally, in one embodiment of this application, identifying the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on multiple consecutive frames of echo data includes: extracting distance features from the time-frequency map corresponding to the multiple consecutive frames of echo data; and determining the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on the distance features.

[0013] Based on the above technical means, the embodiments of this application can compare the results of multiple consecutive frames to more accurately determine the longitudinal distance of the obstruction of the vehicle crossing.

[0014] Optionally, in one embodiment of this application, identifying the actual position of the vehicle crossing the obstruction based on the point cloud data in the vehicle's driving direction includes: identifying the number of effective point clouds accumulated on the left and right sides in the vehicle's driving direction; and taking the position where the number of effective point clouds is greater than a preset number as the actual position of the vehicle crossing the obstruction.

[0015] Based on the above technical means, the embodiments of this application can determine whether the actual position of the vehicle is on the right or left side based on the number of effective point clouds accumulated on the left and right sides of the occluded vehicle, so as to achieve accurate identification of occluded vehicles crossing the road.

[0016] Optionally, in one embodiment of this application, when the vehicle is determined to meet the preset conditions based on the longitudinal distance and / or actual position, controlling the vehicle to perform a preset reminder action and / or a preset safety action includes: determining the risk level of a collision between the vehicle and the vehicle crossing the obstruction based on the longitudinal distance and / or actual position; if the risk level is greater than a preset level, controlling the vehicle to perform the preset reminder action and the preset safety action; otherwise, controlling the vehicle to perform the preset reminder action.

[0017] Based on the above-mentioned technical means, the embodiments of this application can determine the risk level of a vehicle collision, promptly remind the user to make corresponding responses and control the vehicle to perform safe actions, effectively reducing the probability of traffic accidents.

[0018] Optionally, in one embodiment of this application, after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the method further includes: generating a schematic diagram based on the longitudinal distance and / or actual position, wherein the schematic diagram displays the position and / or distance between the vehicle and the vehicle crossing and obstructing the vehicle.

[0019] Based on the above-mentioned technical means, the embodiments of this application can display the distance and location information of vehicles obstructing the view in front of the user through a schematic diagram, so as to facilitate the user's viewing and timely avoidance of risks.

[0020] A second aspect of this application provides a vehicle obstruction detection device, comprising: an acquisition module for acquiring echo data in the vehicle's driving direction; a processing module for performing time-frequency analysis on the echo data to obtain a time-frequency map, extracting micro-Doppler features from the time-frequency map, and identifying whether the micro-Doppler features are preset features; and a determination module for determining that there is a vehicle obstructing the vehicle's driving direction when the micro-Doppler features are the preset features, otherwise determining that there is no vehicle obstructing the vehicle's driving direction.

[0021] Optionally, in one embodiment of this application, the determination module is further configured to identify whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all the preset features; if the micro-Doppler features corresponding to multiple consecutive frames of echo data are the preset features, then it is determined that there is a vehicle crossing and obstructing the vehicle's driving direction.

[0022] Optionally, in one embodiment of this application, it further includes: an identification module, configured to, after determining that there is a vehicle crossing and obstructing the vehicle in the vehicle's driving direction, identify the longitudinal distance between the vehicle and the vehicle crossing and obstructing the vehicle based on the echo data of multiple consecutive frames, and identify the actual position of the vehicle crossing and obstructing the vehicle based on the point cloud data in the vehicle's driving direction; and a control module, configured to, when determining that the vehicle meets preset conditions based on the longitudinal distance and / or the actual position, control the vehicle to perform a preset reminder action and / or a preset safety action.

[0023] Optionally, in one embodiment of this application, the identification module is further configured to extract distance features of the time-frequency map corresponding to multiple consecutive frames of echo data; and determine the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on the distance features.

[0024] Optionally, in one embodiment of this application, the identification module is further configured to identify the number of effective point clouds accumulated on the left and right sides of the vehicle's driving direction; and to take the position where the number of effective point clouds is greater than a preset number as the actual position of the vehicle crossing the obstruction.

[0025] Optionally, in one embodiment of this application, the control module is further configured to determine the risk level of a collision between the vehicle and the vehicle crossing the obstruction based on the longitudinal distance and / or the actual position; if the risk level is greater than a preset level, the control module controls the vehicle to perform a preset reminder action and the preset safety action; otherwise, the control module controls the vehicle to perform a preset reminder action.

[0026] Optionally, in one embodiment of this application, it further includes: a generation module, configured to generate a schematic image based on the longitudinal distance and / or actual position after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, and to display the position and / or distance between the vehicle and the vehicle crossing and obstructing the vehicle in the schematic image.

[0027] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the occlusion vehicle detection method as described in the above embodiments.

[0028] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle occlusion detection method as described in the above embodiments.

[0029] Therefore, this application has at least the following beneficial effects:

[0030] 1. The embodiments of this application can perform time-frequency analysis on the echo data in the vehicle's driving direction and extract micro-Doppler features. By using the micro-Doppler features to output the marker position of the vehicle crossing, the accurate identification of the vehicle crossing the vehicle can be achieved. When there is a vehicle crossing the vehicle in the vehicle's driving direction, collisions can be avoided in advance, sudden braking can be avoided, the driving safety and ride comfort of the vehicle can be improved, and the probability of traffic accidents can be effectively reduced.

[0031] 2. The embodiments of this application can avoid false detections and improve the accuracy of identifying vehicles that cross the road while occluded by comparing whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all preset features.

[0032] 3. The embodiments of this application can determine the possibility of a collision based on the longitudinal distance between the current vehicle and the vehicle blocking the crossing vehicle and the actual position of the vehicle blocking the crossing vehicle, and promptly control the vehicle to issue warnings and take corresponding safety actions to avoid sudden braking and improve the driving safety and ride comfort of the vehicle.

[0033] 4. The embodiments of this application can compare the results of multiple consecutive frames to more accurately determine the longitudinal distance of the obstruction crossing the vehicle.

[0034] 5. In this embodiment of the application, the actual position of the vehicle can be determined as to be on the right or left side based on the number of effective point clouds accumulated on the left and right sides of the vehicle, so as to achieve accurate identification of vehicles crossing the road.

[0035] 6. The embodiments of this application can determine the risk level of a vehicle collision and promptly remind the user to take appropriate action to control the vehicle to perform safe actions, thereby effectively reducing the probability of traffic accidents.

[0036] 7. The embodiments of this application can display the distance and location information of vehicles obstructing the view in front of the user through a schematic diagram, so as to facilitate the user's viewing and timely avoidance of risks.

[0037] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0038] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0039] Figure 1 This is a flowchart of a vehicle obstruction detection method provided according to an embodiment of this application;

[0040] Figure 2 This is a schematic diagram of the structure of the vehicle obstruction detection system provided in the embodiments of this application;

[0041] Figure 3 This is a schematic diagram of the occluded vehicle recognition process provided according to an embodiment of this application;

[0042] Figure 4 A time-frequency diagram of a vehicle being obstructed according to an embodiment of this application;

[0043] Figure 5 This is a schematic diagram illustrating the position of a vehicle obstructing a crossing, according to one embodiment of this application.

[0044] Figure 6 This is a block diagram of a vehicle detection device according to an embodiment of this application;

[0045] Figure 7 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0046] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0047] The following description, with reference to the accompanying drawings, outlines an embodiment of a vehicle occlusion detection method, apparatus, vehicle, and storage medium for this application. Addressing the problems mentioned in the background section, this application provides a vehicle occlusion detection method. This method involves time-frequency analysis of echo data along the vehicle's travel direction and extraction of micro-Doppler features. The micro-Doppler features are used to output a marker for vehicles crossing the road, enabling accurate identification of occluded vehicles crossing the road. When an occluded vehicle is present in the vehicle's travel direction, collisions can be avoided in advance, preventing sudden braking, improving driving safety and passenger comfort, and effectively reducing the probability of traffic accidents. This solves the problems of limited scanning range and accuracy of detectors in related technologies, which prevent the detection of occluded vehicles crossing the road, resulting in identification difficulties and poor safety.

[0048] Specifically, Figure 1 This is a flowchart illustrating a method for detecting obstructed vehicles provided in an embodiment of this application.

[0049] like Figure 1 As shown, the method for detecting obstructed vehicles includes the following steps:

[0050] In step S101, echo data in the vehicle's driving direction is acquired.

[0051] This application mainly addresses scenarios where vehicles are obstructed from crossing. For ease of explanation, the embodiments of this application can take an underground parking garage scenario as an example, using high-resolution forward millimeter-wave radar to detect vehicles obstructed from crossing.

[0052] Specifically, embodiments of this application can install a 4D imaging radar onto a test vehicle, such as... Figure 2 The diagram shows that the front radar is connected to the vehicle infotainment system, chassis system, and motion domain controller. At the same time, a vehicle is parked in a garage at a certain distance from the front of the vehicle to block vehicles from crossing the parking space and to prevent vehicles from slowly driving out of the parking space. The test vehicle moves forward at a certain speed, and the radar beam passes through the front of the vehicle to form echo data.

[0053] In step S102, time-frequency analysis is performed on the echo data to obtain a time-frequency map, the micro-Doppler features of the time-frequency map are extracted, and it is identified whether the micro-Doppler features are preset features.

[0054] It is understandable that, such as Figure 3 As shown in the figure, the embodiments of this application can perform time-frequency analysis on the echo data to form a time-frequency diagram of the vehicle crossing, as illustrated in the figure below. Figure 4 As shown, a machine learning model is used to extract and predict the micro-motion features of occluded vehicles to obtain the prediction result of the current frame. Based on the prediction result, it is determined whether there is a vehicle crossing the line. If there is a vehicle crossing the line, micro-Doppler features are extracted from the time-frequency map. The target distance and target speed of the current frame are filtered out using the vehicle's historical distance and historical speed. The target is output by combining the angle, intensity, and position information of the surrounding point cloud. The recognition result is output.

[0055] In this embodiment of the application, a machine learning model is used to extract, identify and predict the micro-motion features of occluded vehicles. Time-frequency images of vehicles crossing the road at different locations in the garage can be collected, the machine learning model can be repeatedly trained, and the model can be continuously optimized by combining issues such as misidentification and late identification, so as to achieve the goal of stably detecting vehicles crossing the road in different occlusion scenarios.

[0056] In step S103, if the micro-Doppler feature is a preset feature, it is determined that there is a vehicle crossing and obstructing the vehicle's direction of travel; otherwise, it is determined that there is no vehicle crossing and obstructing the vehicle's direction of travel.

[0057] The preset features in this application embodiment can be identified by presence flags 1 and 0 to distinguish whether there is an obstruction to a vehicle crossing. If the presence flag of the obstruction to a vehicle crossing is 1, this application embodiment can determine that there is an obstruction to the vehicle crossing in the direction of travel; if the presence flag of the obstruction to a vehicle crossing is 0, this application embodiment can determine that there is no obstruction to the vehicle crossing in the direction of travel.

[0058] In one embodiment of this application, if the micro-Doppler feature is a preset feature, then determining that there is a vehicle crossing and obstructing the vehicle's direction of travel includes: identifying whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all preset features; if the micro-Doppler features corresponding to multiple consecutive frames of echo data are preset features, then determining that there is a vehicle crossing and obstructing the vehicle's direction of travel.

[0059] Among them, the preset features can be specifically defined, which refers to the micro-Doppler features corresponding to the presence of vehicles that cross and obstruct the view.

[0060] It is understood that during the lateral movement of a vehicle, the embodiments of this application can avoid false detections and achieve accurate identification of occluded lateral vehicles by comparing whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all preset features.

[0061] In one embodiment of this application, after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the method further includes: identifying the longitudinal distance between the vehicle and the vehicle crossing and obstructing the vehicle based on echo data from multiple consecutive frames, and identifying the actual position of the vehicle crossing and obstructing the vehicle based on point cloud data in the vehicle's direction of travel; and controlling the vehicle to perform a preset reminder action and / or a preset safety action when the vehicle meets preset conditions based on the longitudinal distance and / or the actual position.

[0062] This application embodiment can determine the longitudinal distance between the test vehicle and the vehicle crossing the obstruction based on multiple consecutive frames of echo data, and determine the vehicle's position information based on a small amount of point cloud data of the front of the obstructing vehicle detected by the front radar. It can then determine the possibility of a collision between the test vehicle and the vehicle crossing the obstruction, control the vehicle to issue a safety warning, avoid collisions in advance, avoid sudden braking, and improve the vehicle's driving safety and passenger comfort.

[0063] In one embodiment of this application, identifying the longitudinal distance between a vehicle and a vehicle crossing the obstruction based on multiple consecutive frames of echo data includes: extracting distance features from the time-frequency map corresponding to the multiple consecutive frames of echo data; and determining the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on the distance features.

[0064] To more accurately determine the longitudinal distance of vehicles crossing the road, embodiments of this application can compare the results of multiple consecutive frames to achieve stable identification based on micro-Doppler features.

[0065] In one embodiment of this application, identifying the actual position of a vehicle crossing an obstruction based on point cloud data along the vehicle's driving direction includes: identifying the number of effective point clouds accumulated on the left and right sides along the vehicle's driving direction; and taking the position where the number of effective point clouds is greater than a preset number as the actual position of the vehicle crossing the obstruction.

[0066] The preset quantity can be set or calibrated according to the actual situation, without specific limitations.

[0067] This application embodiment can detect a small amount of point cloud obstructing the front of a vehicle using a front radar. The number of effective point clouds accumulated on the left and right sides represents the left and right directions. The cross-vehicle orientation marker output based on the point cloud data can be represented by 0, 1, and 2, where 0 indicates unidentified, 1 indicates left, and 2 indicates right. During the vehicle's cross-vehicle movement, as time progresses, the number of point clouds accumulated on one side gradually increases, while the number on the other side is relatively small, thus determining whether the vehicle's actual position is on the right or left. Furthermore, the detected cross-vehicle marker, left and right orientation, and distance are output via Ethernet signals, such as... Figure 5 As shown. In actual implementation, the embodiments of this application can set the number of effective point clouds, and the position where the effective point cloud data of the vehicle is increased to or greater than a preset number can be used as the actual position of the vehicle crossing and obstructing the view. The preset number can be set according to the actual situation and is not specifically limited.

[0068] It should be noted that due to the influence of noise, there may be unstable or incorrect orientation recognition, especially near walls, pillars and gates. In this embodiment, the confidence level can be added to filter the orientation.

[0069] In one embodiment of this application, when the vehicle meets preset conditions based on the longitudinal distance and / or actual position, the vehicle is controlled to perform preset reminder actions and / or preset safety actions, including: determining the risk level of collision risk between the vehicle and the vehicle crossing the obstruction based on the longitudinal distance and / or actual position; if the risk level is greater than the preset level, the vehicle is controlled to perform preset reminder actions and preset safety actions, otherwise the vehicle is controlled to perform preset reminder actions.

[0070] It is understood that the embodiments of this application can determine the degree of collision risk based on the longitudinal distance and actual position of the current test vehicle and the vehicle crossing the obstruction, in order to execute different action warnings. In the embodiments of this application, the risk level can be divided according to the actual situation, such as low risk, medium risk, etc.

[0071] In actual implementation, the embodiments of this application can set a preset level of medium risk. When the risk of a vehicle collision is greater than the preset medium risk, the embodiments of this application can control the vehicle's acoustic warning device or optical warning device to issue a warning, such as a voice warning from the car audio system or flashing headlights. At the same time as issuing the warning, the vehicle can brake and slow down in time to avoid a collision. Otherwise, the vehicle's acoustic warning device or optical warning device can be controlled to issue a warning, reminding the user to make a timely response, avoid sudden braking, and improve the vehicle's driving safety and passenger comfort.

[0072] In one embodiment of this application, after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the method further includes: generating a schematic diagram based on the longitudinal distance and / or actual position, and displaying the position and / or distance between the vehicle and the vehicle crossing and obstructing the vehicle in the schematic diagram.

[0073] This application embodiment can transmit the detected cross-vehicle signal to the domain control system via Ethernet, and form a signal that the actuator can process through decision-making. After receiving the signal, the vehicle unit displays the cross-vehicle ahead on the screen, which is convenient for users to view and avoid risks in time.

[0074] The vehicle obstruction detection method proposed in this application analyzes the echo data in the vehicle's direction of travel using time-frequency analysis and extracts micro-Doppler features. It then uses these micro-Doppler features to output a marker for vehicles crossing the road, achieving accurate identification of obstructed vehicles. When an obstructing vehicle is present in the vehicle's direction of travel, collisions can be avoided in advance, preventing sudden braking and improving driving safety and passenger comfort, effectively reducing the probability of traffic accidents. This solves the problems of limited scanning range and accuracy of detectors in related technologies, which prevent accurate detection of obstructed vehicles crossing the road, resulting in identification difficulties and poor safety.

[0075] Next, referring to the accompanying drawings, an obstruction vehicle detection device according to an embodiment of this application is described.

[0076] Figure 6 This is a block diagram of a vehicle detection device according to an embodiment of this application.

[0077] like Figure 6 As shown, the vehicle obstruction detection device 10 includes: an acquisition module 100, a processing module 200, and a determination module 300.

[0078] The acquisition module 100 is used to acquire echo data in the direction of vehicle travel; the processing module 200 is used to perform time-frequency analysis on the echo data to obtain a time-frequency map, extract the micro-Doppler features of the time-frequency map, and identify whether the micro-Doppler features are preset features; the determination module 300 is used to determine that there is a vehicle crossing and obstructing the direction of vehicle travel when the micro-Doppler features are preset features, otherwise it is determined that there is no vehicle crossing and obstructing the direction of vehicle travel.

[0079] In one embodiment of this application, the determination module 300 is further used to identify whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all preset features; if the micro-Doppler features corresponding to multiple consecutive frames of echo data are preset features, then it is determined that there is a vehicle crossing and obstructing the vehicle in the direction of travel.

[0080] In one embodiment of this application, the apparatus 10 further includes an identification module and a control module.

[0081] The identification module is used to identify the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on the echo data of multiple consecutive frames after determining that there is a vehicle crossing the obstruction in the vehicle's driving direction, and to identify the actual position of the vehicle crossing the obstruction based on the point cloud data in the vehicle's driving direction; the control module is used to control the vehicle to perform preset reminder actions and / or preset safety actions when it is determined that the vehicle meets preset conditions based on the longitudinal distance and / or the actual position.

[0082] In one embodiment of this application, the identification module is further configured to extract distance features from the time-frequency map corresponding to multiple consecutive frames of echo data; and determine the longitudinal distance between the vehicle and the vehicle crossing the obstruction based on the distance features.

[0083] In one embodiment of this application, the identification module is further used to identify the number of effective point clouds accumulated on the left and right sides of the vehicle's driving direction; and to take the position where the number of effective point clouds is greater than a preset number as the actual position of the vehicle crossing the obstruction.

[0084] In one embodiment of this application, the control module is further configured to determine the risk level of a collision between the vehicle and a vehicle crossing and obstructing the view based on the longitudinal distance and / or the actual position; if the risk level is greater than a preset level, the control module controls the vehicle to perform a preset warning action and a preset safety action; otherwise, the control module controls the vehicle to perform a preset warning action.

[0085] In one embodiment of this application, the apparatus 10 of this application embodiment further includes: a generation module.

[0086] The generation module is used to generate a schematic diagram based on the longitudinal distance and / or actual position after determining that there is a vehicle crossing and obstructing the vehicle's direction of travel. The schematic diagram displays the position and / or distance between the vehicle and the vehicle crossing and obstructing the vehicle.

[0087] It should be noted that the foregoing explanation of the embodiment of the vehicle obstruction detection method also applies to the vehicle obstruction detection device of this embodiment, and will not be repeated here.

[0088] The vehicle obstruction detection device proposed in this application performs time-frequency analysis on the echo data in the vehicle's driving direction and extracts micro-Doppler features. It then uses these micro-Doppler features to output a marker for vehicles crossing the road, achieving accurate identification of obstructed or obstructing vehicles. When an obstructing vehicle is present in the vehicle's driving direction, it can avoid collisions in advance, preventing sudden braking and improving driving safety and passenger comfort, effectively reducing the probability of traffic accidents. This solves the problems of limited scanning range and accuracy of detectors in related technologies, which prevent the detection of obstructed or obstructing vehicles, resulting in identification difficulties and poor safety.

[0089] Figure 7A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0090] The memory 701, the processor 702, and the computer program stored on the memory 701 and executable on the processor 702.

[0091] When the processor 702 executes the program, it implements the vehicle occlusion detection method provided in the above embodiments.

[0092] Furthermore, the vehicle also includes:

[0093] Communication interface 703 is used for communication between memory 701 and processor 702.

[0094] The memory 701 is used to store computer programs that can run on the processor 702.

[0095] The memory 701 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0096] If the memory 701, processor 702, and communication interface 703 are implemented independently, then the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0097] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0098] The processor 702 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0099] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for detecting obstructed vehicles.

[0100] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0102] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0103] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0104] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0105] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for detecting obstructed vehicles, characterized in that, Includes the following steps: Acquire echo data in the vehicle's direction of travel; Time-frequency analysis is performed on the echo data to obtain a time-frequency map, the micro-Doppler features of the time-frequency map are extracted, and it is identified whether the micro-Doppler features are preset features; If the micro-Doppler feature is the preset feature, it is determined that there is a vehicle crossing and obstructing the vehicle's direction of travel; otherwise, it is determined that there is no vehicle crossing and obstructing the vehicle's direction of travel. If the micro-Doppler feature is the preset feature, then determining that there is a vehicle obstructing the vehicle's travel direction includes: Identify whether the micro-Doppler features corresponding to multiple consecutive frames of echo data are all the preset features; If the micro-Doppler features corresponding to the echo data of the consecutive frames are the preset features, then it is determined that there is a vehicle crossing and obstructing the vehicle's direction of travel. The preset feature refers to the micro-Doppler feature corresponding to the presence of a vehicle that crosses and obstructs the view.

2. The method according to claim 1, characterized in that, After determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the process also includes: The longitudinal distance between the vehicle and the vehicle crossing the obstruction is identified based on the echo data of multiple consecutive frames, and the actual position of the vehicle crossing the obstruction is identified based on the point cloud data in the direction of the vehicle's travel. When the vehicle meets the preset conditions based on the longitudinal distance and / or actual position, the vehicle is controlled to perform preset reminder actions and / or preset safety actions.

3. The method according to claim 2, characterized in that, The step of identifying the longitudinal distance between the vehicle and the transversely obstructing vehicle based on echo data from multiple consecutive frames includes: Extract and identify the distance features of the time-frequency map corresponding to multiple consecutive frames of echo data; The longitudinal distance between the vehicle and the vehicle that crosses the obstruction is determined based on the distance characteristics.

4. The method according to claim 2, characterized in that, The step of identifying the actual position of the vehicle crossing the obstruction based on point cloud data in the vehicle's direction of travel includes: Identify the number of effective point clouds accumulated on the left and right sides of the vehicle's driving direction; The location where the number of effective point clouds is greater than a preset number is taken as the actual location of the vehicle that crosses the obstruction.

5. The method according to claim 2, characterized in that, When the vehicle is determined to meet the preset conditions based on the longitudinal distance and / or actual position, the system controls the vehicle to perform preset reminder actions and / or preset safety actions, including: The risk level of collision risk between the vehicle and the vehicle crossing the obstruction is determined based on the longitudinal distance and / or the actual location. If the risk level is greater than the preset level, then the vehicle is controlled to perform the preset reminder action and the preset safety action; otherwise, the vehicle is controlled to perform the preset reminder action.

6. The method according to claim 2, characterized in that, After determining that there is a vehicle crossing and obstructing the vehicle's direction of travel, the process also includes: A schematic diagram is generated based on the longitudinal distance and / or actual position, showing the position and / or distance between the vehicle and the vehicle that crosses and blocks the view.

7. A vehicle obstruction detection device, characterized in that, For implementing the vehicle occlusion detection method as described in any one of claims 1-6, the vehicle occlusion detection device comprises: The acquisition module is used to acquire echo data in the vehicle's driving direction; The processing module is used to perform time-frequency analysis on the echo data to obtain a time-frequency map, extract the micro-Doppler features of the time-frequency map, and identify whether the micro-Doppler features are preset features; The determination module is used to determine that there is a vehicle crossing and obstructing the vehicle's direction of travel when the micro-Doppler feature is the preset feature, otherwise it determines that there is no vehicle crossing and obstructing the vehicle's direction of travel.

8. A vehicle, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle obstruction detection method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the occlusion vehicle detection method as described in any one of claims 1-6.

Images