Vehicle steering obstacle avoidance warning method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle steering obstacle avoidance warning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-detected image and predicted collision time of a front target object, obtaining the predicted collision time based on a collision detection sensor, carrying out the feature extraction of the to-be-detected image, obtaining a detection feature, and carrying out the detection of the to-be-detected image; the method comprises the following steps: acquiring a detection feature of a vehicle, matching the detection feature with model features of a plurality of preset models to obtain a target matching result, and if the target matching result is that a target object model exists, the predicted collision time is smaller than a preset first time threshold value, and steering lane changing operation exists, generating a steering obstacle avoidance warning signal to warn a rear vehicle; according to the method, the image recognition result, the predicted collision time and the steering and lane changing operation are comprehensively judged, the rear vehicle is warned in time when the vehicle turns to avoid obstacles, the false alarm rate is reduced, and the vehicle driving safety is improved.

Description

Technical Field

[0001] The present application relates to the field of driving safety technology, and in particular to a vehicle steering obstacle avoidance warning method, device, electronic device and storage medium. Background Art

[0002] With the development of automobile intelligence and automation, various driving assistance systems have gradually become popular, such as Automatic Emergency Braking (AEB), Lane Departure Warning (LDW), etc. In the existing technical solutions, there are two solutions to deal with the identification of dangerous scenes: one is to avoid collisions through AEB. In most emergency obstacle avoidance scenarios, collisions can be avoided through the driver's steering and lane change operations, and AEB intervention is not required. Triggering AEB has a great impact on the comfort of the driver and passengers, and there is a greater risk of rear-end collisions from the rear vehicles; the second solution is to remind the driver of the risk of collision through sound and steering wheel vibration, and the driver decides whether to change lanes to avoid the risk.

[0003] However, both of the above solutions currently lack the function of timely warning to the rear vehicles. When the driver suddenly takes obstacle avoidance measures, the rear vehicles may not be able to respond in time due to insufficient information, thereby increasing the risk of rear-end collisions. In addition, the rear vehicles in the original lane may recognize the dangerous information of the obstacle in front too late, causing vehicle injuries and personal injuries. Summary of the invention

[0004] The present application provides a vehicle steering obstacle avoidance warning method, device, electronic device and storage medium to solve the above-mentioned technical problem that it is impossible to promptly warn the following vehicle when the vehicle is steering to avoid obstacles.

[0005] In one embodiment of the present application, the present application provides a vehicle steering obstacle avoidance warning method, including: obtaining an image to be inspected and a predicted collision time of a target object in front, wherein the predicted collision time is obtained based on a collision detection sensor; performing feature extraction on the image to be inspected to obtain detection features, and matching the detection features with model features of multiple preset models to obtain a target matching result; if the target matching result is that there is a target object model, and the predicted collision time is less than a preset first time threshold, and a steering and lane change operation is detected, a steering obstacle avoidance warning signal is generated to warn the following vehicle.

[0006] In one embodiment of the present application, before generating a steering obstacle avoidance warning signal, the method further includes: if the target matching result is that a target object model exists and the predicted collision time is less than a preset first time threshold, then obtaining a steering wheel angle rate; if the steering wheel angle rate is greater than a preset steering rate threshold and the duration is greater than a preset second time threshold, then detecting the presence of a steering lane change operation; if the target matching result is that a pedestrian model exists or a lane line model exists and the predicted collision time is less than a preset third time threshold, then generating an obstacle avoidance warning signal to warn the following vehicle in advance; wherein the preset third time threshold is greater than the preset first time threshold, the steering obstacle avoidance warning signal and the obstacle avoidance warning signal are used to control the vehicle lighting system to display different warning lights, and the lane line model is used to characterize a scene where a vehicle merges into a front ramp where the lane line changes from a solid line to a dotted line.

[0007] In one embodiment of the present application, the steering obstacle avoidance warning signal is used to control the brake light in the vehicle lighting system to be always on for a preset fourth time threshold, the turn signal on the same side of the steering wheel turning direction to be always on for a preset fifth time threshold, and the hazard warning light to flash for a preset sixth time threshold; the obstacle avoidance warning signal is used to control the brake light to be always on for a preset seventh time threshold and the target turn signal to flash for a preset number of times threshold.

[0008] In one embodiment of the present application, obtaining a predicted collision time includes: measuring the distance to the target object in front by transmitting a linear frequency modulation signal twice to obtain a first measured distance and a second measured distance; determining a relative speed according to the difference between the transmission frequency of the linear frequency modulation signal, the first measured distance, and the second measured distance; determining a predicted collision time according to the relative speed and the second measured distance; wherein the measurement time of the second measured distance is later than the measurement time of the first measured distance.

[0009] In one embodiment of the present application, the distance to the target in front is measured by transmitting a linear frequency modulation signal, including: transmitting a linear frequency modulation signal to the target in front, and receiving a reflected signal reflected by the target in front; mixing the reflected signal and the linear frequency modulation signal to obtain an intermediate frequency signal; determining the measured distance of the target according to the signal frequency of the intermediate frequency signal and the frequency modulation slope of the linear frequency modulation signal; wherein the measured distance of the target includes a first measured distance or a second measured distance.

[0010] In one embodiment of the present application, feature extraction is performed on the image to be inspected to obtain detection features, including: converting the image to be inspected into a grayscale image, and smoothing the grayscale image through a preset filter to obtain a denoised image; connecting multiple pixel points to be inspected in the denoised image whose actual gradient amplitude is greater than a preset gradient amplitude to obtain a target object contour feature; performing corner point detection on the denoised image to obtain corner point features; extracting the texture of the denoised image to obtain texture features; wherein the detection features include the target object contour features, the corner point features and the texture features.

[0011] In one embodiment of the present application, corner point detection is performed on the denoised image to obtain corner point features, including: calculating the horizontal gradient and vertical gradient of each pixel to be detected in the denoised image by a preset gradient operator; constructing a structure tensor matrix according to the horizontal gradient and vertical gradient of each pixel to be detected, and calculating the tensor eigenvalue of the structure tensor matrix in each pixel to be detected; substituting each tensor eigenvalue into a preset response relationship to obtain a response value of each pixel to be detected; if the response value of a pixel to be detected is greater than a preset response threshold, the pixel to be detected is determined as a potential corner point; wherein the corner point features include at least one potential corner point.

[0012] In one embodiment of the present application, the present application provides a vehicle steering obstacle avoidance warning device, including: an acquisition module, used to acquire an image to be inspected and a predicted collision time of a target object in front; a feature detection module, used to extract features from the image to be inspected, obtain detection features, and match the detection features with model features of multiple preset models to obtain a target matching result; a rear vehicle warning module, used to generate a steering obstacle avoidance warning signal to warn the rear vehicle if the target matching result is that a target object model exists, and the predicted collision time is less than a preset first time threshold, and a steering and lane change operation is detected.

[0013] In one embodiment of the present application, the present application provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the vehicle steering obstacle avoidance warning method as described in any of the above embodiments.

[0014] In one embodiment of the present application, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the vehicle steering obstacle avoidance warning method described in any one of the above embodiments.

[0015] Beneficial effects of the embodiments of the present application: The present application provides a vehicle steering obstacle avoidance warning method, device, electronic device and storage medium. The embodiments of the present application comprehensively judge the image recognition results, predict the collision time and the steering and lane change operations, and timely warn the following vehicle when the vehicle turns to avoid obstacles, thereby reducing the false alarm rate and improving the safety of vehicle driving.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiments of the present application can be applied;

[0019] Figure 2 A schematic diagram of a process flow of a vehicle steering obstacle avoidance warning method according to an embodiment of the present application is shown;

[0020] Figure 3 An application scenario of encountering a truck ahead according to an embodiment of the present application is shown;

[0021] Figure 4 An application scenario in which a vehicle merges into a right ramp according to an embodiment of the present application is shown;

[0022] Figure 5 An application scenario of a pedestrian crossing ahead according to an embodiment of the present application is shown;

[0023] Figure 6 A block diagram of a vehicle steering obstacle avoidance warning device according to an embodiment of the present application is shown;

[0024] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0027] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0028] See also Figure 1 , Figure 1 A schematic diagram of an exemplary system architecture to which the technical solution of the embodiment of the present application can be applied is shown. Figure 1 As shown, the system architecture may include a vehicle 101 and a front target 102. The vehicle 101 is used to detect that the front target 102 poses a danger to driving and warn the following vehicle.

[0029] Exemplarily, the vehicle 101 obtains an image to be inspected and a predicted collision time of a target object in front, and the predicted collision time is obtained based on a collision detection sensor; feature extraction is performed on the image to be inspected to obtain detection features, and the detection features are matched with model features of multiple preset models to obtain a target matching result; if the target matching result is that there is a target object model, and the predicted collision time is less than a preset first time threshold, and a turning lane change operation is detected, a turning obstacle avoidance warning signal is generated to alert the following vehicle.

[0030] In the related art, there is a technical problem that it is impossible to promptly warn the following vehicle when the vehicle turns to avoid obstacles.

[0031] In order to solve the above technical problems, the present application provides a vehicle steering obstacle avoidance warning method, device, electronic device and storage medium. The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.

[0032] See also Figure 2 , Figure 2 FIG. 2 shows a flow chart of a vehicle steering obstacle avoidance warning method according to an embodiment of the present application. Figure 2 As shown, in an exemplary embodiment, the vehicle steering obstacle avoidance warning method includes at least steps S210 to S230, which are described in detail as follows:

[0033] Step S210, obtaining an image of a target object to be inspected and a predicted collision time.

[0034] Among them, the predicted collision time is obtained based on the collision detection sensor

[0035] In one embodiment of the present application, the front target includes vehicles, pedestrians, and lane lines, wherein the vehicles include trucks, two-wheeled vehicles, cars, and the like.

[0036] In one embodiment of the present application, obtaining a predicted collision time includes: measuring the distance to a target ahead by transmitting a linear frequency modulation signal twice to obtain a first measured distance and a second measured distance; determining a relative speed according to a difference between a transmission frequency of the linear frequency modulation signal and the first measured distance and the second measured distance; determining a predicted collision time according to the relative speed and the second measured distance; wherein the measurement time of the second measured distance is later than the measurement time of the first measured distance.

[0037] In one embodiment of the present application, the distance to a target object in front is measured by transmitting a linear frequency modulation signal, including: transmitting a linear frequency modulation signal to the target object in front, and receiving a reflected signal reflected back by the target object in front; mixing the reflected signal and the linear frequency modulation signal to obtain an intermediate frequency signal; determining the measured distance of the target object according to the signal frequency of the intermediate frequency signal and the frequency modulation slope of the linear frequency modulation signal; wherein the measured distance of the target object includes a first measured distance or a second measured distance.

[0038] In one embodiment of the present application, the collision detection sensor includes a millimeter wave radar, which transmits millimeter wave band radio waves forward, receives reflected signals, and calculates the distance, speed and direction of the target in front by measuring the round-trip time difference and frequency change of the signal.

[0039] In one embodiment of the present application, a millimeter wave radar transmits a linear frequency modulated continuous wave (Frequency Modulated Continuous Wave, FMCW) through a transmitting antenna, and the FMCW radar transmits a linear frequency modulation (Linear Frequency Modulation, LFM) signal, also known as a chirp signal. A chirp signal is an electromagnetic wave whose frequency changes linearly with time, and the frequency modulation slope of the chirp signal is K. When the transmitted electromagnetic wave encounters a target object, it will be reflected back, and the reflected electromagnetic waves will be received by a receiving antenna. The received reflected wave is mixed with the transmitted wave to generate an intermediate frequency (Intermediate Frequency, IF) signal. The signal frequency of the intermediate frequency signal is proportional to the distance of the target object. By measuring the signal frequency of this intermediate frequency signal, the time difference between the electromagnetic wave traveling to and from the radar and the target object can be calculated.

[0040] In one embodiment of the present application, the method for determining the measured distance of the target object is as follows:

[0041]

[0042] Among them, Δd is the measured distance of the target object, k is the frequency modulation slope of the linear frequency modulation signal, Δf is the signal frequency of the intermediate frequency signal, and c is the speed of light.

[0043] In one embodiment of the present application, the relative speed Δv between the vehicle and the target object in front can be calculated by the change value of the distance measured by the target object. The relative speed is determined as follows:

[0044] Δv=(Δd 2 -Δd 1 )×a Formula (2)

[0045] Where Δv is the relative velocity, Δd 2 is the second measured distance, Δd 1 is the first measured distance, and a is the transmitting frequency of the linear frequency modulation signal.

[0046] In one embodiment of the present application, the method for determining the predicted collision time is as follows:

[0047] TTC=Δd 2 / Δv Formula (3)

[0048] Where TTC is the predicted collision time, Δd 2 is the second measured distance, and Δv is the relative speed.

[0049] Step S220, extracting features from the image to be inspected to obtain detection features, and matching the detection features with model features of multiple preset models to obtain target matching results.

[0050] In one embodiment of the present application, feature extraction is performed on an image to be inspected to obtain detection features, including: converting the image to be inspected into a grayscale image, and smoothing the grayscale image through a preset filter to obtain a denoised image; connecting multiple pixel points to be inspected in the denoised image whose actual gradient amplitude is greater than a preset gradient amplitude to obtain a target object contour feature; performing corner point detection on the denoised image to obtain corner point features; extracting the texture of the denoised image to obtain texture features; wherein the detection features include target object contour features, corner point features and texture features.

[0051] In one embodiment of the present application, when the vehicle encounters a slow-moving or stationary vehicle in front, the image acquisition device captures the target in front and obtains the image to be inspected, thereby extracting features in the image to be inspected. The color image to be inspected is converted into a grayscale image. In the grayscale image, each pixel to be inspected has only one brightness value, that is, the grayscale value, and in order to reduce noise interference in the grayscale image, a preset filter can be used to smooth the grayscale image, such as a Gaussian filter, a median filter, etc.

[0052] In one embodiment of the present application, the image acquisition device includes a camera, which assists the millimeter-wave radar in target recognition and tracking by extracting features of the image to be inspected.

[0053] In one embodiment of the present application, edge pixels in a grayscale image can be screened out by setting a preset gradient amplitude threshold. Pixels to be detected that are higher than the preset gradient amplitude are considered to be part of the edge, and multiple edge pixels are obtained. For the detected edge pixels, an edge connection algorithm can be used to connect multiple edge pixels into a complete edge line or edge contour to obtain the contour features of the target object. The edge connection algorithm includes Hough transform, chain code tracking, etc. The edge position of the object is determined by detecting the change in pixel grayscale in the denoised image, outlining the outline of the vehicle, such as the unique rectangular shape and straight edges of a truck.

[0054] In one embodiment of the present application, corner point detection is performed on a denoised image to obtain corner point features, including: calculating the horizontal gradient and vertical gradient of each pixel to be detected in the denoised image by a preset gradient operator; constructing a structure tensor matrix according to the horizontal gradient and vertical gradient of each pixel to be detected, and calculating the tensor eigenvalue of the structure tensor matrix in each pixel to be detected; substituting each tensor eigenvalue into a preset response relationship to obtain a response value of each pixel to be detected; if the response value of a pixel to be detected is greater than a preset second threshold, the pixel to be detected is determined as a potential corner point; wherein the corner point feature includes at least one potential corner point.

[0055] In one embodiment of the present application, corner detection is performed on the denoised image that has been previously grayed and denoised and smoothed: the horizontal and vertical gradients of each pixel are calculated using a gradient operator, and for each pixel, the gradient operator includes a Sobel operator. A 2x2 structure tensor matrix is ​​constructed based on the gradient information of the surrounding area. The structure tensor matrix is ​​shown below:

[0056]

[0057] Among them, J is the structure tensor matrix, G x (i, j) is the horizontal gradient of the pixel (i, j) to be detected, G y (i, j) is the vertical gradient of the pixel (i, j) to be detected.

[0058] In one embodiment of the present application, the matrix eigenvalue λ of the structure tensor matrix of each pixel to be detected is calculated. 1 and λ 2 , use the eigenvalue to calculate the response value of each pixel to be tested. The preset response relationship is as follows:

[0059] R=λ 1 λ 2 -k(λ 1 +λ 2 ) 2 Formula (5)

[0060] Among them, R is the response value, λ 1 is the first eigenvalue of the structure tensor matrix, λ 2 The first eigenvalue of the structure tensor matrix, k is a preset constant.

[0061] In one embodiment of the present application, the preset constant k may have a value range of 0.04-0.06.

[0062] In one embodiment of the present application, a preset response threshold T is set, and the pixel points to be detected whose response value R is greater than the preset response threshold T are regarded as potential corner points. For a truck, the corners of its compartment, the connection between the wheel and the compartment, etc. will form obvious potential corner points, and these potential corner points will be highlighted in the feature extraction process.

[0063] In one embodiment of the present application, the compartment of a truck usually has a specific texture, such as the reflection of the metal surface, the color and texture of the paint, etc. Through texture analysis, the texture features of the truck surface can be extracted to further assist in identification.

[0064] In one embodiment of the present application, target recognition and matching are performed after feature extraction is completed, and the detection features collected previously are matched with model features of a plurality of predefined preset models.

[0065] In one embodiment of the present application, the preset models include a pedestrian model, a lane line model, and a vehicle model, wherein the vehicle model includes models corresponding to different vehicle models, such as a truck model.

[0066] In one embodiment of the present application, multiple preset models are used to match and identify detection features in different application scenarios.

[0067] Step S230: If the target matching result is that there is a target model, and the predicted collision time is less than the preset first time threshold, and a turning lane change operation is detected, a turning obstacle avoidance warning signal is generated to warn the following vehicle.

[0068] In one embodiment of the present application, before generating a steering obstacle avoidance warning signal, the method also includes: if the target matching result is that a target object model exists and the predicted collision time is less than a preset first time threshold, then obtaining a steering wheel angle rate; if the steering wheel angle rate is greater than a preset steering rate threshold and the duration is greater than a preset third time threshold, then a steering lane change operation is detected; if the target matching result is that a pedestrian model exists or a lane line model exists and the predicted collision time is less than a preset second time threshold, then generating an obstacle avoidance warning signal to warn the following vehicle in advance; wherein the preset second time threshold is greater than the preset first time threshold, the steering obstacle avoidance warning signal and the obstacle avoidance warning signal are used to control the vehicle lighting system to display different warning lights, and the lane line model is used to characterize the scene where the vehicle merges into the front ramp where the lane line changes from a solid line to a dotted line.

[0069] In one embodiment of the present application, the preset first time threshold can be set to 2 seconds, the preset second time threshold can be set to 50 milliseconds, the preset third time threshold can be set to 2.5 seconds, and the preset turning rate threshold can be set to 400° per second.

[0070] In one embodiment of the present application, the vehicle lighting system includes hazard warning lights, brake lights and turn signals for issuing warnings to following vehicles.

[0071] In one embodiment of the present application, the steering obstacle avoidance warning signal is used to control the brake lights in the vehicle lighting system to be always on for a preset fourth time threshold, the turn signal on the same side of the steering wheel turning direction to be always on for a preset fifth time threshold, and the hazard warning lights to flash for a preset sixth time threshold; the obstacle avoidance warning signal is used to control the brake lights to be always on for a preset seventh time threshold and the target turn signal to flash for a preset number of times threshold.

[0072] In one embodiment of the present application, the preset fourth time threshold can be set to 3 seconds, the preset fifth time threshold can be set to 2 seconds, the preset sixth time threshold can be set to 3 seconds, the preset seventh time threshold can be set to 0.5 seconds, and the preset number threshold can be set to 2 times.

[0073] In one embodiment of the present application, see Figure 3 , Figure 3 The following figure shows an application scenario of a truck in front of you according to an embodiment of the present application. Figure 3 As shown in the figure, when the image acquisition device successfully matches the target in front, senses the presence of a truck model in front, and calculates the predicted collision time TTC with the target in front to be less than 2 seconds, the rear warning system is in a waiting state, and the internal controller obtains the value of the steering wheel angle rate. If the steering wheel angle rate is greater than 400° per second and the duration is greater than 50ms. The rear warning system is activated. The internal controller sends a steering obstacle avoidance warning signal to the vehicle lighting system to control the turn signal on the same side of the steering wheel turning direction for 2 seconds, the brake light is always on for 3 seconds, and the hazard warning light flashes for 3 seconds, warning the rear vehicle in the same lane that there is an obstacle in front, and warning the rear vehicle to initiate a rapid lane change to avoid. After 3 seconds, the warning exits and enters a new perception detection cycle.

[0074] In one embodiment of the present application, see Figure 4 , Figure 4 The following figure shows an application scenario in which a vehicle merges into the right ramp according to an embodiment of the present application. Figure 4 As shown, when driving on a real road, there will be a situation where a vehicle merges into the right ramp. The vehicle on the right is driving too fast, and there are often guardrails and green belts on the right side, which interfere with the driver's line of sight. The distance to the vehicle in front is too close. In general, the speed of vehicles on the main road is faster than that of vehicles entering the ramp, resulting in a high relative speed between the two vehicles, creating a risk of collision. Since the risk of a front collision appears suddenly, the possibility of the driver making an emergency lane change and braking increases. This car can make a prompt before warning the vehicle behind.

[0075] In one embodiment of the present application, the image acquisition device can perform a lane line detection at this time, grayscale the acquired image, filter and denoise it, and then perform edge detection. The lane line usually appears as a clear edge. Finally, feature extraction is performed and compared with the predefined lane line model. When it is recognized that the lane line on the right side changes from a solid line to a dotted line, it can be assumed that there are more lanes on the right side and there is a possibility of vehicles merging in. If the predicted collision time TTC is calculated to be less than 2.5 seconds at this time, the brake stop light will light up for 0.5 seconds, and the left turn signal will flash twice and then go out to prompt the rear vehicle to slow down and predict the next operation of the vehicle. Regardless of whether the vehicle is changing lanes urgently or braking suddenly, the safety of the next operation of the vehicle can be guaranteed. If the risk of collision continues to increase, such as the predicted collision time TTC is less than 2 seconds, and the internal controller obtains a steering wheel angle rate greater than 400° per second and the duration is greater than 50 milliseconds. The rear warning system is activated. The internal controller sends a steering obstacle avoidance warning signal to the vehicle lighting system to control the turn signal on the same side of the steering wheel turning direction for 2 seconds, the brake light stays on for 3 seconds, and the hazard warning light flashes for 3 seconds, warning the following vehicle in the same lane that there is an obstacle ahead, and warning the following vehicle to initiate a quick lane change to avoid the obstacle. After 3 seconds, the warning is exited and a new perception detection cycle is entered.

[0076] In one embodiment of the present application, see Figure 5 , Figure 5 FIG. 2 shows an application scenario in which a pedestrian is crossing ahead according to an embodiment of the present application. Figure 5 As shown in the figure, when the presence of a pedestrian model is sensed and the predicted collision time TTC is less than 2.5S, an advance warning is also issued to the following vehicle. The advance warning can give the following vehicle more time to be alert to the next behavior of the vehicle, reducing the probability of accidents. In addition, different logics are used for different scenarios, and the scenarios are strictly restricted, which greatly reduces the false alarm rate when following the vehicle.

[0077] In one embodiment of the present application, the solution provided by the present application can be implemented on traditional L2-level vehicles. It is based on cameras and millimeter-wave radars and can be integrated with automatic emergency braking. It does not require additional hardware or software and is low-cost. Currently, there is no related emergency steering warning method for the following vehicles on the market. The present application can issue an obstacle warning to the following vehicles in a timely manner when there is a potential collision risk between the present vehicle and the target object in front, reminding the following vehicles to pay attention to the obstacles in front and the warning that the present vehicle will turn to avoid obstacles, thereby avoiding or reducing the occurrence of traffic accidents, increasing driving safety, and having broad application prospects and strong market demand. By combining brake lights and hazard lights The combination of warning lights provides multi-modal warnings, which improves the warning effect compared to traditional brake light warnings. By integrating the multi-sensor data of millimeter-wave radar and image acquisition equipment and linking the light alarm system with it, it can more accurately identify and track obstacles ahead, and predict their movement trajectory and collision time, greatly improving the accuracy of recognition, and warning vehicles behind, improving driving safety. The judgment of comprehensive image recognition results, the judgment of predicted collision time and the judgment of steering wheel angle rate reduce the false alarm rate. Early warning is provided for special scenarios, taking into account the false alarm rate of vehicle driving, and warnings can be issued earlier to reduce accidents.

[0078] See also Figure 6 , Figure 6 A block diagram of a vehicle steering obstacle avoidance warning device according to an embodiment of the present application is shown. The device can be applied to Figure 1 The implementation environment shown in the figure is specifically configured in the vehicle 101. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.

[0079] like Figure 6 As shown, a vehicle turning obstacle avoidance warning device 600 according to an embodiment of the present application includes: an acquisition module 601, a feature detection module 602 and a rear vehicle warning module 603.

[0080] The acquisition module 601 is used to acquire the image of the target object to be detected and predict the collision time, and the predicted collision time is obtained based on the collision detection sensor;

[0081] The feature detection module 602 is used to extract features from the image to be inspected to obtain detection features, and match the detection features with model features of multiple preset models to obtain target matching results;

[0082] The rear vehicle warning module 603 is used to generate a steering obstacle avoidance warning signal to warn the rear vehicle if the target matching result is that a target model exists, the predicted collision time is less than a preset first time threshold, and a steering lane change operation is detected.

[0083] It should be noted that the vehicle steering obstacle avoidance warning device provided in the above embodiment and the vehicle steering obstacle avoidance warning method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In practical applications, the vehicle steering obstacle avoidance warning device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0084] An embodiment of the present application also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the electronic device implements the vehicle steering obstacle avoidance warning method provided in the above-mentioned embodiments.

[0085] See also Figure 7 , Figure 7 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 7 The computer system 700 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0086] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703, such as executing the method in the above embodiment. In the random access memory 703, various programs and data required for system operation are also stored. The central processing unit 701, the read-only memory 702 and the random access memory 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0087] The following components are connected to the input / output interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0088] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 709, and / or installed from a removable medium 711. When the computer program is executed by a central processing unit (CPU) 701, various functions defined in the system of the present application are executed.

[0089] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0090] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The units involved in the embodiments described in the present application can be implemented by software or by hardware, and the units described can also be set in a processor. Among them, the names of these units do not constitute a limitation on the units themselves under certain circumstances. Therefore, the technical solution according to the implementation mode of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation mode of the present application.

[0092] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the vehicle steering obstacle avoidance warning method provided in the above-mentioned embodiments. The computer-readable storage medium may be included in the electronic device described in the above-mentioned embodiments, or may exist independently without being assembled into the electronic device.

[0093] In the above embodiments, unless otherwise specified, by using serial numbers such as "first" and "second" to describe common objects, it only means that they refer to different instances of the same object, rather than indicating that the objects being described must adopt a given order, whether in time, space, sorting or any other way.

[0094] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A vehicle steering obstacle avoidance warning method, characterized in that: The method comprises: Acquire an image of a target object to be inspected and a predicted collision time, wherein the predicted collision time is obtained based on a collision detection sensor; Extracting features from the image to be inspected to obtain detection features, and matching the detection features with model features of multiple preset models to obtain target matching results; If the target matching result is that there is a target object model, and the predicted collision time is less than the preset first time threshold, and a turning lane change operation is detected, a turning obstacle avoidance warning signal is generated to warn the following vehicle.

2. The vehicle steering obstacle avoidance warning method according to claim 1, characterized in that: Before generating the steering obstacle avoidance warning signal, the method further includes: If the target matching result is that there is a target model, and the predicted collision time is less than a preset first time threshold, obtaining a steering wheel angle rate; If the steering wheel angle rate is greater than a preset steering rate threshold, and the duration is greater than a preset second time threshold, a steering lane change operation is detected; If the target matching result is that a pedestrian model or a lane line model exists, and the predicted collision time is less than a preset third time threshold, an obstacle avoidance warning signal is generated to warn the following vehicle in advance; Among them, the preset third time threshold is greater than the preset first time threshold, the steering obstacle avoidance warning signal and the obstacle avoidance warning signal are used to control the vehicle lighting system to display different warning lights, and the lane line model is used to characterize the scene where the vehicle merging into the front ramp changes from a solid line to a dotted line.

3. The vehicle steering obstacle avoidance warning method according to claim 2, characterized in that: The steering obstacle avoidance warning signal is used to control the fourth time threshold for the brake light to be always on, the fifth time threshold for the turn signal on the same side of the steering wheel turning direction, and the sixth time threshold for the hazard warning light to flash; The obstacle avoidance warning signal is used to control the brake light to be always on for a preset seventh time threshold and the target turn signal to flash for a preset number of times threshold.

4. The vehicle steering obstacle avoidance warning method according to claim 1, characterized in that: Get the predicted collision time, including: The distance of the target object in front is measured by transmitting a linear frequency modulation signal twice to obtain a first measured distance and a second measured distance; determining a relative speed based on a transmission frequency of the linear frequency modulation signal, a difference between the first measured distance and the second measured distance; determining a predicted collision time according to the relative speed and the second measured distance; The calculation time of the second measured distance is later than the calculation time of the first measured distance.

5. The vehicle steering obstacle avoidance warning method according to claim 4, characterized in that: The distance measurement of the target ahead is performed by transmitting a linear frequency modulation signal, including: Transmitting a linear frequency modulation signal to the front target object, and receiving a reflected signal reflected back by the front target object; Mixing the reflected signal and the linear frequency modulation signal to obtain an intermediate frequency signal; Determine the target object measurement distance according to the signal frequency of the intermediate frequency signal and the frequency modulation slope of the linear frequency modulation signal; The target object measured distance includes a first measured distance or a second measured distance.

6. The vehicle steering obstacle avoidance warning method according to any one of claims 1 to 5, characterized in that: Extracting features from the image to be inspected to obtain detection features includes: Converting the image to be inspected into a grayscale image, and smoothing the grayscale image using a preset filter to obtain a noise-reduced image; Connecting a plurality of pixels to be inspected whose actual gradient amplitude is greater than a preset gradient amplitude in the denoised image to obtain contour features of the target object; Performing corner point detection on the denoised image to obtain corner point features; Extracting the texture of the denoised image to obtain texture features; Wherein, the detection features include the target object contour features, the corner point features and the texture features.

7. The vehicle steering obstacle avoidance warning method according to claim 6, characterized in that: Performing corner point detection on the denoised image to obtain corner point features includes: Calculating the horizontal gradient and vertical gradient of each pixel to be detected in the denoised image by using a preset gradient operator; Constructing a structure tensor matrix according to the horizontal gradient and the vertical gradient of each pixel to be inspected, and calculating the tensor eigenvalue of the structure tensor matrix in each pixel to be inspected; Substitute each tensor eigenvalue into the preset response relationship to obtain the response value of each pixel to be tested; If the response value of a pixel to be detected is greater than a preset response threshold, the pixel to be detected is determined as a potential corner point; Wherein, the corner point feature includes at least one potential corner point.

8. A vehicle steering obstacle avoidance warning device, characterized in that: The device comprises: An acquisition module, used to acquire an image of a target object to be inspected and a predicted collision time, wherein the predicted collision time is obtained based on a collision detection sensor; A feature detection module is used to extract features from the image to be detected to obtain detection features, and match the detection features with model features of multiple preset models to obtain target matching results; The rear vehicle warning module is used to generate a steering obstacle avoidance warning signal to warn the rear vehicle if the target matching result is that a target model exists, the predicted collision time is less than a preset first time threshold, and a steering lane change operation is detected.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the vehicle steering obstacle avoidance warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the vehicle steering obstacle avoidance warning method according to any one of claims 1 to 7.

Images