A method, apparatus, equipment, and storage medium for identifying hazardous targets.

Abstract

This invention discloses a method, apparatus, device, and storage medium for determining hazardous targets. The method includes: determining at least two lateral boundaries of a target area within the lane where the vehicle is located; wherein the lateral boundaries of the target area are determined according to lane line equations; if the steering wheel angle of the vehicle exceeds a preset angle threshold, then determining a target area based on the lateral boundaries of the target area and a preset length range of the vehicle's travel direction; and determining hazardous targets among potential targets within the vehicle's detection range based on the target area. This technical solution solves the problem of low accuracy in screening hazardous targets within fixed target areas. By improving the planning method of target areas, it can improve the accuracy of hazardous target screening while enhancing driving safety and user satisfaction.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to a method, apparatus, device, and storage medium for identifying dangerous targets. Background Technology

[0002] With the continuous development of autonomous driving technology, driver assistance functions such as automatic emergency braking, forward collision warning, lane keeping assist, and blind spot detection not only improve vehicle driving safety but also bring users a good driving experience.

[0003] Currently, driver assistance systems are quite mature in recognizing obstacles ahead and controlling the vehicle when driving in a straight line. Automatic emergency braking systems typically plan a target area of ​​fixed length and width in front of the vehicle and filter obstacles within that target area.

[0004] However, the planning of target areas in existing technologies is relatively simplistic. When vehicles enter or exit curves or other scenarios, the accuracy of filtering for obstacles and other dangerous targets is not high, which can easily lead to false triggering and oversensitivity of the driver assistance system, thereby reducing driving safety and resulting in a poor driving experience for the user. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for determining hazardous targets, in order to solve the problem of low accuracy in screening hazardous targets within a fixed-shape target area. By improving the planning method of the target area, it is possible to improve the accuracy of hazardous target screening while enhancing driving safety and user satisfaction.

[0006] According to one aspect of the present invention, a method for determining a dangerous target is provided, the method comprising:

[0007] Determine at least two lateral boundaries of the target area in the lane where the vehicle is located; wherein the lateral boundaries of the target area are determined according to the lane line equation;

[0008] If the steering wheel angle of this vehicle exceeds the preset angle threshold, the target area is determined based on the preset length range of the target area's lateral boundary and the vehicle's driving direction.

[0009] Based on the target area, identify hazardous targets among potential targets within the vehicle's detection range.

[0010] According to another aspect of the present invention, a device for identifying dangerous targets is provided, the device comprising:

[0011] The lane line boundary determination module is used to determine at least two lateral boundaries of the target area in the lane where the vehicle is located; wherein, the lateral boundaries of the target area are determined according to the lane line equation;

[0012] The target area determination module is used to determine the target area based on the lateral boundary of the target area and a preset length range of the vehicle's driving direction if the steering wheel angle of the vehicle exceeds a preset angle threshold.

[0013] The hazardous target determination module is used to determine hazardous targets among potential targets within the detection range of the vehicle, based on the target area.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for determining dangerous targets as described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining a dangerous target as described in any embodiment of the present invention.

[0019] The technical solution of this invention plans a target area based on the lateral boundary of the target area and a preset length range in the vehicle's driving direction when the steering wheel angle of the vehicle exceeds a preset angle threshold. Then, based on the target area, dangerous targets are identified from potential targets within the vehicle's detection range. This technical solution solves the problem of low accuracy in screening dangerous targets within fixed-shape target areas. By improving the target area planning method, it can improve the accuracy of dangerous target screening while enhancing driving safety and user satisfaction.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1AThis is a flowchart of a method for determining a hazardous target according to Embodiment 1 of the present invention;

[0023] Figure 1B This is a schematic diagram of the target area in a turning scenario provided by an embodiment of the present invention;

[0024] Figure 2A This is a flowchart of a method for determining a hazardous target according to Embodiment 2 of the present invention;

[0025] Figure 2B This is a schematic diagram of the potential target distribution provided by an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of a device for determining dangerous targets according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the method for determining dangerous targets according to embodiments of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0030] Example 1

[0031] Figure 1AThis is a flowchart illustrating a method for determining a hazardous target according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving the determination of hazardous targets, particularly in scenarios where a vehicle is driving on complex road sections such as curves. This method can be executed by a hazardous target determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1A As shown, the method includes:

[0032] S110. Determine at least two lateral boundaries of the target area in the lane where the vehicle is located.

[0033] This solution can be executed by a driver assistance system, which may include subsystems such as lane keeping assist, automatic parking assist, brake assist, and driving assist. The lane keeping assist subsystem can use visual sensors such as cameras to identify lane markings and then generate lane line information based on the identification results. This lane line information may include a lane line equation; for example, the lane keeping assist subsystem can fit a lane line equation to the lane lines detected by the visual sensors. The lane line information may also include lane line confidence scores to evaluate the reliability of the lane line recognition by the visual sensors. In addition, the driver assistance system can also obtain the lane line equation of the vehicle's lane through navigation software. This lane line equation can be a representation of the lane lines observed from the vehicle's perspective. Specifically, the lane line equation can be a multi-order curve equation; for example, a third-order lane line equation can be expressed as: y = a0 + a1x + a2x 2 +a3x 3 Where a0, a1, a2, and a3 are the lane line equation coefficients. It should be noted that the lane line equation can also be a higher-order curve equation. The higher the order of the lane line equation, the better the fitting accuracy; correspondingly, the more complex the solution to the lane line equation coefficients. The coefficients of the lane line equation can be updated at a certain frequency as the vehicle moves, for example, once per second.

[0034] Understandably, this vehicle can travel on a single-lane road or a multi-lane road. Therefore, the driver assistance system can obtain at least two lane line equations, each of which can describe a lane line. The lateral boundary of the target area can be determined based on the constant term of the lane line equation. This target area can be a hazardous target monitoring area set by the driver assistance system to ensure vehicle driving safety.

[0035] In this solution, optionally, determining at least two lateral boundaries of the target area in the lane where the vehicle is located includes:

[0036] The confidence level of the lane line in the lane where the vehicle is located is obtained through the driver assistance system;

[0037] If the lane line confidence exceeds a preset confidence threshold, the lane line equation of the lane where the vehicle is located is obtained through the driving assistance system, and the lateral boundary of the target area is determined based on the obtained lane line equation.

[0038] If the confidence level of the lane line is lower than the preset confidence threshold, then a lane line equation is constructed based on the pre-acquired vehicle parameter information, and the lateral boundary of the target area is determined based on the constructed lane line equation.

[0039] It's easy to understand that lane markings on roads can be unclear or damaged. Driver assistance systems can determine whether lane markings can be recognized by using the lane marking confidence level returned by the visual sensor. For example, the lane marking confidence level can be 0 or 1, where 0 indicates no lane marking is recognized and 1 indicates it is. The lane marking confidence level returned by the visual sensor can also be an evaluation of the lane marking recognition effect, such as the lane marking recognition accuracy. If the visual sensor has high lane marking recognition accuracy, for example, above 70%, it indicates that the lane marking information generated by the lane keeping assist subsystem is reliable. The driver assistance system can directly obtain the lane marking equation for the lane where the vehicle is located from the lane keeping assist subsystem and determine the lateral boundary of the target area based on the constant term in the lane marking equation. If, due to blurred lane markings, damaged visual sensors, or other reasons, the visual sensor cannot recognize the lane markings or has low recognition accuracy, for example, below 70%, the driver assistance system can construct the lane marking equation based on the vehicle's parameter information.

[0040] The vehicle parameter information may include the vehicle's width, length, and operating status. For example, a driver assistance system can set a tolerance width as the lane width based on the vehicle's width, and then determine the constant term of the lane line equation based on the lane width. Alternatively, the driver assistance system can determine the coefficients of the x-term in the lane line equation based on the relationship between the vehicle's operating status and the coefficients of the lane line equation, and then determine the coefficients of the x-term in the lane line equation based on the vehicle's operating status information. After obtaining the constructed lane line equation, the lateral boundary of the target area is determined based on the lane line equation.

[0041] This scheme can determine the coefficients of the lane line equation by using the lane line confidence level, and then locate the lateral boundary of the target area based on the lane line equation, which is beneficial to achieving the reliability and accuracy of the lateral boundary location of the target area.

[0042] Based on the above scheme, the vehicle parameter information includes steering wheel angle, steering ratio, and wheelbase; the lane line equation includes linear coefficients and quadratic coefficients.

[0043] The process of constructing lane line equations based on pre-acquired vehicle parameter information includes:

[0044] Based on the steering wheel angle and steering ratio, determine the front wheel angle of the vehicle, and determine the coefficient of the first term based on the front wheel angle;

[0045] The steering radius is determined based on the front wheel angle and the wheelbase, and the quadratic coefficient is determined based on the steering radius.

[0046] The lane line equation is constructed based on the coefficients of the first and second terms.

[0047] In this scheme, the lane line equation can be a second-order parabola equation, expressed as y = a0 + a1x + a2x 2 Taking a lane containing two lane lines as an example, the lane line equations corresponding to the two lane lines can be expressed as:

[0048]

[0049] Where 0≤x≤ROI_longth, δ represents the front wheel steering angle, R represents the steering radius, and y lift Indicates the boundary of the left lane line, y right This represents the right lane boundary. ROI_width represents the width of the region of interest (ROI), and ROI_longth represents the length of the ROI. It's important to note that the width of the ROI can be set based on the vehicle's width; for example, if the vehicle width is typically 3 meters, the ROI width could be set to 4 meters. The length of the ROI is usually set to a relatively long distance, such as 70-150 meters, to allow the driver assistance system to detect dangerous targets promptly. The length and width of the ROI can also be set based on the vehicle's motion and driving environment. For example, if the vehicle is slowly traveling in a busy street, the ROI width could be set to 6 meters to provide timely detection of obstacles in complex scenarios. Since the vehicle is moving slowly, the ROI length could be set to 70 meters to meet safety requirements. It should be noted that the ROI can be the area for detecting dangerous targets while the vehicle is traveling straight on a road.

[0050] As is easily understood, the front wheel steering angle can be obtained directly from the driver assistance system, or it can be calculated by obtaining the steering wheel angle from the driver assistance system and then calculating the angle based on the steering wheel angle and the vehicle's steering ratio. Specifically, the formula for calculating the front wheel steering angle δ can be:

[0051]

[0052] Among them, Angle steer This indicates the steering wheel angle, and K indicates the steering ratio. It should be noted that, to ensure consistency of parameters, the front wheel angle can be converted from degrees to radians for easier calculation.

[0053] Similarly, the turning radius can be obtained directly from the driver assistance system, or it can be calculated. Specifically, the formula for calculating the turning radius R can be:

[0054]

[0055] Where L represents the wheelbase.

[0056] It should be noted that the above lane line equation can be applied to any driving scenario. For example, when a vehicle is traveling straight, the steering wheel angle can be 0 or have slight variations within a reasonable range. In this case, tanδ equals or approaches 0. It does not exist or tends to 0. The lane line equation can be expressed as:

[0057]

[0058] In this solution, the driver assistance system can automatically construct lane line equations based on vehicle parameter information when lane line equations cannot be directly obtained. The lane line equations constructed by this solution are more closely aligned with the actual driving conditions of the vehicle, which helps to determine a reasonable target area and effectively avoids misidentification and oversensitivity while ensuring the vehicle's safety.

[0059] S120. If the steering wheel angle of the vehicle exceeds a preset angle threshold, the target area is determined based on the preset length range of the target area's lateral boundary and the vehicle's driving direction.

[0060] Figure 1B This is a schematic diagram of the target area in a turning scenario provided by an embodiment of the present invention, such as... Figure 1B As shown, in the prior art, the target area can be set as target area A, which is a visual area with a fixed length and width. In a straight-moving scene, target area A can effectively delineate dangerous targets. However, in scenarios such as... Figure 1B In the turning scenario shown, part of the target area A already involves the oncoming lane. Designating vehicles traveling normally in the oncoming lane as dangerous targets can easily lead to misidentification and oversensitivity, while also ignoring dangerous targets existing in the lane where the vehicle is located.

[0061] In this solution, when the driver assistance system detects that the steering wheel angle exceeds a certain threshold, it indicates that the vehicle is in a turning scenario. The driver assistance system can define the target area based on the lateral boundary of the target area and a pre-defined length range in the vehicle's direction of travel, such as... Figure 1BTarget area B in the text. The driver assistance system can directly acquire the lateral boundary of the target area within a preset length range, and use the closed area enclosed by the lateral boundary of the target area and the boundary of the length range as the target area. In some scenarios, if the lane width is too large relative to the vehicle, the driver assistance system can also translate the lateral boundary of the target area into the lane, thereby defining a reasonable target area for the vehicle, such as... Figure 1B The target region B is shown in the figure.

[0062] It should be noted that in multi-lane scenarios, the visual sensor may detect more than two lane lines. The driver assistance system can identify the two lane lines closest to the vehicle as target lane lines, generate target lane line equations based on these target lane lines, and then use these two target lane line equations to determine the target lane line boundaries and delineate the target area. Alternatively, the driver assistance system can generate pseudo lane line equations based on the vehicle's parameter information, compare these pseudo lane line equations with multiple lane line equations determined from the detected lane lines, and determine two target lane line equations.

[0063] S130. Based on the target area, identify dangerous targets among potential targets within the detection range of this vehicle.

[0064] Vehicles are typically equipped with obstacle detection devices such as radar and infrared sensors to detect potential targets within a certain range of the vehicle. These potential targets can include vehicles, pedestrians, railings, and buildings, and can be stationary or moving. After defining the target area, the driver assistance system can identify potential targets within the target area detected by the obstacle detection device as hazardous targets, and control the vehicle to take timely braking measures to avoid collisions, scrapes, or other damage.

[0065] This technical solution plans a target area based on lane line boundaries and a preset length range in the vehicle's direction of travel when the steering wheel angle exceeds a preset threshold. Then, based on this target area, it identifies hazardous targets among potential targets within the vehicle's detection range. This solution solves the problem of low accuracy in screening hazardous targets within fixed target areas. By improving the target area planning method, it can enhance driving safety and user satisfaction while increasing the accuracy of hazardous target screening.

[0066] Example 2

[0067] Figure 2A This is a flowchart of a method for determining a hazardous target according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2A As shown, the method includes:

[0068] S210. Determine at least two lateral boundaries of the target area in the lane where the vehicle is located.

[0069] The method for identifying hazardous targets in this solution can be applied to various vehicle driving scenarios, such as turning scenarios and straight-line driving scenarios.

[0070] S220. If the steering wheel angle of the vehicle exceeds a preset angle threshold, the target area is determined based on the preset length range of the target area's lateral boundary and the vehicle's driving direction.

[0071] S230. Based on the relative distance information between the potential target and the vehicle, determine whether the potential target is within the target area.

[0072] The relative distance information includes lateral and longitudinal relative distances. The driver assistance system can collect the relative distance information between the potential target and the vehicle using radar. Based on the lateral and longitudinal relative distances, the driver assistance system can determine the position of the potential target and then determine whether it is within the target area. Determining whether a potential target is within the target area by locating its position is generally applicable to any driving scenario.

[0073] Figure 2B This is a schematic diagram of the distribution of potential targets according to an embodiment of the present invention. In a straight-moving scenario, the following conditions can be used to more easily and quickly determine whether a potential target is located within the target area:

[0074]

[0075] When this vehicle is traveling on a straight section of road, the target area can be as follows: Figure 2B As shown, when the lateral and longitudinal relative distances between a potential target and the vehicle meet the above conditions, it indicates that the potential target is within the target area. If the potential target is within the target area, S240 is executed to identify the potential target as a hazardous target. If the potential target is not within the target area, S250 is executed to further assess the risk status of the potential target.

[0076] S240. The potential target is identified as a dangerous target.

[0077] S250. Based on the lateral relative distance and the lateral relative speed between the potential target and the vehicle, determine whether the potential target poses an intrusion risk.

[0078] Understandably, driver assistance systems can collect relative speed information between potential targets and the vehicle using speed sensors, and can also calculate relative speed information based on the relative distance and time information between the potential target and the vehicle. Based on the lateral relative distance, the driver assistance system can determine the distance of the potential target from the vehicle. Based on the lateral relative speed between the potential target and the vehicle, the driver assistance system can determine the movement trend of the potential target. When a potential target is laterally approaching the vehicle and shows a tendency to move towards the vehicle, it indicates that the potential target is encroaching on the vehicle's lane. For the vehicle, this potential target poses an intrusion risk. Taking a straight-ahead road section as an example, if... Figure 2B If potential target 1 is not within the target area of ​​this vehicle, but is cutting into the lane where this vehicle is located in the direction indicated by the arrow, then it can be determined that potential target 1 poses an intrusion risk.

[0079] In one feasible solution, determining whether a potential target poses an intrusion risk based on the lateral relative distance and the lateral relative speed between the potential target and the vehicle includes:

[0080] If the absolute value of the lateral relative velocity is greater than a preset velocity threshold, and the product of the lateral relative distance and the lateral relative velocity is less than 0, then the potential target is determined to have an intrusion risk.

[0081] Specifically, the criteria for judging intrusion risk can be expressed as follows:

[0082]

[0083] The driver assistance system can set a speed threshold. If the absolute value of the lateral relative speed is higher than the threshold, it indicates that the lateral relative speed between the potential target and the vehicle is relatively high, posing a higher risk. If the product of the lateral relative distance and the lateral relative speed is less than 0, it means that the signs of the lateral relative distance and the lateral relative speed are opposite, indicating that the potential target is approaching the vehicle. Figure 2B Potential targets 1 and 2 are shown in the image. The product of the lateral relative distance and the lateral relative velocity is greater than 0, indicating that the lateral relative distance and the lateral relative velocity have the same sign, and the potential targets are moving away from the vehicle. Figure 2B Potential targets 3 and 4 are identified. When both of the above conditions are met simultaneously, it indicates that the potential targets pose a risk of intrusion.

[0084] This solution can accurately determine whether a potential target poses an intrusion risk by using the lateral relative distance and the lateral relative speed between the potential target and the vehicle, which is beneficial for targeted screening of potential targets outside the target area.

[0085] S260. If there is an intrusion risk, then based on the relative speed information between the potential target and the vehicle, the relative distance information, and the width of the vehicle, determine whether there is a collision risk between the potential target and the vehicle.

[0086] In this solution, the relative speed information includes lateral relative speed and longitudinal relative speed. If a potential target poses an intrusion risk, the driver assistance system can further predict whether a collision risk exists between the potential target and the vehicle based on the relative speed information, relative distance information, and the width of the vehicle. Specifically, the driver assistance system can calculate the actual distance between the potential target and the vehicle based on the relative distance information, determine whether there is a meeting point between the potential target and the vehicle according to their respective travel directions, and if so, use the actual distance and relative speed information to predict the passage time of the potential target and the vehicle to the meeting point, and then determine whether the potential target and the vehicle are likely to meet based on the comparison of the passage times.

[0087] In one feasible solution, determining whether there is a collision risk between the potential target and the vehicle based on the relative speed information between the potential target and the vehicle, the relative distance information, and the width of the vehicle includes:

[0088] The collision time is calculated based on the longitudinal relative distance and the longitudinal relative speed; and the exit time of the potential target is calculated based on the lateral relative distance, the width of the vehicle, and the lateral relative speed.

[0089] If the collision time is less than or equal to the departure time, it is determined whether there is a collision risk between the potential target and the vehicle.

[0090] The formula for calculating collision time can be expressed as:

[0091] T1 = |Longitudinal relative distance| ÷ |Longitudinal relative velocity|;

[0092] The formula for calculating departure time can be expressed as:

[0093]

[0094] If the collision time is greater than the departure time, it is predicted that the potential target will not collide with the vehicle under the current relative distance and relative speed. If the collision time is less than or equal to the departure time, it indicates that a collision between the potential target and the vehicle is possible under the current relative distance and relative speed. In this case, the vehicle should be controlled in time to reduce speed or brake to avoid the risk of collision.

[0095] S270. If there is a risk of collision, the potential target shall be identified as a dangerous target.

[0096] For potential targets not within the target area, this solution can accurately screen dangerous targets through two levels of judgment: intrusion risk and collision risk, effectively avoiding false triggering and oversensitivity of the driver assistance system.

[0097] This technical solution plans a target area based on lane line boundaries and a preset length range in the vehicle's direction of travel when the steering wheel angle exceeds a preset threshold. Then, based on this target area, it identifies hazardous targets among potential targets within the vehicle's detection range. This solution solves the problem of low accuracy in screening hazardous targets within fixed target areas. By improving the target area planning method, it can enhance driving safety and user satisfaction while increasing the accuracy of hazardous target screening.

[0098] Example 3

[0099] Figure 3 This is a schematic diagram of a device for determining dangerous targets provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0100] The lateral boundary determination module 310 is used to determine at least two lateral boundaries of the target area in the lane where the vehicle is located; wherein, the lateral boundaries of the target area are determined according to the lane line equation;

[0101] The target area determination module 320 is used to determine the target area based on the lateral boundary of the target area and a preset length range of the vehicle's driving direction if the steering wheel angle of the vehicle exceeds a preset angle threshold.

[0102] The hazardous target determination module 330 is used to determine hazardous targets among potential targets within the detection range of the vehicle based on the target area.

[0103] In this solution, optionally, the lane line boundary determination module 310 includes:

[0104] The confidence level acquisition unit is used to acquire the lane line confidence level of the lane where the vehicle is located through the driving assistance system;

[0105] The lane line equation acquisition unit is used to acquire the lane line equation of the lane where the vehicle is located through the driving assistance system if the lane line confidence exceeds a preset confidence threshold, and determine the lateral boundary of the target area based on the acquired lane line equation.

[0106] The lane line equation construction unit is used to construct a lane line equation based on the pre-acquired vehicle parameter information if the lane line confidence is lower than a preset confidence threshold, and to determine the lateral boundary of the target area based on the constructed lane line equation.

[0107] Based on the above scheme, optionally, the vehicle parameter information includes steering wheel angle, steering ratio, and wheelbase; the lane line equation includes linear coefficients and quadratic coefficients;

[0108] The lane line equation construction unit includes:

[0109] The first-order term coefficient determination subunit is used to determine the front wheel angle of the vehicle based on the steering wheel angle and the steering ratio of the steering gear, and to determine the first-order term coefficient based on the front wheel angle.

[0110] The quadratic term coefficient determination subunit is used to determine the steering radius based on the front wheel steering angle and the wheelbase, and to determine the quadratic term coefficient based on the steering radius;

[0111] The lane line equation construction sub-unit is used to construct the lane line equation based on the first-order and second-order coefficients.

[0112] In one feasible embodiment, the hazardous target determination module 330 includes:

[0113] A potential target determination unit is used to determine whether a potential target is within the target area based on the relative distance information between the potential target and the vehicle; wherein the relative distance information includes lateral relative distance and longitudinal relative distance;

[0114] The first dangerous target determination unit is used to determine the potential target as a dangerous target if the potential target is located within the target area.

[0115] Based on the above solution, optionally, the hazardous target determination module 330 further includes:

[0116] An intrusion risk determination unit is used to determine whether there is an intrusion risk to the potential target if the potential target is not in the target area, based on the lateral relative distance and the lateral relative speed between the potential target and the vehicle.

[0117] The collision risk determination unit is used to determine whether there is a collision risk between the potential target and the vehicle based on the relative speed information between the potential target and the vehicle, the relative distance information, and the width of the vehicle if there is an intrusion risk.

[0118] The second hazardous target determination unit is used to determine the potential target as a hazardous target if there is a collision risk.

[0119] In this embodiment, optionally, the intrusion risk determination unit is specifically used for:

[0120] If the absolute value of the lateral relative velocity is greater than a preset velocity threshold, and the product of the lateral relative distance and the lateral relative velocity is less than 0, then the potential target is determined to have an intrusion risk.

[0121] Based on the above scheme, optionally, the relative velocity information includes lateral relative velocity and longitudinal relative velocity;

[0122] The collision risk determination unit includes:

[0123] The time calculation subunit is used to calculate the collision time based on the longitudinal relative distance and the longitudinal relative speed; and to calculate the exit time of the potential target based on the lateral relative distance, the width of the vehicle, and the lateral relative speed.

[0124] The collision risk determination subunit is used to determine whether there is a collision risk between the potential target and the vehicle if the collision time is less than or equal to the departure time.

[0125] The hazardous target determination device provided in the embodiments of the present invention can execute the hazardous target determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0126] Example 4

[0127] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0128] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0129] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0130] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as methods for identifying hazardous targets.

[0131] In some embodiments, the method for determining hazardous targets may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the method for determining hazardous targets described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the method for determining hazardous targets by any other suitable means (e.g., by means of firmware).

[0132] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0134] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0136] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0137] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0138] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0139] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of determining a dangerous object, characterized by, The method comprises: acquiring lane line confidence of a lane where the ego vehicle is located through a driving assistance system; if the lane line confidence exceeds a preset confidence threshold, acquiring lane line equation of the lane where the ego vehicle is located through the driving assistance system, and determining target region lateral boundary based on the acquired lane line equation; if the lane line confidence is lower than the preset confidence threshold, constructing lane line equation according to pre-acquired ego vehicle parameter information, and determining the target region lateral boundary based on the constructed lane line equation; if steering wheel angle of the ego vehicle exceeds a preset angle threshold, determining the target region according to the target region lateral boundary and a preset length range of a driving direction of the ego vehicle; determining a dangerous target from potential targets within a detection range of the ego vehicle according to the target region.

2. The method of claim 1, wherein, The ego vehicle parameter information comprises steering wheel angle, steering gear steering ratio and wheelbase; the lane line equation comprises a linear term coefficient and a quadratic term coefficient; The constructing lane line equation according to the pre-acquired ego vehicle parameter information comprises: determining front wheel angle of the vehicle according to the steering wheel angle and the steering gear steering ratio, and determining the linear term coefficient according to the front wheel angle; determining steering radius according to the front wheel angle and the wheelbase, and determining the quadratic term coefficient according to the steering radius; constructing the lane line equation according to the linear term coefficient and the quadratic term coefficient.

3. The method of claim 1, wherein, The determining a dangerous target from potential targets within a detection range of the ego vehicle according to the target region comprises: determining whether the potential target is within the target region according to relative distance information between the potential target and the ego vehicle; wherein the relative distance information comprises lateral relative distance and longitudinal relative distance; if the potential target is within the target region, determining the potential target as a dangerous target.

4. The method of claim 3, wherein, After determining whether the potential target is within the target region, the method further comprises: if the potential target is not within the target region, determining whether the potential target has invasion risk according to the lateral relative distance and lateral relative speed between the potential target and the ego vehicle; if there is invasion risk, determining whether the potential target and the ego vehicle have collision risk according to relative speed information between the potential target and the ego vehicle, the relative distance information and ego vehicle width; if there is collision risk, determining the potential target as a dangerous target.

5. The method of claim 4, wherein, The determining whether the potential target has invasion risk according to the lateral relative distance and lateral relative speed between the potential target and the ego vehicle comprises: if absolute value of the lateral relative speed is greater than a preset speed threshold, and product of the lateral relative distance and the lateral relative speed is less than 0, determining that the potential target has invasion risk.

6. The method of claim 4, wherein, The relative speed information comprises lateral relative speed and longitudinal relative speed; The determining whether the potential target and the ego vehicle have collision risk according to relative speed information between the potential target and the ego vehicle, the relative distance information and ego vehicle width comprises: calculating collision time according to the longitudinal relative distance and the longitudinal relative speed; and calculating driving-out time of the potential target according to the lateral relative distance, the ego vehicle width and the lateral relative speed; If the collision time is less than or equal to the driving-out time, it is determined whether the potential target and the vehicle have a collision risk.

7. A dangerous object determining apparatus characterized by comprising: The method comprises the steps of: a lane line boundary determination module configured to acquire, by a driving assistance system, lane line confidence of a lane in which the vehicle is located; if the lane line confidence exceeds a preset confidence threshold, acquiring, by the driving assistance system, a lane line equation of the lane in which the vehicle is located, and determining a target region lateral boundary based on the acquired lane line equation; if the lane line confidence is lower than the preset confidence threshold, constructing a lane line equation according to pre-acquired vehicle parameter information, and determining a target region lateral boundary based on the constructed lane line equation; a target region determination module configured to determine a target region according to the target region lateral boundary and a preset length range of a driving direction of the vehicle if a steering wheel angle of the vehicle exceeds a preset angle threshold; a dangerous target determination module configured to determine a dangerous target from potential targets within a detection range of the vehicle according to the target region.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method for determining a dangerous target according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the method for determining a dangerous target according to any one of claims 1-6 when executed by the processor.

Images