Visual target screening method and device, equipment and storage medium

Abstract

The invention discloses a visual target screening method, device and equipment and a storage medium, relates to the technical field of vehicle control, and discloses a visual target screening method which comprises the following steps: when a visual target is detected, obtaining a visual target motion state and a visual target distance, determining a corresponding visual target screening strategy based on the visual target motion state and the visual target distance; determining a visual target validity evaluation result according to the visual target motion state; and when the visual target validity evaluation result is that the visual target is valid, determining visual target delay processing time according to the visual target screening strategy so as to complete visual target screening. According to the scheme, misjudgment of the visual targets and unnecessary vehicle control intervention can be reduced through the corresponding visual target screening strategy.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a visual target screening method, device, equipment and storage medium. Background Art

[0002] Generally speaking, the recognition accuracy and priority of visual sensors are higher than other sensors such as radar. However, when the visual sensor is affected by its own characteristics and is inaccurate, the system itself cannot judge the accuracy. At this time, it is likely to cause a lot of bad user experience such as misscreening and misbraking. Therefore, it is urgent to solve this kind of problem.

[0003] Currently, many cruise systems use multiple sensor fusion technologies, such as cameras, radars, and lidars, to improve their ability to perceive the surrounding environment. These solutions usually combine advanced algorithms such as deep learning, pattern recognition, and machine vision technology to identify and track targets. However, since visual sensors are easily affected by ambient light, weather conditions, and obstructions, existing solutions still have the risk of misselection when processing visual targets. How to improve the accuracy of cruise systems in identifying visual targets has become an issue to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a visual target screening method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the accuracy of visual target recognition by the cruise system.

[0006] To achieve the above objectives, the present application proposes a visual target screening method, the method comprising:

[0007] When a visual target is detected, obtaining a visual target motion state and a visual target distance, and determining a corresponding visual target screening strategy based on the visual target motion state and the visual target distance;

[0008] Determining a visual target effectiveness evaluation result according to the visual target motion state;

[0009] When the visual target validity evaluation result is that the visual target is valid, the visual target delay processing time is determined according to the visual target screening strategy to complete the visual target screening.

[0010] In one embodiment, the visual target motion state includes a motion state and a stationary state;

[0011] The step of determining the visual target effectiveness evaluation result according to the visual target motion state comprises:

[0012] When the motion state of the visual target is a motion state, obtaining the visual target speed, the vehicle speed, the visual confidence and the environmental state information, and determining the visual target effectiveness evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence and the environmental state information;

[0013] When the motion state of the visual target is a stationary state, it is determined that the visual target validity evaluation result is that the visual target is valid.

[0014] In one embodiment, the step of determining the visual target effectiveness evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence, and the environmental state information comprises:

[0015] Determine a visual target distance linear change result, a visual target speed linear change result and a visual target speed integral result based on the visual target distance, the visual target speed and the vehicle speed;

[0016] Evaluate the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score;

[0017] A visual target effectiveness evaluation result is determined based on the visual target reality score.

[0018] In one embodiment, the step of evaluating the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score includes:

[0019] When the visual target distance is greater than a preset distance, and any one of the visual target distance linear change result, the visual target speed linear change result, and the visual target speed integral result satisfies a preset evaluation result, a first score, a second score, and a third score are generated based on the visual target distance linear change result, the visual target speed linear change result, and the visual target speed integral result;

[0020] The authenticity of the visual target is evaluated based on the first score, the second score, and the third score to obtain a visual target authenticity score.

[0021] In one embodiment, the step of evaluating the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score includes:

[0022] When the visual target distance is less than or equal to the preset distance, and any one of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence, and the environmental state information satisfies the preset evaluation result, a first score, a second score, a third score, a fourth score, and a fifth score are correspondingly generated based on the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence, and the environmental state information;

[0023] The authenticity of the visual target is evaluated based on the first score, the second score, the third score, the fourth score, and the fifth score to obtain a visual target authenticity score.

[0024] In one embodiment, when the visual target validity evaluation result is that the visual target is valid, determining the visual target delay processing time according to the visual target screening strategy to complete the step of visual target screening includes:

[0025] When the visual target validity evaluation result is that the visual target is valid and the motion state of the visual target is a stationary state, determining whether the visual target distance meets the delay processing condition according to the visual target screening strategy to obtain a delay determination result;

[0026] When the delay determination result is that the visual target distance meets the delay processing condition, the collision time of the visual target is obtained, and the visual target delay processing time is determined based on the collision time to complete the visual target screening.

[0027] In one embodiment, when the delay determination result is that the visual target distance meets the delay processing condition, the collision time of the visual target is obtained, and the visual target delay processing time is determined based on the collision time to complete the step of visual target screening, and further includes:

[0028] Acquire a first target deceleration of the visual target;

[0029] When the collision time is greater than or equal to a preset time and the first target deceleration satisfies a preset deceleration condition, sending a second target deceleration to the actuator, wherein the second target deceleration is less than the first target deceleration;

[0030] When the collision time is less than the preset time, the first target deceleration is sent to the actuator.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a visual target screening device, the visual target screening device comprising:

[0032] A screening strategy selection module, used to obtain a visual target motion state and a visual target distance when a visual target is detected, and determine a corresponding visual target screening strategy based on the visual target motion state and the visual target distance;

[0033] A visual target determination module, used to determine a visual target effectiveness evaluation result according to the visual target motion state;

[0034] The visual target processing module is used to determine the visual target delay processing time according to the visual target screening strategy to complete the visual target screening when the visual target validity evaluation result is that the visual target is valid.

[0035] In addition, to achieve the above-mentioned objectives, the present application also proposes a visual target screening device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the visual target screening method as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the visual target screening method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the visual target screening method described above are implemented.

[0038] One or more technical solutions proposed in this application have at least the following technical effects:

[0039] When a visual target is detected, the visual target motion state and visual target distance are obtained, and a corresponding visual target screening strategy is determined based on the visual target motion state and the visual target distance; a visual target validity evaluation result is determined according to the visual target motion state; when the visual target validity evaluation result is that the visual target is valid, a visual target delay processing time is determined according to the visual target screening strategy to complete visual target screening. The solution of the present application can determine an appropriate visual target screening strategy for the scene based on visual motion characteristics and distance characteristics when a visual target is detected, and determine a visual target delay processing time based on the visual target screening strategy, so that the cruise system can further collect visual target data for accurate analysis, reduce misjudgment and unnecessary intervention, and improve the response speed and accuracy to real obstacles, thereby improving the overall performance of autonomous driving and user comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 A schematic diagram of a process flow provided for Embodiment 1 of the visual target screening method of the present application;

[0043] Figure 2 A classification diagram of visual target screening strategies of the first embodiment of the visual target screening method of the present application;

[0044] Figure 3 A schematic diagram of a flow chart provided for Embodiment 2 of the visual target screening method of the present application;

[0045] Figure 4 This is a schematic diagram of the module structure of the visual target screening device according to an embodiment of the present application;

[0046] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the visual target screening method in the embodiment of the present application.

[0047] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0049] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0050] Since the existing technology's visual sensors are easily affected by ambient light, weather conditions and obstructions, the existing solutions still have the risk of misselection when processing visual targets. How to improve the accuracy of the cruise system's recognition of visual targets has become a problem to be solved.

[0051] The present application provides a solution, which is to obtain the visual target motion state and the visual target distance when a visual target is detected, and determine the corresponding visual target screening strategy based on the visual target motion state and the visual target distance; determine the visual target validity evaluation result according to the visual target motion state; when the visual target validity evaluation result is that the visual target is valid, determine the visual target delay processing time according to the visual target screening strategy to complete the visual target screening.

[0052] The solution of the present application can determine the appropriate visual target screening strategy for the scene according to the visual motion characteristics and distance characteristics when the visual target is detected, and determine the delayed processing time of the visual target according to the visual target screening strategy, so that the cruise system can further collect the data of the visual target for accurate analysis, which can reduce misjudgment and unnecessary intervention, and improve the response speed and accuracy to real obstacles, thereby improving the overall performance of autonomous driving and the user's vehicle comfort.

[0053] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a visual target screening device, etc. The following takes the visual target screening device as an example to illustrate this embodiment and the following embodiments.

[0054] Based on this, the present application embodiment provides a visual target screening method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the visual target screening method of the present application.

[0055] In this embodiment, the visual target screening method includes steps S10 to S40:

[0056] Step S10, when a visual target is detected, obtaining a visual target motion state and a visual target distance, and determining a corresponding visual target screening strategy based on the visual target motion state and the visual target distance;

[0057] It should be noted that due to the limitations of visual sensors, affected by the environment, weather, light conditions, etc., it is easy to mistakenly identify a non-existent obstacle, thereby braking the false obstacle target. Mis-braking will not only affect the user's car experience, but may also cause collisions and rear-end accidents with other vehicles. Therefore, it is necessary to reconfirm the target attributes given by the perception system. If they are not satisfied, the corresponding delayed target processing will be performed.

[0058] It should be understood that visual targets refer to objects detected by the visual sensors carried by autonomous vehicles, such as other vehicles, pedestrians, bicycles, road signs, and obstacles. Specifically, the visual target is a single visual target detected by a single visual sensor. In urban scenarios, when the vehicle is in a stable following state, new low-speed targets (such as pedestrians, parked vehicles, and other obstacles) may appear at the moment the front vehicle cuts out. In order to accurately screen the suddenly detected visual targets, it is necessary to formulate corresponding visual target screening strategies according to the visual target motion state and visual target distance. The visual target state refers to the stationary state and the moving state, and the visual target distance refers to the distance between the visual target and the vehicle.

[0059] For example, please refer to Figure 2 , Figure 2 This is a classification diagram of visual target screening strategies for the first embodiment of the visual target screening method of this application. Taking 70m as the distance threshold, different visual target screening strategies are adopted for detected moving visual targets and stationary visual targets, and different visual target screening strategies are adopted for detected visual targets within 70m and outside 70m. Only 70m is used as an example for illustration here, and this embodiment does not limit the specific distance.

[0060] Step S20, determining a visual target effectiveness evaluation result according to the visual target motion state;

[0061] It should be understood that the visual target effectiveness evaluation result includes the visual target being effective and the visual target being ineffective. For visual targets in different motion states, the visual target effectiveness evaluation result should be different.

[0062] In a feasible implementation manner, the visual target motion state includes a motion state and a static state, and step S20 may include steps S21 to S22:

[0063] Step S21, when the visual target motion state is a motion state, obtaining the visual target speed, the vehicle speed, the visual confidence and the environmental state information, and determining the visual target effectiveness evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence and the environmental state information;

[0064] It should be understood that for moving visual targets, due to the limitations of the visual sensor itself, the variability of the visual target and the complexity of the environment, it is easy to have the problem of false detection. In order to further determine the effectiveness of the moving visual target, it is necessary to combine the motion parameters of the moving target such as the visual target distance and the visual target speed, the vehicle motion parameters such as the vehicle speed, the system confidence parameters such as the visual confidence and the environmental status information collected by other sensors of the perception system such as radar sensors, infrared sensors and ultrasonic sensors to evaluate the effectiveness of the visual target and obtain the visual target effectiveness evaluation result.

[0065] In a feasible implementation, step S21 may include steps A11 to A13:

[0066] Step A11, determining a visual target distance linear change result, a visual target speed linear change result and a visual target speed integral result based on the visual target distance, the visual target speed and the vehicle speed;

[0067] It should be noted that the linear change result of the visual target distance refers to whether the target distance changes linearly relative to the vehicle speed; the linear change result of the visual target speed refers to whether the visual target speed changes linearly relative to the vehicle speed; the visual target speed integral result refers to whether the result obtained by integrating the visual target speed over a period of time can match the visual target distance.

[0068] Step A12, evaluating the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score;

[0069] It should be noted that the visual confidence is the credibility calculated by the visual sensor based on the visual attributes of the detected visual target. Specifically, the visual sensor can detect the consistency of the shape information and position information of the visual target in multiple consecutive frames to obtain the visual confidence of the visual target. The environmental state information includes the light intensity information of the scene where the visual target is located and the congestion level information of the scene where the visual target is located.

[0070] Exemplarily, five evaluation conditions can be set to calculate the visual target reality score, including: a. Whether the target distance changes linearly relative to the vehicle speed; b. Whether the visual target speed changes linearly relative to the vehicle speed; c. The visual target speed integral result refers to whether the result obtained by integrating the visual target speed over a period of time can match the visual target distance; d. Whether the visual confidence is continuously greater than a certain value; e. Whether the surrounding environment is a simple scene with sufficient light and no congestion. Among them, a corresponds to the result of the linear change of the visual target distance, b corresponds to the result of the linear change of the visual target speed, c corresponds to the result of the visual target speed integral, d corresponds to the visual confidence, and e corresponds to the environmental status information.

[0071] In a feasible implementation, step A12 may include: when the visual target distance is greater than a preset distance, and any one of the linear change result of the visual target distance, the linear change result of the visual target speed, and the integral result of the visual target speed meets a preset evaluation result, a first score, a second score, and a third score are generated based on the linear change result of the visual target distance, the linear change result of the visual target speed, and the integral result of the visual target speed; based on the first score, the second score, and the third score, the authenticity of the visual target is evaluated to obtain a visual target authenticity score.

[0072] It should be noted that the preset distance is a threshold value set according to the performance of the visual sensor, which is used to control the selection of evaluation conditions for the visual target authenticity score, and can be specifically set to 70m. For moving visual targets whose visual target distance is greater than the preset distance, due to the long distance, the single visual sensor is affected by various factors such as environment, weather, and light conditions, and the credibility is relatively low. When evaluating the visual target authenticity, it mainly relies on the linear change results of the visual target distance, the linear change results of the visual target speed, and the visual target speed integral results calculated using the data of other sensors in the perception system.

[0073] It should be understood that the first score, the second score and the third score correspond to the scores for the linear change result of the visual target distance, the linear change result of the visual target speed and the integral result of the visual target speed, respectively. Specifically, when calculating the visual target reality score, if any one of the following conditions is negative, it is considered to meet the preset evaluation result: a. Whether the target distance changes linearly relative to the vehicle speed; b. Whether the visual target speed changes linearly relative to the vehicle speed; c. The visual target speed integral result refers to whether the result obtained by integrating the visual target speed over a period of time can match the visual target distance. The calculation formula for the visual target reality score S is as follows:

[0074] S=k1*a+k2*b+k3*c

[0075] When the corresponding condition is yes, the corresponding k coefficient is set to 1, and when the corresponding condition is no, the corresponding k coefficient is set to 0. When any condition of the detected moving visual target is no, the visual target authenticity score will be continuously calculated. The values ​​of a, b, and c are preset by the system. As time goes by, the values ​​of a, b, and c become larger.

[0076] Exemplarily, when any condition is negative for 0.2s, a=3, b=3, c=4; when any condition is negative for 0.5s, a=4, b=4, c=6; when any condition is negative for 1s, a=6, b=6, c=6.

[0077] In another feasible implementation, step A12 may include: when the visual target distance is less than or equal to a preset distance, and any one of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence and the environmental status information meets a preset evaluation result, generating a first score, a second score, a third score, a fourth score and a fifth score based on the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence and the environmental status information; and evaluating the authenticity of the visual target based on the first score, the second score, the third score, the fourth score and the fifth score to obtain a visual target authenticity score.

[0078] It should be noted that for moving visual targets whose visual target distance is less than or equal to the preset distance, the recognition performance of the sensor of the perception system is better because the distance to the vehicle is closer. At this time, the authenticity of the visual target can be evaluated in combination with more evaluation conditions.

[0079] It should be understood that the first score, the second score, the third score, the fourth score and the fifth score correspond to the scores for the linear change results of the visual target distance, the linear change results of the visual target speed, the visual target speed integral results, the visual confidence and the environmental status information, respectively. Specifically, when calculating the visual target reality score, if any one of the following conditions is negative, it is considered to meet the preset evaluation result: a. Whether the target distance changes linearly relative to the vehicle speed; b. Whether the visual target speed changes linearly relative to the vehicle speed; c. The visual target speed integral result refers to whether the result obtained by integrating the visual target speed over a period of time can match the visual target distance; d. Whether the visual confidence is continuously greater than a certain value; e. Whether the surrounding environment is a simple scene with sufficient light and no congestion. Among them, a corresponds to the linear change result of the visual target distance, b corresponds to the linear change result of the visual target speed, c corresponds to the visual target speed integral result, d corresponds to the visual confidence, and e corresponds to the environmental status information. The calculation formula of the visual target reality score S is as follows:

[0080] S=k1*a+k2*b+k3*c+k4*d+k5*e

[0081] When the corresponding condition is yes, the corresponding k coefficient is set to 1, and when the corresponding condition is no, the corresponding k coefficient is set to 0. When any condition of the detected moving visual target is no, the visual target authenticity score will be continuously calculated. The values ​​of a, b, c, d, and e are preset by the system. As time goes by, the values ​​of a, b, c, d, and e become larger.

[0082] Exemplarily, when any condition is negative and reaches 0.2s, a=3, b=3, c=4, d=6, e=6; when any condition is negative and reaches 0.4s, a=4, b=4, c=6, d=6, e=6; when any condition is negative and reaches 0.6s, a=6, b=6, c=6, d=6, e=6.

[0083] Step A13, determining a visual target effectiveness evaluation result based on the visual target authenticity score.

[0084] It should be understood that the higher the visual target authenticity score, the greater the reliability that the visual target is a real obstacle. A score threshold can be set. When the visual target authenticity score reaches this score threshold, the visual target is determined to be valid, and the visual target whose visual target validity evaluation result is a valid visual target is given to the corresponding control module for further processing. Specifically, for the visual target authenticity score S calculated by the above method, when S is greater than 5, the visual target is determined to be valid.

[0085] Step S22, when the motion state of the visual target is a stationary state, determining that the visual target validity evaluation result is that the visual target is valid.

[0086] It should be understood that for a visual target in a stationary state, due to the stability of the visual target, the visual sensor has a higher recognition performance for such a visual target. When a stationary visual target is detected, the system will directly determine that the visual target is valid.

[0087] Step S30, when the visual target validity evaluation result is that the visual target is valid, determining the visual target delay processing time according to the visual target screening strategy to complete the visual target screening.

[0088] It should be noted that when the visual target validity assessment result is that the visual target is valid, it means that the detected visual target is a real obstacle. At this time, the cruise system determines the appropriate response strategy such as avoidance, deceleration or braking based on the attribute data of the visual target. The attribute data includes position information, speed information, acceleration information, size and shape information, and type information. Different delay processing times need to be determined for different scenarios. During the delay processing time, the system continuously collects data on the visual target for analysis to ensure the accuracy of the attribute data. The delay processing time can be shortened for more urgent scenarios, and the delay processing time can be extended for more stable scenarios.

[0089] It should be understood that for visual targets in a stationary state, due to the stability of the target, the visual target in a stationary state can be directly identified as valid, but in order to ensure the reliability of the attribute data of the collected visual target, a suitable visual target delay processing time can be determined based on the distance between the vehicle and the visual target and the speed of the vehicle. For visual targets in a moving state, due to the variability of the target, in order to ensure driving safety, the visual target delay processing time can be set to 0. When the visual target is identified as valid, the visual target detection result containing the attribute data is fed back to the corresponding control module, and the visual target is processed in time, so that the vehicle maintains a safe distance from the obstacle.

[0090] This embodiment provides a visual target screening method, which obtains the visual target motion state and the visual target distance when the visual target is detected, and determines the corresponding visual target screening strategy based on the visual target motion state and the visual target distance; determines the visual target validity evaluation result according to the visual target motion state; and when the visual target validity evaluation result is that the visual target is valid, determines the visual target delay processing time according to the visual target screening strategy to complete the visual target screening. The solution of the present application can determine the appropriate visual target screening strategy for the scene according to the visual motion characteristics and distance characteristics when the visual target is detected, and determine the visual target delay processing time according to the visual target screening strategy, so that the cruise system can further collect the visual target data for accurate analysis, which can reduce misjudgment and unnecessary intervention, and improve the response speed and accuracy to real obstacles, thereby improving the overall performance of autonomous driving and the user's vehicle comfort.

[0091] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S30 includes steps S31-S32:

[0092] Step S31, when the visual target validity evaluation result is that the visual target is valid and the motion state of the visual target is a stationary state, determining whether the visual target distance meets the delay processing condition according to the visual target screening strategy, and obtaining a delay determination result;

[0093] It should be noted that for determining effective stationary visual targets, a distance threshold will be set in the visual target screening strategy to determine whether the stationary visual target needs to be delayed. The distance threshold needs to be set according to the performance of the visual sensor. For stationary visual targets whose visual targets are less than or equal to the distance threshold, no other additional judgment measures are taken, and it is determined that it does not meet the delay processing conditions. After normal filtering, it can be directly sent to the control module for processing. For stationary visual targets whose visual target distance is greater than the distance threshold, in order to ensure the reliability of the attribute data of the collected visual targets, it is determined that it meets the delay processing conditions, so as to further determine the appropriate visual target delay processing time based on the distance between the vehicle and the visual target and the vehicle speed.

[0094] Step S32, when the delay determination result is that the visual target distance meets the delay processing condition, the collision time of the visual target is obtained, and the visual target delay processing time is determined based on the collision time to complete the visual target screening.

[0095] It should be noted that the TTC (Time To Collision) of the visual target can be calculated based on the relative speed between the visual target and the vehicle. When determining the visual target delay processing time based on the collision time, a visual target delay processing time mapping table can be set. For collision times in different time threshold intervals, there are different delay processing times. Exemplarily, for a stationary visual target with a TTC greater than 10s, the target can be released 1.5s later, that is, the visual target delay processing time is 1.5s; for a stationary visual target with a TTC of 6s to 10s, the target can be released 1s later, and the visual target delay processing time is 1s; for a stationary visual target with a TTC less than 6s, the target is released immediately, that is, the visual target delay processing time is 0s.

[0096] In a feasible implementation, after step S32, it may also include: obtaining a first target deceleration of the visual target; when the collision time is greater than or equal to a preset time and the first target deceleration meets a preset deceleration condition, sending a second target deceleration to the actuator, the second target deceleration is less than the first target deceleration; when the collision time is less than the preset time, sending the first target deceleration to the actuator.

[0097] It should be noted that when a valid stationary visual target is identified and reaches the visual target delay processing time, its attribute data will be given to the vehicle control module. At this time, the control module will calculate a target deceleration, namely the first target deceleration, through the control algorithm based on the attribute data of the visual target. The preset time is a safety time threshold set by the system, which is used to determine whether the vehicle needs to take deceleration measures. When the TTC is greater than or equal to the preset time, it will be determined whether the first target deceleration is within the preset deceleration range, that is, whether the preset deceleration condition is met. When the preset deceleration condition is met, in order to allow the user to obtain a comfortable braking experience, the second target deceleration that is less than the first target deceleration is sent to the actuator so that the vehicle decelerates according to the second target deceleration. When the TTC is less than the preset time, the distance between the visual target and the vehicle is too close. In order to avoid the risk of collision, the first target deceleration is sent to the actuator so that the vehicle decelerates according to the first target deceleration.

[0098] For example, the preset time can be 6s, the second target deceleration can be half of the first target deceleration, and the preset deceleration range is -0.5m / s2 to -1m / s2. When TTC is greater than or equal to 6s, and the first target deceleration is -0.5m / s2 to -1m / s2, 0.5 times the original target deceleration is sent to the actuator; when TTC is greater than or equal to 6s, and the target deceleration is 0 to -0.5m / s2, no deceleration request is sent; when TTC is less than 6s, the normally calculated target deceleration is immediately sent to the actuator.

[0099] This embodiment determines the appropriate delay processing time according to the collision time, which can reduce unnecessary emergency braking or avoidance actions caused by misjudgment of stationary targets while ensuring driving safety, thereby ensuring the driving safety and comfort of users.

[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the visual target screening method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0101] This application also provides a visual target screening device, please refer to Figure 4 , the visual target screening device comprises:

[0102] A screening strategy selection module 10 is used to obtain a visual target motion state and a visual target distance when a visual target is detected, and determine a corresponding visual target screening strategy based on the visual target motion state and the visual target distance;

[0103] A visual target determination module 20, configured to determine a visual target effectiveness evaluation result according to the visual target motion state;

[0104] The visual target processing module 30 is used to determine the visual target delay processing time according to the visual target screening strategy to complete the visual target screening when the visual target validity evaluation result is that the visual target is valid.

[0105] The visual target screening device provided by the present application adopts the visual target screening method in the above embodiment, which can solve the technical problem of how to improve the accuracy of visual target recognition by the cruise system. Compared with the prior art, the beneficial effects of the visual target screening device provided by the present application are the same as the beneficial effects of the visual target screening method provided by the above embodiment, and the other technical features in the visual target screening device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0106] In one embodiment, the visual target determination module 20 is further used to obtain the visual target speed, the vehicle speed, the visual confidence level and the environmental status information when the visual target motion state is in motion, and determine the visual target validity evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence level and the environmental status information; when the visual target motion state is in a stationary state, determine that the visual target validity evaluation result is that the visual target is valid.

[0107] In one embodiment, the visual target determination module 20 is further used to determine a visual target distance linear change result, a visual target speed linear change result and a visual target speed integral result based on the visual target distance, the visual target speed and the vehicle speed; evaluate the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence and the environmental status information to obtain a visual target authenticity score; and determine a visual target effectiveness evaluation result based on the visual target authenticity score.

[0108] In one embodiment, the visual target determination module 20 is further used to generate a first score, a second score and a third score based on the visual target distance linear change result, the visual target speed linear change result and the visual target speed integration result when the visual target distance is greater than a preset distance and any one of the visual target distance linear change result, the visual target speed linear change result and the visual target speed integration result satisfies a preset evaluation result; evaluate the authenticity of the visual target based on the first score, the second score and the third score to obtain a visual target authenticity score.

[0109] In one embodiment, the visual target determination module 20 is further used to generate a first score, a second score, a third score, a fourth score and a fifth score based on the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental status information when the visual target distance is less than or equal to a preset distance and any one of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental status information satisfies a preset evaluation result; and evaluate the authenticity of the visual target based on the first score, the second score, the third score, the fourth score and the fifth score to obtain a visual target authenticity score.

[0110] In one embodiment, the visual target processing module 30 is also used to determine whether the visual target distance meets the delay processing condition according to the visual target screening strategy when the visual target validity evaluation result is that the visual target is valid and the visual target motion state is a stationary state, and obtain a delay determination result; when the delay determination result is that the visual target distance meets the delay processing condition, obtain the collision time of the visual target, and determine the visual target delay processing time based on the collision time to complete the visual target screening.

[0111] In one embodiment, the visual target processing module 30 is also used to obtain a first target deceleration of the visual target; when the collision time is greater than or equal to a preset time and the first target deceleration meets a preset deceleration condition, a second target deceleration is sent to the actuator, and the second target deceleration is less than the first target deceleration; when the collision time is less than the preset time, the first target deceleration is sent to the actuator.

[0112] The present application provides a visual target screening device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the visual target screening method in the above-mentioned embodiment one.

[0113] Reference below Figure 5 , which shows a schematic diagram of the structure of a visual target screening device suitable for implementing the embodiment of the present application. The visual target screening device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The visual target screening device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0114] like Figure 5As shown, the visual target screening device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the visual target screening device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the visual target screening device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a visual target screening device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0115] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code 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 device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0116] The visual target screening device provided by the present application adopts the visual target screening method in the above embodiment, which can solve the technical problem of how to improve the accuracy of visual target recognition by the cruise system. Compared with the prior art, the beneficial effects of the visual target screening device provided by the present application are the same as the beneficial effects of the visual target screening method provided by the above embodiment, and the other technical features in the visual target screening device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0117] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0118] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0119] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the visual target screening method in the above-mentioned embodiment.

[0120] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, 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 or 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 this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0121] The computer-readable storage medium may be included in the visual target screening device; or may exist independently without being assembled into the visual target screening device.

[0122] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the visual target screening device, the visual target screening device: obtains the visual target motion state and the visual target distance when the visual target is detected, and determines the corresponding visual target screening strategy based on the visual target motion state and the visual target distance; determines the visual target validity evaluation result according to the visual target motion state; when the visual target validity evaluation result is that the visual target is valid, determines the visual target delay processing time according to the visual target screening strategy to complete the visual target screening.

[0123] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart 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.

[0125] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0126] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned visual target screening method, and can solve the technical problem of how to improve the accuracy of the cruise system in identifying visual targets. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the visual target screening method provided in the above-mentioned embodiment, and will not be repeated here.

[0127] The present application also provides a computer program product, including a computer program, which implements the steps of the visual target screening method as described above when executed by a processor.

[0128] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of visual target recognition by the cruise system. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the visual target screening method provided in the above embodiment, which will not be repeated here.

[0129] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A visual target screening method, characterized in that: The visual target screening method comprises: When a visual target is detected, obtaining a visual target motion state and a visual target distance, and determining a corresponding visual target screening strategy based on the visual target motion state and the visual target distance; Determining a visual target effectiveness evaluation result according to the visual target motion state; When the visual target validity evaluation result is that the visual target is valid, the visual target delay processing time is determined according to the visual target screening strategy to complete the visual target screening.

2. The method according to claim 1, characterized in that The visual target motion state includes a motion state and a static state; The step of determining the visual target effectiveness evaluation result according to the visual target motion state comprises: When the motion state of the visual target is a motion state, obtaining the visual target speed, the vehicle speed, the visual confidence and the environmental state information, and determining the visual target effectiveness evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence and the environmental state information; When the motion state of the visual target is a stationary state, it is determined that the visual target validity evaluation result is that the visual target is valid.

3. The method according to claim 2, characterized in that The step of determining the visual target effectiveness evaluation result based on at least three of the visual target distance, the visual target speed, the vehicle speed, the visual confidence and the environmental state information comprises: Determine a visual target distance linear change result, a visual target speed linear change result and a visual target speed integral result based on the visual target distance, the visual target speed and the vehicle speed; Evaluate the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score; A visual target effectiveness evaluation result is determined based on the visual target reality score.

4. The method according to claim 3, characterized in that The step of evaluating the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score comprises: When the visual target distance is greater than a preset distance, and any one of the visual target distance linear change result, the visual target speed linear change result, and the visual target speed integral result satisfies a preset evaluation result, a first score, a second score, and a third score are generated based on the visual target distance linear change result, the visual target speed linear change result, and the visual target speed integral result; The authenticity of the visual target is evaluated based on the first score, the second score, and the third score to obtain a visual target authenticity score.

5. The method according to claim 3, characterized in that The step of evaluating the authenticity of the visual target based on at least three of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integration result, the visual confidence and the environmental state information to obtain a visual target authenticity score comprises: When the visual target distance is less than or equal to the preset distance, and any one of the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence, and the environmental state information satisfies the preset evaluation result, a first score, a second score, a third score, a fourth score, and a fifth score are correspondingly generated based on the visual target distance linear change result, the visual target speed linear change result, the visual target speed integral result, the visual confidence, and the environmental state information; The authenticity of the visual target is evaluated based on the first score, the second score, the third score, the fourth score, and the fifth score to obtain a visual target authenticity score.

6. The method according to claim 1, characterized in that The step of determining the visual target delay processing time according to the visual target screening strategy to complete the visual target screening when the visual target validity evaluation result is that the visual target is valid includes: When the visual target validity evaluation result is that the visual target is valid and the motion state of the visual target is a stationary state, determining whether the visual target distance meets the delay processing condition according to the visual target screening strategy to obtain a delay determination result; When the delay determination result is that the visual target distance meets the delay processing condition, the collision time of the visual target is obtained, and the visual target delay processing time is determined based on the collision time to complete the visual target screening.

7. The method according to claim 6, characterized in that When the delay determination result is that the visual target distance meets the delay processing condition, the collision time of the visual target is obtained, and the visual target delay processing time is determined based on the collision time to complete the step of visual target screening, the method further includes: Acquire a first target deceleration of the visual target; When the collision time is greater than or equal to a preset time and the first target deceleration satisfies a preset deceleration condition, sending a second target deceleration to the actuator, wherein the second target deceleration is less than the first target deceleration; When the collision time is less than the preset time, the first target deceleration is sent to the actuator.

8. A visual target screening device, characterized in that: The device comprises: A screening strategy selection module, used to obtain a visual target motion state and a visual target distance when a visual target is detected, and determine a corresponding visual target screening strategy based on the visual target motion state and the visual target distance; A visual target determination module, used to determine a visual target effectiveness evaluation result according to the visual target motion state; The visual target processing module is used to determine the visual target delay processing time according to the visual target screening strategy to complete the visual target screening when the visual target validity evaluation result is that the visual target is valid.

9. A visual target screening device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the visual target screening method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the visual target screening method according to any one of claims 1 to 7 are implemented.

Images