Collision warning method and device, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure disclose a collision warning method and device, electronic equipment and storage medium, wherein the method comprises: obtaining surrounding environment visual information of a current vehicle and current state information of the current vehicle; determining a target drivable safety region boundary based on the surrounding environment visual information; determining a target warning region based on the current state information; determining a lateral collision risk state based on the target drivable safety region boundary and the target warning region, the lateral collision risk state including two states of risk and no risk; and performing lateral collision warning in response to the lateral collision risk state being at risk. Embodiments of the present disclosure can timely perform lateral collision warning, remind the user on the vehicle to take timely obstacle avoidance measures, achieve effective warning of lateral collision, avoid or slow down the occurrence of traffic accidents caused by lateral visual dead angle, improve the timeliness and effectiveness of lateral collision warning, and effectively improve the driving safety of the vehicle.

Description

Technical Field

[0001] This disclosure relates to computer vision technology, and in particular to a collision warning method, apparatus, electronic device, and storage medium. Background Technology

[0002] Vehicle collision warning systems are vehicle assistance systems that alert drivers through sound, vision, and touch to avoid or mitigate traffic accidents. Among related technologies, L2-level advanced driver assistance systems (ADAS) include forward collision warning (FCW) and rear collision warning (RCW) functions. However, due to the obstruction of the vehicle's structure, drivers have certain blind spots regarding lateral movements, which can easily lead to side collisions (or lateral impacts), resulting in poor vehicle safety. Summary of the Invention

[0003] To address the aforementioned technical problems such as poor vehicle safety due to side collisions, this disclosure is proposed. Embodiments of this disclosure provide a collision warning method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of the present disclosure, a collision warning method is provided, comprising: acquiring visual information of the surrounding environment of a current vehicle and current state information of the current vehicle; determining a target drivable safe zone boundary based on the visual information of the surrounding environment; determining a target warning zone based on the current state information; determining a lateral collision risk state based on the target drivable safe zone boundary and the target warning zone, the lateral collision risk state including two states: risky and no risk; and issuing a lateral collision warning in response to the lateral collision risk state being risky.

[0005] According to another aspect of the present disclosure, a collision warning device is provided, comprising: a first acquisition module, configured to acquire visual information of the surrounding environment of a current vehicle and current state information of the current vehicle; a first processing module, configured to determine a target drivable safe zone boundary based on the visual information of the surrounding environment; a second processing module, configured to determine a target warning zone based on the current state information; a third processing module, configured to determine a lateral collision risk state based on the target drivable safe zone boundary and the target warning zone, the lateral collision risk state including two states: risky and no risk; and a fourth processing module, configured to issue a lateral collision warning in response to the lateral collision risk state being risky.

[0006] According to another aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the collision warning method described in any of the above embodiments of the present disclosure.

[0007] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the collision warning method described in any of the above embodiments of the present disclosure.

[0008] Based on the collision warning method, device, electronic device, and storage medium provided in the above embodiments of this disclosure, the target warning area is determined based on the current state information of the vehicle, the boundary of the target drivable safe area is determined based on the visual information of the surrounding environment of the vehicle, and then the lateral collision risk status is determined based on the boundary of the target drivable safe area and the target warning area. When the lateral collision risk status is determined to be risky, a collision warning can be issued in a timely manner to remind the user in the vehicle to take obstacle avoidance measures in time, thereby achieving effective warning of lateral collisions, so as to avoid or mitigate the occurrence of traffic accidents and effectively improve vehicle driving safety.

[0009] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0010] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 This is an exemplary application scenario of the collision warning method provided in this disclosure;

[0012] Figure 2 This is a schematic flowchart of a collision warning method provided in an exemplary embodiment of this disclosure;

[0013] Figure 3 This is a flowchart illustrating a collision warning method provided in another exemplary embodiment of this disclosure;

[0014] Figure 4 This is a flowchart illustrating step 2023 provided in an exemplary embodiment of this disclosure;

[0015] Figure 5 This is a schematic diagram of the boundary of the maximum safe elliptical region provided in an exemplary embodiment of this disclosure;

[0016] Figure 6 This is a schematic diagram of a risk-free state of collision risk provided by an exemplary embodiment of this disclosure;

[0017] Figure 7 This is a schematic diagram of a risky state of collision risk provided by an exemplary embodiment of this disclosure;

[0018] Figure 8 This is a schematic diagram of another risky state of collision risk provided by an exemplary embodiment of this disclosure;

[0019] Figure 9 This is a flowchart illustrating step 2023 provided in another exemplary embodiment of this disclosure;

[0020] Figure 10 This is a flowchart illustrating step 2031 provided in an exemplary embodiment of this disclosure;

[0021] Figure 11 This is a schematic diagram of the structure of a collision warning device provided in an exemplary embodiment of the present disclosure;

[0022] Figure 12 This is a schematic diagram of the structure of a collision warning device provided in another exemplary embodiment of this disclosure;

[0023] Figure 13 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Detailed Implementation

[0024] Hereinafter, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0025] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0026] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0027] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0028] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0029] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0030] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0031] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0032] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0033] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0034] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0035] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0036] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0037] This disclosure outlines

[0038] In the process of realizing this disclosure, the inventors discovered that vehicle collision warning systems typically have forward collision warning and rear collision warning functions. However, due to the obstruction of the vehicle structure, the driver has certain blind spots in the side, which can easily lead to side collisions (or lateral collisions), resulting in poor vehicle driving safety.

[0039] Exemplary Overview

[0040] Figure 1 This is an exemplary application scenario of the collision warning method provided in this disclosure.

[0041] In order to provide timely lateral collision warning during vehicle operation, the collision warning method disclosed herein can determine the boundary of the target drivable safe zone based on visual information of the surrounding environment, determine the target warning zone based on the vehicle's current state information, and then determine whether there is a risk of lateral collision by combining the boundary of the target drivable safe zone and the target warning zone. If there is a risk, a lateral collision warning can be issued in a timely manner, thereby reminding the driver to take obstacle avoidance measures and avoiding lateral collision accidents caused by blind spots in the side vision, effectively improving vehicle driving safety. The vehicle's current state information may include the vehicle's lateral speed, and may also include other relevant information, such as the vehicle's width, longitudinal speed, lateral acceleration, etc., which can be set according to actual needs. Visual information about the surrounding environment can be obtained through cameras installed on the vehicle. For example, in the case of a lateral collision, side-view cameras can be used to collect information about the vehicle's lateral surroundings. These side-view cameras can include a front left camera, a rear left camera, a front right camera, and a rear right camera. The front left camera can be installed at the front left of the vehicle to collect visual information from the rear left perspective; the rear left camera can be installed at the rear left of the vehicle to collect visual information from the front left perspective; the front right camera can be installed at the front right of the vehicle to collect visual information from the rear right perspective; and the rear right camera can be installed at the rear right of the vehicle to collect visual information from the front right perspective. The specific camera setup can be customized according to actual needs and is not limited to the above methods. The boundary of the target drivable safe zone includes multiple coordinate points on the boundary. Each coordinate point can be a coordinate point in the vehicle coordinate system. The vehicle coordinate system can be established according to actual needs, for example, with the center of the rear axle of the vehicle as the origin, the length direction of the vehicle as the vertical axis (represented by x), and the width direction of the vehicle as the horizontal axis (represented by y).

[0042] Exemplary methods

[0043] Figure 2 This is a schematic flowchart of a collision warning method provided in an exemplary embodiment of this disclosure. This embodiment can be applied to electronic devices, specifically, for example, on an in-vehicle computing platform. Figure 2 As shown, it includes the following steps:

[0044] Step 201: Obtain visual information about the surrounding environment of the current vehicle and the current status information of the current vehicle.

[0045] The current status information can include the vehicle's lateral velocity, as well as other relevant information such as longitudinal velocity and lateral acceleration, which can be configured according to actual needs. This current status information can be obtained from relevant data acquisition devices on the vehicle, such as speed sensors and acceleration sensors. Visual information about the surrounding environment can be obtained through cameras installed on the vehicle; details will not be elaborated further.

[0046] Step 202: Determine the boundary of the target's safe driving zone based on visual information of the surrounding environment.

[0047] The target drivable safe zone boundary includes multiple coordinate points on the drivable safe zone boundary, each of which can be a coordinate point in the vehicle coordinate system. The target drivable safe zone boundary can be determined based on the drivable zone boundary. Specifically, the target drivable safe zone boundary can be the boundary of the drivable area (Free Space), or the target drivable safe zone formed by the target drivable safe zone boundary can be a subset of the drivable area formed by the drivable zone boundary, depending on actual needs. The drivable zone boundary refers to the intersection between the current drivable road area and obstacles. The drivable zone boundary can be determined using any feasible method, such as using multi-object detection or semantic segmentation to determine the obstacle area and road surface area from the surrounding visual information, thereby obtaining the drivable zone boundary based on the obstacle area and road surface area. Specifically, the drivable zone contour pixel point set in the image pixel coordinate system can be determined first, and then, through coordinate system transformation, the drivable zone contour coordinate point set in the vehicle coordinate system can be obtained. The drivable zone boundary can then be determined based on the drivable zone contour coordinate point set.

[0048] Step 203: Determine the target warning area based on the current status information.

[0049] The current state information represents the vehicle's subsequent direction of travel and its speed in that direction. Different speeds result in different potential collision times and levels of danger. Therefore, a target warning area can be determined based on the current state information for lateral collision warning. Since it incorporates the current state information of the vehicle, the target warning area differs for different vehicle states. For example, when the lateral speed is high, the target warning area is set to a larger value in the lateral direction, thereby enabling early detection of collision risks and improving the accuracy and effectiveness of collision warnings.

[0050] Steps 203 and 202 are not in any particular order.

[0051] Step 204: Based on the target drivable safe zone boundary and the target warning zone, determine the lateral collision risk status, which includes two states: risky and no risk.

[0052] In this context, "risky" indicates that the current vehicle faces a risk of lateral collision, while "no risk" indicates that the current vehicle does not face a risk of lateral collision. The target drivable safe zone boundary represents the drivable area of ​​the current vehicle, while the target warning area represents the area where a warning is required based on the current state information of the current vehicle. By analyzing the relationship between the target drivable safe zone boundary and the target warning area, the lateral collision risk of the current vehicle can be determined.

[0053] In an optional example, forward collision risk and / or rear collision risk can also be determined based on the target drivable safe zone boundary and the target warning zone, which can be set according to actual needs.

[0054] In an optional example, the risk can be set to multiple risk levels according to actual needs. Different warning methods and / or warning content can be set for different risk levels, which can be specifically set according to actual needs. For example, different target warning areas can be set for different risk levels, and the risk level can be determined by the relationship between the boundary of the target's safe driving area and each target warning area.

[0055] Step 205: In response to the lateral collision risk status being deemed risky, a lateral collision warning is issued.

[0056] When the current vehicle's lateral collision risk status is determined to be risky, it means that the vehicle needs to take corresponding obstacle avoidance measures. Therefore, a lateral collision warning can be issued in a timely manner to remind the driver to take appropriate obstacle avoidance measures in time to avoid lateral collision accidents caused by blind spots in the side vision.

[0057] The collision warning method provided in this embodiment determines the target warning area based on the vehicle's current state information, determines the boundary of the target drivable safe area based on the visual information of the vehicle's surrounding environment, and then determines the lateral collision risk status based on the boundary of the target drivable safe area and the target warning area. When the lateral collision risk status is determined to be risky, a lateral collision warning can be issued in a timely manner to remind the user in the vehicle to take obstacle avoidance measures in time. This achieves effective lateral collision warning to avoid or mitigate traffic accidents caused by blind spots in the side vision, improves the timeliness and effectiveness of lateral collision warning, and effectively improves vehicle driving safety.

[0058] Figure 3 This is a flowchart illustrating a collision warning method provided in another exemplary embodiment of this disclosure.

[0059] In an optional example, step 204, based on the target drivable safe zone boundary and the target warning zone, determines the lateral collision risk status, including:

[0060] Step 2041: In response to the target warning area exceeding the boundary of the target drivable safe area, the lateral collision risk status is determined to be risky.

[0061] The target warning area indicates that any obstacle within this area requires a warning. The target drivable safe zone boundary is the boundary of the safe zone where the vehicle can drive. When the target warning area exceeds the target drivable safe zone boundary, it indicates that there may be obstacles within the target warning area, and therefore the lateral collision risk status is determined to be risky.

[0062] Step 2042: In response to the fact that the target warning area does not exceed the boundary of the target drivable safe area, the lateral collision risk status is determined to be no risk.

[0063] Since the target warning area is determined based on the current status information of the vehicle, when the target warning area does not exceed the boundary of the target drivable safe area, it means that there are no obstacles in the target warning area. Therefore, the lateral collision risk status is determined to be no risk and lateral collision warning is not required at this time.

[0064] This disclosure compares the target warning area with the target drivable safe area boundary to determine whether there is a risk of lateral collision based on whether the target warning area is within the target drivable safe area. This can further ensure timely and effective warning of the risk of lateral collision in the current state of the vehicle while effectively ensuring that the vehicle is driving within the drivable safe area, thereby further improving vehicle driving safety.

[0065] In one optional example, step 202, which determines the boundary of the target drivable safe zone based on visual information of the surrounding environment, includes:

[0066] Step 2021: Based on the visual information of the surrounding environment, determine the set of drivable area contour pixels in the image pixel coordinate system.

[0067] The surrounding environment visual information can include environmental images corresponding to each viewpoint in at least one perspective, where each viewpoint corresponds to a camera on the vehicle. For example, the aforementioned four side-view cameras can obtain environmental images corresponding to four different viewpoints. Based on each environmental image, a set of drivable area contour pixels in the image pixel coordinate system corresponding to each viewpoint can be determined in a certain way, serving as the set of drivable area contour pixels in the image coordinate system corresponding to the surrounding environment visual information. The drivable area contour pixel set is the set of pixels on the boundary of the drivable area in the image pixel coordinate system; the specific determination principle will not be elaborated further.

[0068] Step 2022: Based on the set of drivable area contour pixels, determine the set of drivable area contour coordinates in the vehicle coordinate system corresponding to the current vehicle.

[0069] Specifically, by utilizing the transformation relationship between the image pixel coordinate system and the vehicle coordinate system, the set of pixel points representing the drivable area contour can be transformed to the vehicle coordinate system, thus obtaining the set of coordinate points representing the drivable area contour in the current vehicle's vehicle coordinate system. For example, the transformation can be performed first from the image pixel coordinate system to the camera coordinate system, and then from the camera coordinate system to the vehicle coordinate system. The specific transformation principle will not be elaborated further.

[0070] Step 2023: Determine the boundary of the target drivable safe area based on the set of drivable area contour coordinate points.

[0071] The set of coordinate points representing the drivable area outline constitutes the aforementioned drivable area boundary. The target drivable safe area boundary can be further determined based on the drivable area boundary according to certain requirements. For example, if the drivable area boundary shape is irregular, a regularly shaped area boundary can be determined within the drivable area boundary as the target drivable safe area boundary. The specific shape can be set according to actual needs, such as ellipse or rectangle, to facilitate shape description. In practical applications, the boundary formed by the drivable area outline coordinate points can also be used as the target drivable safe area boundary, which can be set according to actual needs.

[0072] This disclosure determines the set of drivable area contour pixels in the image pixel coordinate system by using visual information of the surrounding environment, and then transforms it to the vehicle coordinate system to obtain the set of drivable area contour coordinates. Based on the set of drivable area contour coordinates, the boundary of the target drivable safe area is determined. This realizes the determination of the drivable safe area boundary based solely on the surround view image, without the need for radar or other types of sensor assistance, which can effectively reduce sensor costs.

[0073] Figure 4 This is a flowchart illustrating step 2023 provided in an exemplary embodiment of this disclosure.

[0074] In one optional example, step 2023, determining the boundary of the target drivable safe zone based on the set of drivable area contour coordinate points, includes:

[0075] Step 20231a: Based on the set of coordinate points of the drivable area contour, determine the boundary of the maximum safe elliptical region around the current vehicle, with the boundary of the maximum safe elliptical region centered on the origin of the vehicle coordinate system.

[0076] The major semi-axis of the boundary of the maximum safe elliptical region can be either the semi-axis in the lateral direction along the vehicle coordinate system or the semi-axis in the longitudinal direction, which can be set according to actual needs.

[0077] In one alternative example, since the vehicle's longitudinal speed is typically higher and its lateral speed is typically lower, to ensure both longitudinal and lateral safety, the major semi-axis of the maximum safety elliptical region boundary can be set to the longitudinal direction and the minor semi-axis to the lateral direction.

[0078] Step 20232a: Use the boundary of the maximum safe elliptical region as the boundary of the target drivable safe region.

[0079] For example, Figure 5 This is a schematic diagram of the boundary of the maximum safe elliptical region provided in an exemplary embodiment of this disclosure. The ellipse represents the boundary of the maximum safe elliptical region, and the small circles surrounding the ellipse represent coordinate points in the set of coordinate points of the drivable area outline. The small rectangle at the center of the ellipse can represent the current vehicle.

[0080] This disclosure determines the boundary of the maximum safe elliptical region around the current vehicle as the target safe drivable region boundary based on the set of coordinate points of the drivable area contour. The ellipse better fits the range of vehicle driving characteristics, thereby making the lateral collision risk state determined based on the boundary of the maximum safe elliptical region more accurate and effective.

[0081] In an optional example, step 20231a, which determines the boundary of the maximum safe elliptical region around the current vehicle based on the set of drivable region contour coordinate points, includes: determining the description parameters corresponding to the boundary of the maximum safe elliptical region based on the set of drivable region contour coordinate points and preset constraints, wherein the description parameters include the major semi-axis parameter and the minor semi-axis parameter of the boundary of the maximum safe elliptical region; and determining the boundary of the maximum safe elliptical region based on the description parameters.

[0082] The preset constraints can be set according to actual needs. For example, all coordinate points in the set of coordinate points of the drivable area outline must not be located inside the ellipse, but outside or on the ellipse. The preset constraints can also include other related conditions, such as the major semi-axis being vertical and the minor semi-axis being horizontal, etc. The specific settings can be made according to actual needs. The major semi-axis parameter includes the length of the major semi-axis, and the minor semi-axis parameter includes the length of the minor semi-axis.

[0083] For example, according to the equation of an ellipse:

[0084]

[0085] Where 'a' represents the semi-axis length in the longitudinal direction (x-axis direction of the vehicle coordinate system), and 'b' represents the semi-axis length in the lateral direction (y-axis direction of the vehicle coordinate system). The objective equation of this disclosure is max f = (a + b), with the constraint that all envelope points (coordinate points in the set of coordinate points of the drivable area contour) lie on or outside the ellipse, i.e., all envelope points satisfy:

[0086]

[0087] To ensure that the shape of the boundary of the maximum safe elliptical region is not too distorted, based on the vehicle's driving characteristics, the longitudinal semi-axis of the ellipse can be set to be larger than the lateral semi-axis, but not by too much. For example, the shape of the ellipse can be constrained.

[0088] b <a<Nb

[0089] N can be set according to actual needs, for example, set to 10.

[0090] Finally, solving for the maximum safe elliptical region boundary is transformed into the following optimization problem.

[0091] maxb

[0092] The constraints are:

[0093] ((x i y i )∈Envelope point set)

[0094] Right now,

[0095]

[0096] (x i y i () represents the coordinates of the points in the set of coordinates of the drivable area outline. This means finding all coordinate points in the set of coordinate points of the drivable area outline that make Based on this, we can determine b and a.

[0097] Based on the coordinate points in the set of drivable area contour coordinate points and preset constraints, this disclosure can determine the boundary of the maximum safe elliptical area that better matches the vehicle's driving characteristics, providing more accurate and effective data support for judging the lateral collision risk state.

[0098] In an optional example, the major semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along the first direction of the vehicle coordinate system, and the minor semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along the second direction of the vehicle coordinate system; step 204, based on the boundary of the target drivable safe region and the target warning region, determines the lateral collision risk state as risky, including: in response to the maximum lateral coordinate of the target warning region being greater than the minor semi-axis parameter, or the absolute value of the minimum lateral coordinate of the target warning region being greater than the minor semi-axis parameter, determining the lateral collision risk state as risky.

[0099] In this system, the first direction can be lateral, and the corresponding second direction is longitudinal. Alternatively, the first direction can also be longitudinal, in which case the second direction would be lateral. The specific direction can be set according to actual needs. Since the boundary of the target drivable safe area of ​​the ellipse is centered on the origin of the vehicle coordinate system, its semi-axis parameter can represent the absolute value of the coordinate in the corresponding direction. The target warning area is the area surrounding the current vehicle. As long as the lateral range of the target warning area can be determined to be within the lateral range of the ellipse, there is no risk of lateral collision. The maximum lateral coordinate of the target warning area must be positive, and conversely, the minimum lateral coordinate of the target warning area must be negative. Therefore, the lateral collision risk status can be determined by comparing the absolute values ​​of the maximum and minimum lateral coordinates of the target warning area with the minor semi-axis parameter. For example, if the maximum horizontal coordinate of the target warning area is less than the minor axis parameter and the absolute value of the minimum horizontal coordinate of the target warning area is less than the minor axis parameter, it means that the target warning area is within the boundary of the target drivable safe zone in the lateral direction, and therefore there is no risk of lateral collision. Conversely, if the maximum horizontal coordinate of the target warning area is greater than the minor axis parameter, or the absolute value of the minimum horizontal coordinate of the target warning area is greater than the minor axis parameter, it indicates that the current target warning area may have exceeded the boundary of the target drivable safe zone in the lateral direction, and therefore there is a risk of lateral collision.

[0100] For example, Figure 6 This is a schematic diagram of a risk-free state of collision risk provided by an exemplary embodiment of this disclosure. Figure 7 This is a schematic diagram of a risky state of collision risk provided by an exemplary embodiment of this disclosure. Figure 8 This is a schematic diagram of another risky state of collision risk provided by an exemplary embodiment of this disclosure. In it, the warning ROI area represents the target warning area, the ellipse represents the boundary of the target drivable safe area, and the "self" represents the current vehicle. It can be seen that... Figure 6 The warning area for the target did not exceed the boundary of the target's safe driving area, therefore there was no risk of lateral collision. Figure 7 The maximum lateral coordinate of the target warning area is greater than the minor semi-axis parameter, which exceeds the boundary of the target's safe driving area, thus posing a risk of lateral collision. Figure 8 The absolute value of the minimum lateral coordinate of the target warning area is greater than the minor semi-axis parameter, which exceeds the boundary of the target's safe driving area, thus posing a risk of lateral collision.

[0101] In an optional example, when the major semi-axis of the ellipse's target drivable safety zone boundary is in the lateral direction, the absolute values ​​of the maximum and minimum abscissas of the target warning area can be compared with the major semi-axis parameter to determine the lateral collision risk. The specific principle is similar to the aforementioned comparison of the minor semi-axis parameter, and will not be repeated here. However, to further ensure vehicle driving safety, the comparison can be set according to the aforementioned minor semi-axis parameter, which can be set according to actual needs. To further ensure vehicle driving safety, based on vehicle driving characteristics, the major semi-axis of the obtained target drivable safety zone boundary ellipse can be constrained to be the longitudinal semi-axis, and the minor semi-axis to be the lateral semi-axis.

[0102] This disclosure uses the comparison of the maximum and minimum lateral coordinates of the target warning area with the minor semi-axis parameter of the ellipse's target drivable safe zone boundary to determine the lateral collision risk, which can further ensure the lateral driving safety of the vehicle.

[0103] Figure 9 This is a flowchart illustrating step 2023 provided in another exemplary embodiment of this disclosure.

[0104] In one optional example, the boundary of the target drivable safe zone is determined based on the set of drivable area contour coordinate points, including:

[0105] Step 20231b: Based on the set of drivable area contour coordinate points, determine the boundary of the maximum safe rectangular area around the current vehicle that can be driven.

[0106] Similar to the aforementioned maximum safe elliptical region boundary, the maximum safe rectangular region boundary can be determined based on the set of coordinate points of the drivable area contour and certain constraints. These constraints are set using a rectangular description method, with the same purpose as described above: ensuring that the envelope points are all outside or on the rectangle, and not inside it, thus guaranteeing that there are no obstacles within the area formed by the boundary of the target drivable safe region. The rectangle can be centered at the origin of the vehicle coordinate system or not, depending on actual needs.

[0107] For example, the vertical coordinate range of the rectangle can be constrained, and the coordinate values ​​of the rectangle on the positive half-axis and the negative half-axis of the horizontal y-axis can be determined based on the horizontal coordinates of the coordinate points within the vertical coordinate range of the drivable area contour coordinate point set, thereby determining the boundary of the maximum safe rectangular area within the envelope of the drivable area contour coordinate point set.

[0108] Step 20232b: Use the boundary of the largest safe rectangular area as the boundary of the target drivable safe area.

[0109] This disclosure can also use the boundary of the maximum safe rectangular area as the boundary of the target drivable safe area for determining the lateral collision risk state, so as to ensure lateral driving safety.

[0110] In an optional example, at least two methods can be combined to determine the lateral collision risk status, such as judging based on the boundary of the maximum safe elliptical region and the boundary of the maximum safe rectangular region, respectively, and combining the two judgment results to determine the lateral collision risk status, so as to further improve the accuracy and effectiveness of lateral collision risk warning.

[0111] In an optional example, the boundary of the maximum safe rectangular area includes the maximum lateral boundary coordinate value and the minimum lateral boundary coordinate value in the vehicle coordinate system; step 204, based on the boundary of the target drivable safe area and the target warning area, determines the lateral collision risk status, including: in response to the maximum lateral coordinate of the target warning area being greater than the maximum lateral boundary coordinate value, or the minimum lateral coordinate of the target warning area being less than the minimum lateral boundary coordinate value, determining the lateral collision risk status as risky.

[0112] Specifically, the rectangle can be constrained to have adjacent sides parallel to the two coordinate axes, ensuring that the lateral coordinates of points on the vertical side of the rectangle are the same, and the vertical coordinates of points on the lateral side of the rectangle are the same. Based on this, the maximum lateral boundary coordinate of the rectangle can be determined as the lateral coordinate value of its vertical side along the positive y-axis. Similarly, the minimum lateral boundary coordinate of the rectangle can be determined as the lateral coordinate value of its other side. By comparing the maximum lateral coordinate of the target warning area with the maximum lateral boundary coordinate of the rectangle, and by comparing the minimum lateral coordinate of the target warning area with the minimum lateral boundary coordinate of the rectangle, it can be effectively determined whether the target warning area exceeds the boundary of the target drivable safe zone in the lateral direction, thereby determining the lateral collision risk status.

[0113] In one alternative example, the forward collision risk status and rear collision risk status of the current vehicle can be determined by other means or by the method disclosed herein, and can be set according to actual needs.

[0114] In an optional example, step 2021, determining the set of drivable area contour pixels in the image pixel coordinate system based on the visual information of the surrounding environment, includes: determining the set of drivable area contour pixels based on the visual information of the surrounding environment and a pre-trained semantic segmentation model.

[0115] Step 2022, which determines the set of drivable area contour coordinates in the vehicle coordinate system corresponding to the current vehicle based on the set of drivable area contour pixels, includes: transforming the set of drivable area contour pixels from the image pixel coordinate system to the vehicle coordinate system based on pre-obtained coordinate transformation rules to obtain the set of drivable area contour coordinates.

[0116] The semantic segmentation model can be any implementable model, such as a semantic segmentation model based on U-Net (U-shaped network), a semantic segmentation model based on FCN (Fully Convolutional Networks), a semantic segmentation model based on DeepLab and its series, etc. The specific model can be set according to actual needs, and this disclosure does not impose any limitations. The coordinate transformation rule is a pre-calibrated transformation rule from the image pixel coordinate system to the vehicle coordinate system.

[0117] This disclosure obtains a set of pixel points representing the drivable area contour through a semantic segmentation model, and then obtains a set of coordinate points representing the drivable area contour in the vehicle coordinate system based on coordinate system transformation, providing effective data support for determining the boundary of the target drivable safe area.

[0118] In an optional example, the current state information includes the current lateral speed and width of the vehicle; step 203, based on the current state information, determines the target warning area, including:

[0119] Step 2031: Determine the lateral boundary of the warning based on the lateral speed, vehicle width, and preset minimum lateral safety distance.

[0120] The preset minimum lateral safety distance for warning can be set according to actual needs, and the lateral boundary of the warning is the lateral boundary of the target warning area. Lateral speed and vehicle width are both lateral attributes of the current vehicle and have a corresponding influence on the lateral collision risk. Therefore, this disclosure integrates the vehicle's lateral speed and vehicle width for determining lateral collision risk, further improving the accuracy and effectiveness of lateral collision warning.

[0121] For example, the roles of lateral speed and vehicle width in lateral movement can be combined to set mapping rules for determining the lateral boundary of the warning. For instance, when the vehicle's positive lateral speed is greater than 0, the positive boundary value of the target warning area can be set to be larger, and the negative boundary value to be smaller. This ensures that the vehicle has a sufficient warning range on that side when it is moving in the positive lateral direction, thus avoiding lateral collision accidents caused by untimely warnings.

[0122] Step 2032: Determine the target warning area based on the horizontal boundary of the warning.

[0123] The longitudinal boundary of the warning system can be set according to actual needs. For example, similar to the lateral boundary, it can be determined based on the vehicle's current longitudinal speed and length. This allows the upper boundary to be greater than the absolute value of the lower boundary when the vehicle is moving forward, and less than the absolute value of the lower boundary when the vehicle is reversing. The specific setting is not limited. Based on the lateral and longitudinal boundaries, the target warning area is determined.

[0124] This disclosure, by combining lateral speed, vehicle width, and preset minimum lateral safety distance, can effectively determine the target warning area that matches the current state of the vehicle, thereby further improving the vehicle's lateral driving safety.

[0125] Figure 10 This is a flowchart illustrating step 2031 provided in an exemplary embodiment of this disclosure.

[0126] In an optional example, step 2031, which determines the warning lateral boundary based on lateral speed, vehicle width, and a preset minimum lateral safety distance, includes:

[0127] 1. In response to a lateral velocity greater than or equal to 0, the lower boundary value of the first warning lateral boundary is determined based on the preset minimum lateral safety distance for warning, vehicle width, and the mapping rule of the first lower boundary value. The lower boundary value of the first warning lateral boundary is the coordinate value in the vehicle coordinate system.

[0128] The lower bound of the first warning lateral boundary represents the minimum boundary threshold of the warning lateral boundary. The preset minimum lateral safety distance for warning can characterize the minimum lateral safety distance without considering vehicle width and lateral speed. For example, when the lateral speed is greater than 0, the current vehicle tends to drift to the right. The lower bound of the first warning lateral boundary can be the boundary value on the left side of the vehicle. Since lateral speed has a relatively small impact on the left side, the lower bound of the first warning lateral boundary can be determined without considering lateral speed, based on the preset minimum lateral safety distance for warning and the vehicle width. Of course, in practical applications, lateral speed can also be considered, and the specific setting can be based on actual needs.

[0129] For example, the lower bound of the first warning horizontal boundary can be represented as: -dy min -0.5w. Where dy min This indicates the minimum lateral safety distance for preset warnings, and w represents the vehicle width.

[0130] 2. Based on the lateral speed, the preset minimum lateral safety distance for warning, the vehicle width, and the mapping rule of the first upper boundary value, determine the upper boundary value of the first warning lateral boundary, so that the upper boundary value of the first warning lateral boundary is greater than or equal to the absolute value of the lower boundary value of the first warning lateral boundary. The upper boundary value of the first warning lateral boundary is the coordinate value in the vehicle coordinate system.

[0131] Among them, the upper limit value of the first warning horizontal boundary represents the maximum boundary threshold of the warning horizontal boundary.

[0132] For example, the upper bound of the first warning horizontal boundary can be expressed as: max{t×V y ,dy min}+0.5w], where t represents the preset time, such as 1 second or other values, which can be set according to actual needs; V y This represents lateral velocity; other symbols are as described above. It can be seen that the upper limit of the first warning lateral boundary can increase with the increase of lateral velocity, thus ensuring timely and effective lateral collision warning under lateral offset conditions.

[0133] In an optional example, the upper bound of the first warning horizontal boundary can also be expressed as: t×V y +dy min +0.5w, the specific mapping rule for the first upper bound value can be set according to actual needs, as long as the absolute value of the upper bound value of the warning horizontal boundary is greater than the lower bound value.

[0134] 3. Determine the horizontal boundary of the early warning system based on the lower and upper bounds of the first horizontal boundary.

[0135] For example, the warning horizontal boundary is represented as: [-dy min -0.5w,max{t×V y ,dy min}+0.5w).

[0136] This disclosure sets corresponding mapping rules so that when the lateral speed is greater than 0, the upper limit of the warning lateral boundary is greater than the absolute value of the lower limit, thereby increasing the lateral warning range in the lateral speed direction and ensuring that there is enough time for lateral collision warning in the lateral deviation state, thus further improving lateral driving safety.

[0137] In an optional example, step 2031, which determines the warning lateral boundary based on lateral speed, vehicle width, and a preset minimum lateral safety distance, further includes:

[0138] a. In response to a lateral velocity less than 0, the lower boundary value of the second warning lateral boundary is determined based on the lateral velocity, the preset minimum lateral safety distance for warning, the vehicle width, and the mapping rule of the second lower boundary value. The lower boundary value of the second warning lateral boundary is the coordinate value in the vehicle coordinate system.

[0139] b. Based on the preset minimum lateral safety distance for early warning, vehicle width, and the mapping rule of the second upper boundary value, determine the upper boundary value of the second lateral boundary for early warning, so that the absolute value of the lower boundary value of the second lateral boundary for early warning is greater than or equal to the upper boundary value of the second lateral boundary for early warning. The upper boundary value of the second lateral boundary for early warning is the coordinate value in the vehicle coordinate system.

[0140] c. Determine the horizontal boundary of the early warning system based on the lower limit value of the second early warning horizontal boundary and the upper limit value of the second early warning horizontal boundary.

[0141] The specific operating principle of step ac is similar to that of the aforementioned lateral velocity being greater than or equal to 0. The only difference is that the direction of the lateral velocity is different. The corresponding mapping rule is adjusted so that the absolute value of the lower boundary of the second warning lateral boundary is greater than or equal to the upper boundary of the second warning lateral boundary. The details will not be elaborated further.

[0142] For example, when the lateral velocity is less than 0, the determined warning lateral boundary can be expressed as: [min{t×V y ,-dy min}-0.5w,dy min +0.5w).

[0143] In one optional example, the lateral collision warning can be implemented in any feasible way, such as graphic warning, sound warning, etc., which can be set according to actual needs.

[0144] The embodiments or optional examples disclosed above can be implemented individually or in any combination without conflict. The specific implementation can be set according to actual needs, and this disclosure does not limit it.

[0145] Any collision warning method provided in this disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers. Alternatively, any collision warning method provided in this disclosure can be executed by a processor, such as by a processor executing any of the collision warning methods mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated below.

[0146] Exemplary device

[0147] Figure 11 This is a schematic diagram of a collision warning device provided in an exemplary embodiment of the present disclosure. The device in this embodiment can be used to implement the corresponding method embodiments of the present disclosure, such as… Figure 11The device shown includes: a first acquisition module 501, a first processing module 502, a second processing module 503, a third processing module 504, and a fourth processing module 505.

[0148] The first acquisition module 501 is used to acquire visual information of the surrounding environment of the current vehicle and the current state information of the current vehicle; the first processing module 502 is used to determine the boundary of the target drivable safe area based on the visual information of the surrounding environment; the second processing module 503 is used to determine the target warning area based on the current state information; the third processing module 504 is used to determine the lateral collision risk state based on the boundary of the target drivable safe area and the target warning area, the lateral collision risk state including two states: risky and no risk; the fourth processing module 505 is used to issue a lateral collision warning in response to the lateral collision risk state being risky.

[0149] Figure 12 This is a schematic diagram of the structure of a collision warning device provided in another exemplary embodiment of this disclosure.

[0150] In an optional example, the third processing module 504 includes: a first determining unit 5041, configured to determine the lateral collision risk state as risky in response to the target warning area exceeding the boundary of the target drivable safe area; and a second determining unit 5042, configured to determine the lateral collision risk state as risk-free in response to the target warning area not exceeding the boundary of the target drivable safe area.

[0151] In one optional example, the first processing module 502 includes:

[0152] The first processing unit 5021 is used to determine the set of drivable area contour pixels in the image pixel coordinate system based on the surrounding environment visual information; the second processing unit 5022 is used to determine the set of drivable area contour coordinates in the vehicle coordinate system corresponding to the current vehicle based on the set of drivable area contour pixels; the third processing unit 5023 is used to determine the boundary of the target drivable safe area based on the set of drivable area contour coordinates.

[0153] In an optional example, the third processing unit 5023 is specifically used to: determine the boundary of the maximum safe elliptical region around the current vehicle based on the set of drivable area contour coordinate points, wherein the boundary of the maximum safe elliptical region is centered on the origin of the vehicle coordinate system; and use the boundary of the maximum safe elliptical region as the boundary of the target drivable safe region.

[0154] In an optional example, the third processing unit 5023 is specifically used to: determine the description parameters corresponding to the boundary of the maximum safe elliptical region based on the set of contour points of the drivable area and preset constraints, wherein the description parameters include the major semi-axis parameter and the minor semi-axis parameter of the boundary of the maximum safe elliptical region; and determine the boundary of the maximum safe elliptical region based on the description parameters.

[0155] In an optional example, the major semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along a first direction of the vehicle coordinate system, and the minor semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along a second direction of the vehicle coordinate system; the third processing module 504 is specifically used to: determine the lateral collision risk state as risky in response to the maximum lateral coordinate of the target warning region being greater than the minor semi-axis parameter, or the absolute value of the minimum lateral coordinate of the target warning region being greater than the minor semi-axis parameter.

[0156] In an optional example, the third processing unit 5023 is specifically used to: determine the boundary of the maximum safe rectangular area around the current vehicle based on the set of drivable area contour coordinate points; and use the boundary of the maximum safe rectangular area as the boundary of the target drivable safe area.

[0157] In an optional example, the boundary of the maximum safe rectangular area includes the maximum lateral boundary coordinate value and the minimum lateral boundary coordinate value in the vehicle coordinate system; the third processing module 504 is specifically used to: determine the lateral collision risk state as risky in response to the maximum lateral coordinate of the target warning area being greater than the maximum lateral boundary coordinate value, or the minimum lateral coordinate of the target warning area being less than the minimum lateral boundary coordinate value.

[0158] In an optional example, the first processing unit 5021 is specifically used to: determine the set of outline pixels of the drivable area based on the visual information of the surrounding environment and the semantic segmentation model obtained through pre-training; the second processing unit 5022 is specifically used to: transform the set of outline pixels of the drivable area from the image pixel coordinate system to the vehicle coordinate system based on the coordinate transformation rules obtained in advance, so as to obtain the set of outline coordinates of the drivable area.

[0159] In an optional example, the current state information includes the current lateral speed and vehicle width of the vehicle; the second processing module 503 includes:

[0160] The third determining unit 5031 is used to determine the warning lateral boundary based on the lateral speed, the vehicle width, and the preset warning minimum lateral safety distance; the fourth determining unit 5032 is used to determine the target warning area based on the warning lateral boundary.

[0161] In an optional example, the third determining unit 5031 is specifically used for:

[0162] In response to the lateral speed being greater than or equal to 0, based on the preset minimum lateral safety distance for warning, the vehicle width, and a first lower boundary value mapping rule, a first warning lateral boundary lower boundary value is determined, where the first warning lateral boundary lower boundary value is a coordinate value in the vehicle coordinate system; based on the lateral speed, the preset minimum lateral safety distance for warning, the vehicle width, and a first upper boundary value mapping rule, a first warning lateral boundary upper boundary value is determined, such that the first warning lateral boundary upper boundary value is greater than or equal to the absolute value of the first warning lateral boundary lower boundary value, where the first warning lateral boundary upper boundary value is a coordinate value in the vehicle coordinate system; based on the first warning lateral boundary lower boundary value and the first warning lateral boundary upper boundary value, the warning lateral boundary is determined; or In response to the lateral speed being less than 0, a second warning lateral boundary lower bound value is determined based on the lateral speed, the preset warning minimum lateral safety distance, the vehicle width, and a second lower bound value mapping rule. The lower bound value of the second warning lateral boundary is a coordinate value in the vehicle coordinate system. Based on the preset warning minimum lateral safety distance, the vehicle width, and the second upper bound value mapping rule, a second warning lateral boundary upper bound value is determined such that the absolute value of the lower bound value of the second warning lateral boundary is greater than or equal to the upper bound value of the second warning lateral boundary. The upper bound value of the second warning lateral boundary is a coordinate value in the vehicle coordinate system. Based on the lower bound value and the upper bound value of the second warning lateral boundary, the warning lateral boundary is determined.

[0163] Exemplary electronic devices

[0164] This disclosure also provides an electronic device, including: a memory for storing computer programs;

[0165] A processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, it implements the collision warning method described in any of the above embodiments of the present disclosure.

[0166] Figure 13 This is a schematic diagram of an application embodiment of the electronic device disclosed herein. In this embodiment, the electronic device 10 includes one or more processors 11 and a memory 12.

[0167] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0168] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the methods of the various embodiments of this disclosure described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0169] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0170] For example, the input device 13 may be the microphone or microphone array described above, used to capture the input signal of the sound source.

[0171] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0172] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0173] Of course, for the sake of simplicity, Figure 13 Only some of the components of the electronic device 10 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0174] Exemplary computer program products and computer-readable storage media

[0175] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0176] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0177] Furthermore, embodiments of this disclosure may also be computer-readable storage media having computer program instructions stored thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0178] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable 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.

[0179] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0180] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0181] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0182] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0183] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0184] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0185] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A collision warning method, comprising: Obtain visual information about the surrounding environment of the current vehicle and the current state information of the current vehicle; Based on the surrounding visual information, the boundary of the target drivable safe area is determined; the boundary of the target drivable safe area is the boundary of the drivable area, or the target drivable safe area formed by the boundary of the target drivable safe area is a subset of the drivable area formed by the boundary of the drivable area; the boundary of the drivable area refers to the intersection of the drivable road area of ​​the current vehicle and the obstacle. Based on the current status information, the target warning area is determined; Based on the target drivable safe zone boundary and the target warning zone, the lateral collision risk status is determined, which includes two states: risky and no risk. The lateral collision risk status is determined by the relationship between the target drivable safe zone boundary and the target warning zone. In response to the condition that the lateral collision risk is present, a lateral collision warning is issued. The current status information includes the lateral speed and width of the current vehicle. The step of determining the target warning area based on the current status information includes: The warning lateral boundary is determined based on the lateral speed, the vehicle width, and the preset minimum lateral safety distance. Based on the aforementioned horizontal boundary of the early warning system, the target early warning area is determined.

2. The method according to claim 1, wherein, The determination of the lateral collision risk status based on the target drivable safe zone boundary and the target warning zone includes: In response to the target warning area exceeding the boundary of the target drivable safe area, the lateral collision risk status is determined to be risky; Since the target warning area does not exceed the boundary of the target drivable safe area, the lateral collision risk status is determined to be no risk.

3. The method according to claim 1, wherein, Determining the boundary of the target's safe driving zone based on the surrounding environmental visual information includes: Based on the visual information of the surrounding environment, determine the set of drivable area contour pixels in the image pixel coordinate system. Based on the set of drivable area contour pixels, determine the set of drivable area contour coordinates in the vehicle coordinate system corresponding to the current vehicle. Based on the set of coordinate points of the drivable area contour, the boundary of the target drivable safe area is determined.

4. The method according to claim 3, wherein, Determining the boundary of the target drivable safe area based on the set of coordinate points of the drivable area contour includes: Based on the set of coordinate points of the drivable area contour, the boundary of the maximum safe elliptical region around the current vehicle is determined, with the origin of the vehicle coordinate system as the center. The boundary of the maximum safe elliptical region is taken as the boundary of the target drivable safe region.

5. The method according to claim 4, wherein, Determining the boundary of the maximum safe elliptical region for drivability around the current vehicle based on the set of coordinate points of the drivable area contour includes: Based on the set of coordinate points of the drivable area contour and the preset constraints, the description parameters corresponding to the boundary of the maximum safe elliptical region are determined. The description parameters include the major semi-axis parameter and the minor semi-axis parameter of the boundary of the maximum safe elliptical region. Based on the described parameters, the boundary of the maximum safe elliptical region is determined.

6. The method according to claim 5, wherein, The major semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along the first direction of the vehicle coordinate system, and the minor semi-axis of the boundary of the maximum safe elliptical region is the semi-axis along the second direction of the vehicle coordinate system. The determination of the lateral collision risk status based on the target drivable safe zone boundary and the target warning zone includes: In response to the maximum lateral coordinate of the target warning area being greater than the minor axis parameter, or the absolute value of the minimum lateral coordinate of the target warning area being greater than the minor axis parameter, the lateral collision risk status is determined to be risky.

7. The method according to claim 3, wherein, Determining the boundary of the target drivable safe area based on the set of coordinate points of the drivable area contour includes: Based on the set of contour points of the drivable area, determine the boundary of the maximum safe rectangular area around the current vehicle that is drivable. The boundary of the largest safe rectangular area is taken as the boundary of the target drivable safe area.

8. The method according to claim 7, wherein, The boundary of the maximum safe rectangular area includes the maximum lateral boundary coordinate value and the minimum lateral boundary coordinate value in the vehicle coordinate system; The determination of the lateral collision risk status based on the target drivable safe zone boundary and the target warning zone includes: In response to the maximum lateral coordinate of the target warning area being greater than the maximum lateral boundary coordinate value, or the minimum lateral coordinate of the target warning area being less than the minimum lateral boundary coordinate value, the lateral collision risk status is determined to be risky.

9. The method according to claim 3, wherein, The step of determining the set of drivable area contour pixels in the image pixel coordinate system based on the surrounding environment visual information includes: Based on the visual information of the surrounding environment and the pre-trained semantic segmentation model, the set of outline pixels of the drivable area is determined. The step of determining the set of drivable area contour coordinates in the vehicle coordinate system corresponding to the current vehicle based on the set of drivable area contour pixels includes: Based on the pre-obtained coordinate transformation rules, the set of drivable area contour pixels is transformed from the image pixel coordinate system to the vehicle coordinate system to obtain the set of drivable area contour coordinates.

10. The method according to claim 1, wherein, The determination of the warning lateral boundary based on the lateral speed, the vehicle width, and the preset minimum lateral safety distance includes: In response to the lateral speed being greater than or equal to 0, a first warning lateral boundary lower limit value is determined based on the preset warning minimum lateral safety distance, the vehicle width, and the first lower limit value mapping rule. The first warning lateral boundary lower limit value is the coordinate value in the vehicle coordinate system. Based on the lateral speed, the preset minimum lateral safety distance for warning, the vehicle width, and the mapping rule of the first upper boundary value, the upper boundary value of the first warning lateral boundary is determined so that the upper boundary value of the first warning lateral boundary is greater than or equal to the absolute value of the lower boundary value of the first warning lateral boundary. The upper boundary value of the first warning lateral boundary is the coordinate value in the vehicle coordinate system. The warning horizontal boundary is determined based on the lower boundary value and the upper boundary value of the first warning horizontal boundary; or, In response to the lateral speed being less than 0, a second warning lateral boundary lower limit value is determined based on the lateral speed, the preset warning minimum lateral safety distance, the vehicle width, and the second lower limit value mapping rule. The second warning lateral boundary lower limit value is the coordinate value in the vehicle coordinate system. Based on the preset minimum lateral safety distance for early warning, the vehicle width, and the mapping rule for the second upper boundary value, the upper boundary value of the second lateral boundary for early warning is determined so that the absolute value of the lower boundary value of the second lateral boundary for early warning is greater than or equal to the upper boundary value of the second lateral boundary for early warning. The upper boundary value of the second lateral boundary for early warning is the coordinate value in the vehicle coordinate system. The warning horizontal boundary is determined based on the lower boundary value and the upper boundary value of the second warning horizontal boundary.

11. A collision warning device, comprising: The first acquisition module is used to acquire visual information of the surrounding environment of the current vehicle and the current state information of the current vehicle. The first processing module is used to determine the boundary of the target drivable safe area based on the surrounding environmental visual information; the target drivable safe area boundary is a drivable area boundary, or the target drivable safe area formed by the target drivable safe area boundary is a subset of the drivable area formed by the drivable area boundary; the drivable area boundary refers to the boundary between the drivable road area of ​​the current vehicle and the obstacle. The second processing module is used to determine the target warning area based on the current status information; The third processing module is used to determine the lateral collision risk status based on the boundary of the target drivable safe area and the target warning area. The lateral collision risk status includes two states: risky and no risk. The lateral collision risk status is determined by the relationship between the boundary of the target drivable safe area and the target warning area. The fourth processing module is used to issue a lateral collision warning in response to the lateral collision risk status being deemed risky. The current status information includes the lateral speed and width of the current vehicle. The second processing module includes: The third determining unit is used to determine the warning lateral boundary based on the lateral speed, the vehicle width, and the preset warning minimum lateral safety distance; The fourth determining unit is used to determine the target warning area based on the warning horizontal boundary.

12. A computer-readable storage medium storing a computer program for performing the collision warning method according to any one of claims 1-10.

13. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the collision warning method according to any one of claims 1-10.

Images