Object Detection Method, Device, Equipment and Medium

Abstract

The present invention provides a target detection method, apparatus, device and medium, which are applied to a switch-type lidar. The method includes: obtaining the current pose and target driving path of a target vehicle equipped with the switch-type lidar; selecting a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose; calculating the central angle corresponding to the arc formed by the current pose and the target point on the circumference; determining the target detection area of the switch-type lidar corresponding to the central angle; and performing target detection on the target detection area by using the switch-type lidar to generate a target detection result. By implementing the present invention, the detection area is reasonably divided, avoiding the problems of target missing detection or false detection caused by an overly large or overly small detection area. At the same time, dividing the area by the rotation angle is very flexible, and the detection area can be quickly adjusted according to the change of the driving path, further improving the accuracy of the target detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of target detection, and particularly to a target detection method, device, equipment and medium. Background Art

[0002] The switching laser radar is different from the point cloud radar, and its output signal is of boolean type. Users can, according to their own needs, offline set different safety areas for different application scenarios. When the device is running online, if the laser radar detects that there is a target in the safety area, it will output a boolean signal indicating that there is a target in the area; otherwise, it will output the opposite boolean signal indicating that there is no target in the area.

[0003] Generally, the switching laser radar can set multiple different polygon detection areas. The user needs to divide the shape of the detection area in advance in the host computer, and when running online, enable a set of detection areas to obtain the corresponding boolean feedback signal to determine whether there is a target in the detection area. For the switching single-line laser radar applied to an unmanned vehicle, the user needs to manually set the detection area reasonably according to the motion state of the vehicle. For example, if the vehicle needs to go straight, a certain area is demarcated in front of the vehicle for detection; if the vehicle needs to turn right, an area is demarcated on the right side of the vehicle for detection, etc. In this process, if the demarcation of the detection area is too large, it is easy to cause false detection of the target; if the detected area is too small, it is easy to cause missed detection of the target, bringing potential safety hazards. Therefore, how to improve the accuracy of target detection using the switching laser radar has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a target detection method, device, equipment and medium to overcome the problem that the accuracy of the detection result is affected due to unreasonable manual division of the detection area in the existing method of detecting the target by the switching laser radar.

[0005] According to a first aspect, an embodiment of the present invention provides a target detection method, the method comprising:

[0006] Obtain the current pose and the target driving path of a target vehicle equipped with a switching laser radar;

[0007] Select a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose, the target point and the current pose are located on a circle centered on the instantaneous center of motion, and the line connecting the position where the current pose is located and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle;

[0008] Calculate the central angle corresponding to the arc formed by the current pose and the target point on the circle;

[0009] Determine the target detection area of the switch-type lidar corresponding to the central angle;

[0010] Perform target detection on the target detection area using the switch-type lidar to generate a target detection result.

[0011] Optionally, the determining the target detection area of the switch-type lidar corresponding to the central angle includes:

[0012] Calculate the first distance between the target point and the position where the current pose is located;

[0013] Based on the first distance and the central angle, screen the target detection area from a preset detection area database, where the preset detection area database stores the detection areas corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances.

[0014] Optionally, the process of constructing the preset detection area database includes:

[0015] Divide the corner interval of the target vehicle based on the motion state of the target vehicle;

[0016] Calculate the first area covered by the target vehicle in each corner interval and the detectable area corresponding to the switch-type lidar when the target vehicle moves in a circular motion to different detection distances respectively;

[0017] Based on the intersection of the first area and the detectable area of the target vehicle in each corner interval when the target vehicle moves in a circular motion to different detection distances, determine the detection area corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances.

[0018] Optionally, the screening of the target detection area from the preset detection area database based on the first distance and the central angle includes:

[0019] Obtain each first detection area corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to the first distance from the preset detection area database;

[0020] Screen the target detection area corresponding to the target corner interval corresponding to the central angle from each first detection area.

[0021] Optionally, the selecting a target point on the target driving path includes:

[0022] Select a target point on the target driving path with a distance from the position where the current pose is located being a preset distance threshold;

[0023] Alternatively, calculate the alternative points on the target driving path where the path offset exceeds a preset angle threshold; calculate the moving distances between the position where the current pose is located and each alternative point; and determine the target point as the alternative point with the minimum moving distance.

[0024] Optionally, the process of constructing the preset detection area database further includes:

[0025] Obtain the installation position of the switch-type lidar on the target vehicle;

[0026] Calculate the detectable areas corresponding to different installation positions of the switch-type lidar;

[0027] Based on the intersection of the first area and the detectable area of the target vehicle in each corner interval when the target vehicle moves in a circular motion to different detection distances at different installation positions of the switch-type lidar, determine the detection areas corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances at different installation positions of the switch-type lidar.

[0028] Optionally, the step of obtaining, from the preset detection area database, the first detection areas corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to the first distance includes:

[0029] Obtain the current installation position of the switch-type lidar on the target vehicle;

[0030] Perform a pre-search in the preset detection area database based on the current installation position;

[0031] Obtain, from the pre-search results, the first detection areas corresponding to the switch-type lidar in each corner interval when the target vehicle moves in a circular motion to the first distance.

[0032] According to a second aspect, an embodiment of the present invention provides a target detection device, the device includes:

[0033] An acquisition module, configured to acquire the current pose and the target driving path of a target vehicle equipped with a switch-type lidar;

[0034] A first processing module, configured to select a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose, where the target point and the current pose are located on a circle with the instantaneous center of motion as the center, and the line connecting the position where the current pose is located and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle;

[0035] A second processing module, configured to calculate a central angle corresponding to an arc formed by the current pose and the target point on the circumference;

[0036] A third processing module, configured to determine a target detection area of the switch-type lidar corresponding to the central angle;

[0037] A fourth processing module, configured to perform target detection on the target detection area by using the switch-type lidar to generate a target detection result.

[0038] According to a third aspect, an embodiment of the present invention provides an electronic device, including:

[0039] A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method according to the first aspect and any one of its optional embodiments.

[0040] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the method according to the first aspect or any one of the optional embodiments of the first aspect.

[0041] The technical solution of the present invention has the following advantages:

[0042] The target detection method provided by the embodiment of the present invention determines the central angle corresponding to the movement of the vehicle from the current pose to the target point in a circular motion by calculating the instantaneous center of motion of the target vehicle by using the current pose of the vehicle to select a target point on the target driving path. Furthermore, the detection area of the switch-type lidar is determined by using the central angle, that is, the rotation angle of the vehicle movement, and target detection is enabled, so that the detection area is reasonably divided, and the problem of target omission or misdetection caused by an overly large or overly small detection area is avoided. At the same time, the area division by the rotation angle is very flexible, and the detection area can be quickly adjusted according to the change of the driving path, further improving the accuracy of the target detection result. Description of the Drawings

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of the target detection method in the embodiment of the present invention;

[0045] Figure 2 This is an example diagram of the target motion rotation angle in the embodiment of the present invention;

[0046] Figure 3 This is a schematic diagram of the control process of the target protection strategy for the driverless vehicle in the embodiment of the present invention;

[0047] Figure 4 This is a schematic diagram of the detectable area of the switch-type single-line lidar on the driverless forklift in the embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of the covered area of the driverless forklift body during driving in the embodiment of the present invention;

[0049] Figure 6 This is a schematic diagram of the detection area corresponding to the switch-type single-line lidar on the driverless forklift in the embodiment of the present invention;

[0050] Figure 7 This is a schematic diagram of the structure of the target detection device in the embodiment of the present invention;

[0051] Figure 8 This is a schematic diagram of the structure of the electronic device in the embodiment of the present invention. Detailed implementation manners

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] The technical features involved in the different implementation manners of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0054] Generally, a switching laser radar can be set with multiple different polygonal detection areas. The user needs to divide the shape of the detection area in advance in the host computer and enable a set of detection areas during online operation to obtain the corresponding Boolean value feedback model to determine whether there is a target in the detection area. For the switching single-line laser radar applied to an autonomous vehicle, the user needs to manually set the detection area reasonably according to the motion state of the vehicle. For example, if the vehicle needs to go straight, a certain area is demarcated in front of the vehicle for detection; if the vehicle needs to turn right, an area is demarcated on the right side of the vehicle for detection, etc. In this process, if the demarcation of the detection area is too large, it is easy to cause false detection of the target; if the detection area is too small, it is easy to cause missed detection of the target, bringing potential safety hazards. Therefore, reasonable demarcation of the detection area is the key to the effective application of the switching single-line laser radar on an autonomous vehicle. At the same time, due to the limitation of the number of detection areas of the switching laser radar, the user must also reasonably allocate the number of detection areas to avoid waste of detection areas. Currently, there is no stable and general technical solution for the safety protection of the switching laser radar to meet these requirements in the industry.

[0055] Based on the above problems, an embodiment of the present invention provides a target detection method, as Figure 1 shown, the method specifically includes the following steps:

[0056] Step S101: Obtain the current pose and target driving path of the target vehicle equipped with a switching laser radar.

[0057] Specifically, the current pose of the target vehicle includes: the position where the target vehicle is currently located and the attitude of the target vehicle, such as the orientation of the vehicle head, etc. The target driving path is the planned driving path corresponding to the target vehicle, and the target vehicle automatically drives according to the target driving path. In practical applications, the target driving path can be obtained by real-time planning of the target vehicle or a fixed driving path set in advance by the user. The present invention is not limited thereto.

[0058] Step S102: Select a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose.

[0059] Among them, the target point and the current pose are located on a circle with the instantaneous center of motion as the center, and the line connecting the position where the current pose is located and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle. Exemplarily, as Figure 2 shown, point P is the position corresponding to the current pose of the target vehicle, the arrow indicates the orientation of the vehicle head of the target vehicle, curve 201 is the target driving path, point Q is the target point on the target driving path, and point O is the current instantaneous center of motion of the target vehicle, satisfying |OP| = |OQ|, and OP is perpendicular to the current orientation of the vehicle.

[0060] Step S103: Calculate the central angle corresponding to the arc formed by the current pose and the target point on the circumference.

[0061] Exemplarily, as Figure 2 shown, according to the instantaneous center of motion O of the vehicle and the kinematic model of the vehicle, calculate the target motion rotation angle θ of the vehicle, so that the vehicle can move to the target point Q by making a circular motion with the target motion rotation angle θ. This target motion rotation angle θ is the above-mentioned central angle.

[0062] Step S104: Determine the target detection area of the switch-type lidar corresponding to the central angle.

[0063] Specifically, since the coverage range of the detection area of the switch-type lidar changes with the change of the motion rotation angle of the target vehicle during driving, therefore, by calculating the above-mentioned central angle, that is, the motion rotation angle of the target vehicle, the detection area of the switch-type lidar can be uniquely determined to improve the accuracy of target detection.

[0064] Step S105: Use the switch-type lidar to perform target detection on the target detection area and generate a target detection result.

[0065] Specifically, by setting the detection area of the switch-type lidar as the above-mentioned target detection area, it is detected whether there is a target in the target detection area by the switch-type lidar. Exemplarily, if the switch-type lidar detects that there is a target in the target detection area, it will output a Boolean value signal indicating that there is a target in the area; otherwise, it will output the opposite Boolean value signal indicating that there is no target in the target detection area, so that the target vehicle can judge whether to execute an obstacle avoidance strategy according to the corresponding detection result, such as: controlling the vehicle to decelerate, the vehicle to stop for obstacles, voice or light alarms, etc., which are specifically designed flexibly according to the actual vehicle function requirements, and the present invention is not limited thereto.

[0066] By performing the above steps, the target detection method provided by the embodiment of the present invention determines the central angle corresponding to the vehicle moving from the current pose to the target point by circular motion by calculating the instantaneous center of motion of the target vehicle by selecting the target point on the target driving path using the current pose of the vehicle. Furthermore, the detection area of the switch-type lidar is determined by using this central angle, that is, the rotation angle of the vehicle's motion, and target detection is enabled, so that the detection area is reasonably divided, avoiding the problem of missed detection or false detection of targets caused by too large or too small detection areas. At the same time, dividing the area by the rotation angle is very flexible, and the detection area can be quickly adjusted according to the change of the driving path, further improving the accuracy of the target detection result.

[0067] Specifically, in one embodiment, in step S102, a target point is selected on the target driving path. Specifically, a target point whose distance from the position of the current pose on the target driving path is a preset distance threshold can be selected. The preset distance threshold can be flexibly set according to experience or the target detection accuracy of the target vehicle during driving and the adjustment frequency requirement of the detection area. Exemplarily, when the target vehicle is an unmanned forklift for transferring materials indoors, the preset distance threshold can be set to 1 meter, 3 meters, etc. The present invention is not limited thereto. Thus, the target point can be selected according to the set preset distance threshold according to the specific driving requirements of the target vehicle to meet the usage requirements of different users and improve the user experience.

[0068] In another alternative embodiment, in step S102, selecting a target point on the target driving path specifically includes the following steps:

[0069] Step S211: Calculate alternative points on the target driving path where the path deviation exceeds the preset angle threshold.

[0070] Specifically, in practical applications, when the vehicle is turning, the risk of target collision is more likely to occur. Target detection during turning is particularly important for safe autonomous driving. The vectors formed by two adjacent driving points on the target driving path can be calculated in sequence, and the included angle between two adjacent vectors can be calculated. When the included angle exceeds the preset angle threshold, the common driving point of the two vectors is determined as an alternative point.

[0071] Step S212: Calculate the moving distance from the position of the current pose to each alternative point.

[0072] Step S213: Determine the alternative point with the minimum moving distance as the target point.

[0073] Specifically, all alternative points on the target driving path are points that need to adjust the detection area of the switchable lidar. Therefore, according to the current pose of the vehicle and the target driving path, the point with the shortest moving distance from the position of the current pose is sequentially selected as the target point for adjusting the detection area, thus avoiding the problem that the target point is selected too far and missing the turning point during driving on the target driving path without timely adjusting the detection area of the switchable lidar, which affects the accuracy of the target detection result. Further improve the accuracy of the target detection result, and make the adjustment of the detection area of the switchable lidar more in line with the actual driving scenario of the vehicle, and improve the user experience.

[0074] Specifically, in one embodiment, step S104 specifically includes the following steps:

[0075] Step S41: Calculate the first distance between the target point and the position of the current pose.

[0076] Step S42: Screen the target detection area from the preset detection area database based on the first distance and the central angle.

[0077] Among them, in the preset detection area database, when the target vehicle moves in a circular motion to different detection distances, the detection areas corresponding to the switching lidar in each corner interval are stored.

[0078] Specifically, the process of constructing the above preset detection area database includes the following steps:

[0079] Step S201: Divide the corner intervals of the target vehicle based on the motion state of the target vehicle.

[0080] Step S202: Calculate the first area covered by the target vehicle in each corner interval and the detectable area corresponding to the switching lidar when the target vehicle moves in a circular motion to different detection distances respectively.

[0081] Step S203: Based on the intersection of the first area and the detectable area of the target vehicle in each corner interval when the target vehicle moves in a circular motion to different detection distances, determine the detection areas corresponding to the switching lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances.

[0082] Furthermore, in step S42 above, by obtaining the first detection areas corresponding to the switching lidar in each corner interval when the target vehicle moves in a circular motion to the first distance from the preset detection area database; screening the target detection areas corresponding to the target corner interval corresponding to the central angle from the first detection areas.

[0083] In addition, in practical applications, the process of constructing the above preset detection area database further includes: obtaining the installation position of the switching lidar on the target vehicle; calculating the detectable areas corresponding to different installation positions of the switching lidar; based on the intersection of the first area and the detectable area of the target vehicle in each corner interval when the target vehicle moves in a circular motion to different detection distances at different installation positions of the switching lidar, determine the detection areas corresponding to the switching lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances at different installation positions of the switching lidar.

[0084] Furthermore, it can be achieved by obtaining the current installation position of the switching lidar on the target vehicle; performing a pre-search in the preset detection area database based on the current installation position; obtaining the first detection areas corresponding to the switching lidar in each corner interval when the target vehicle moves in a circular motion to the first distance from the pre-search results.

[0085] Specifically, since multiple switching lidars can be installed on a target vehicle at different positions simultaneously, and the detectable areas of the switching lidars on the target vehicle are affected by the installation positions, by establishing the correspondence between the installation positions of the switching lidars and the detectable areas, and further establishing the correspondence between the installation positions of the switching lidars and the detectable areas corresponding to each corner interval of the switching lidars, the retrieval conditions of the preset detectable area database can be further refined, and the target detectable area corresponding to the actual installation position of the switching lidar on the target vehicle can be accurately screened out, further improving the accuracy of the target detection result.

[0086] Next, the specific working process and working principle of the target detection method provided by the embodiments of the present invention will be described in detail in combination with specific application examples.

[0087] The specific process of implementing the target protection strategy control of an autonomous vehicle by using the target detection solution provided by the embodiments of the present invention is as Figure 3 shown. The detection area of the radar is divided offline according to the vehicle corner; according to the future driving path of the vehicle, the vehicle target curvature / corner is calculated online; the required detection area is selected according to the vehicle target curvature / corner, and the corresponding protection strategy is executed.

[0088] Specifically, the detection area of the switching lidar can be divided offline, and the specific process is as follows:

[0089] Define the corner interval: According to the motion state of the vehicle, n sets of vehicle corner intervals R i =[α i , β i , i = 1, 2,..., n. For any i, j ∈ {1, 2,..., n}, i ≠ j, it satisfies α i ≥θ min , β i ≤θ max , where θ min is the minimum corner allowed for the vehicle motion, θ maxThe maximum steering angle allowed for vehicle movement; among them, the minimum steering angle and the maximum steering angle are set according to the actual physical characteristics of the vehicle, and will not be elaborated here. The movement state of the vehicle is measured by the steering angle of the vehicle's front wheels. For example, for common straight driving, small-angle right turn, large-angle right turn, etc., the steering angle intervals [-1, 1], [5, 10], [30, 40], etc. can be delimited for distinction, and the unit is degree (here the steering angle is the front wheel steering angle corresponding to the kinematic bicycle model, 0 degree corresponds to the front wheel being parallel to the extension line of the rear wheel, that is, the vehicle is in a straight driving state, and the clockwise direction is positive); the switch-type single-line lidar generally has a maximum detection area limit. For example, it can be divided into at most 40 steering angle intervals. Then the user needs to delimit the actual steering angle intervals according to the detection area quantity limit and the desired movement states to be detected (straight driving, steering at different angles, etc.). The specific delimitation quantity and results will not be elaborated here.

[0090] Calculate the coverage path of the vehicle in the steering angle interval: Set the detection distance d i , and set the vehicle to move in a circular motion to d i distance, and obtain the expected coverage area of the vehicle in the steering angle interval R i below This detection distance d i can be selected according to the actual vehicle movement performance and design requirements. For example, for an AGV operating indoors, since its movement speed is relatively low, the usual detection distance only needs to be set at 1 - 2m; for a high-speed autonomous driving vehicle traveling on an open road, a longer detection distance needs to be set, such as 50m or 100m, etc.

[0091] Calculate the detection area corresponding to the steering angle interval: Let the detectable area of the lidar be Then the detection area corresponding to the switch-type lidar in the steering angle interval R i below is

[0092] Write the corresponding detection area offline into the switch-type lidar.

[0093] After the detection area of the switch-type lidar is delimited and written offline into the switch-type lidar, the online execution process during specific driving in the vehicle is as follows:

[0094] Calculate the target steering angle of the vehicle: According to the current pose P of the vehicle, select a point Q on the target path of the vehicle, calculate the target instantaneous center of motion O of the vehicle, satisfying |OP| = |OQ|, and OP is perpendicular to the current orientation of the vehicle; according to the instantaneous center O and the vehicle kinematic model, calculate the target movement steering angle θ of the vehicle, so that the vehicle can move to the target point Q by making a circular motion with the target movement steering angle θ.

[0095] Execute a protection strategy according to the target corner: Locate the corner interval where the target corner θ is located, enable the lidar in the detection area corresponding to the corner interval to perform target detection, and execute the target protection strategy for the subsequent vehicle according to the detection result, such as: deceleration, obstacle avoidance, etc.

[0096] Exemplarily, as Figure 4 shown, taking an unmanned forklift 1 with a steerable wheel chassis as an example, the actual front wheel corner limit range of the vehicle is [-90°, 90°]; the vehicle is equipped with a switch-type single-line lidar in each of the right front and left rear directions (denoted as A and B in the figure), and each lidar can be divided into at most 45 detection areas. The actual detectable areas of the two lidars are respectively as Figure 4 shown by the dotted area and the solid area in

[0097] Above, if the driving path of the unmanned forklift 1 is to turn right and move forward, and the corner interval of the right turn is [15°, 25°], then the area covered by the body of the unmanned forklift 1 during driving is as Figure 5 shown. Correspondingly, the final detection areas corresponding to the two switch-type lidars (A and B) installed on the unmanned forklift 1 are as Figure 6 shown by the enclosed areas corresponding to 3 and 4 in Figure 6 Note that the overlapping detection area part of the two switch-type lidars is not shown in

[0098] From the above example, it can be seen that the target detection scheme provided by the embodiments of the present invention systematically and generally solves the application strategy of switch-type lidars in target protection, realizes that the size of the detection area of the switch-type lidar can be reasonably divided to avoid false detection or missed detection of the target; and the number of detection areas can be reasonably allocated to avoid waste of detection resources. At the same time, the area is divided by corners very flexibly and is convenient for quick adjustment; in addition, this implementation scheme has generality and strong flexibility, can be applied to unmanned vehicles of any shape, and is convenient for large-scale replication and maintenance.

[0099] The embodiments of the present invention also provide a target detection device, which is applied to a switch-type lidar, as Figure 7 shown, and the device includes:

[0100] An acquisition module 101, configured to acquire the current pose and target driving path of a target vehicle equipped with a switch-type lidar. For the detailed content, refer to the relevant description of step S101 in the above method embodiment, and details will not be elaborated here.

[0101] The first processing module 102 is configured to select a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose. The target point and the current pose are located on a circle with the instantaneous center of motion as the center, and the line connecting the position where the current pose is located and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle. For the detailed content, refer to the relevant description of step S102 in the above method embodiment, and details will not be elaborated here.

[0102] The second processing module 103 is configured to calculate the central angle corresponding to the arc formed by the current pose and the target point on the circle. For the detailed content, refer to the relevant description of step S103 in the above method embodiment, and details will not be elaborated here.

[0103] The third processing module 104 is configured to determine the target detection area of the switch-type lidar corresponding to the central angle. For the detailed content, refer to the relevant description of step S104 in the above method embodiment, and details will not be elaborated here.

[0104] The fourth processing module 105 is configured to perform target detection on the target detection area by using the switch-type lidar to generate a target detection result. For the detailed content, refer to the relevant description of step S105 in the above method embodiment, and details will not be elaborated here.

[0105] The target detection device provided by the embodiment of the present invention is used to execute the target detection method provided by the above embodiment. The implementation manner and principle are the same. For the detailed content, refer to the relevant description of the above method embodiment, and details will not be elaborated here.

[0106] Through the collaborative cooperation of the above-mentioned various components, the target detection device provided by the embodiment of the present invention determines the central angle corresponding to the vehicle moving from the current pose to the target point in a circular motion by calculating the instantaneous center of motion of the target vehicle by selecting a target point on the target driving path by using the current pose of the vehicle. Furthermore, the detection area of the switch-type lidar is determined by using this central angle, that is, the rotation angle of the vehicle movement, and target detection is enabled, so that the detection area is reasonably divided, avoiding the problem of target omission or false detection caused by an overly large or small detection area. At the same time, dividing the area by the rotation angle is very flexible, and the detection area can be quickly adjusted according to the change of the driving path, further improving the accuracy of the target detection result.

[0107] The embodiment of the present invention further provides an electronic device, as Figure 8 shown. The electronic device includes: a processor 901 and a memory 902. Among them, the processor 901 and the memory 902 can be connected through a bus or other means. Figure 8 Taking the connection through the bus as an example.

[0108] The processor 901 may be a Central Processing Unit (CPU). The processor 901 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above types of chips.

[0109] As a non-transitory computer-readable storage medium, the memory 902 can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the above method embodiments. The processor 901 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 902, that is, implements the methods in the above method embodiments.

[0110] The memory 902 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor 901, etc. In addition, the memory 902 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 902 may optionally include a memory remotely set relative to the processor 901, and these remote memories can be connected to the processor 901 through a network. Examples of the above networks include, but are not limited to, the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] One or more modules are stored in the memory 902 and, when executed by the processor 901, implement the methods in the above method embodiments.

[0112] For the specific details of the above electronic device, reference can be made to the corresponding relevant descriptions and effects in the above embodiments for understanding, and details will not be repeated here.

[0113] Those skilled in the art can understand that to implement all or part of the processes in the above-described embodiment methods, it can be completed by instructing relevant hardware through a computer program. The implemented program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-described method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memories.

[0114] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A target detection method, characterized in that, The method includes: Obtaining the current pose and the target driving path of a target vehicle equipped with a switch - type lidar; Selecting a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose, where the target point and the current pose are located on a circle centered at the instantaneous center of motion, and the line connecting the position of the current pose and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle; Calculating the central angle corresponding to the arc formed by the current pose and the target point on the circle; Determining the target detection area of the switch - type lidar corresponding to the central angle; Performing target detection on the target detection area by using the switch - type lidar to generate a target detection result.

2. The method according to claim 1, characterized in that, The determining the target detection area of the switch - type lidar corresponding to the central angle includes: Calculating the first distance between the target point and the position where the current pose is located; Based on the first distance and the central angle, screening the target detection area from a preset detection area database, where the preset detection area database stores the detection areas corresponding to the switch - type lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances.

3. The method according to claim 2, characterized in that, The process of constructing the preset detection area database includes: Dividing the corner intervals of the target vehicle based on the motion state of the target vehicle; Calculating the first area covered by the target vehicle in each corner interval and the detectable area corresponding to the switch - type lidar when the target vehicle moves in a circular motion to different detection distances respectively; Based on the intersection of the first area and the detectable area of the target vehicle in each corner interval when the target vehicle moves in a circular motion to different detection distances, determining the detection areas corresponding to the switch - type lidar in each corner interval when the target vehicle moves in a circular motion to different detection distances.

4. The method according to claim 3, characterized in that, The screening the target detection area from the preset detection area database based on the first distance and the central angle includes: Obtaining each first detection area corresponding to the switch - type lidar in each corner interval when the target vehicle moves in a circular motion to the first distance from the preset detection area database; Screening the target detection area corresponding to the target corner interval corresponding to the central angle from each first detection area.

5. The method according to claim 1, characterized in that, The selecting a target point on the target driving path includes: Selecting a target point on the target driving path whose distance from the position where the current pose is located is a preset distance threshold; Alternatively, calculating alternative points on the target driving path where the path deviation exceeds a preset angle threshold; calculating the moving distances between the position where the current pose is located and each alternative point; and determining the alternative point with the minimum moving distance as the target point.

6. The method according to claim 4, characterized in that, The process of constructing the preset detection area database further includes: Obtaining the installation position of the switch - type lidar on the target vehicle; Calculating the detectable areas corresponding to different installation positions of the switch - type lidar; Based on the intersection of the first area and the detectable area in each corner interval of the target vehicle when the switching laser radar is at different installation positions and the target vehicle moves in a circular motion to different detection distances, determine the detection area corresponding to the switching laser radar in each corner interval when the switching laser radar is at different installation positions and the target vehicle moves in a circular motion to different detection distances.

7. The method according to claim 6, characterized in that, The step of obtaining, from the preset detection area database, each first detection area corresponding to the switching laser radar in each corner interval when the target vehicle moves in a circular motion to the first distance includes: Obtain the current installation position of the switching laser radar on the target vehicle; Perform a pre-search in the preset detection area database based on the current installation position; Obtain, from the pre-search results, each first detection area corresponding to the switching laser radar in each corner interval when the target vehicle moves in a circular motion to the first distance.

8. A target detection device, characterized in that, The device includes: An acquisition module, configured to acquire the current pose and the target driving path of a target vehicle equipped with a switching laser radar; A first processing module, configured to select a target point on the target driving path to calculate the instantaneous center of motion of the target vehicle by using the target point and the current pose, where the target point and the current pose are located on a circle centered at the instantaneous center of motion, and the line connecting the position where the current pose is located and the instantaneous center of motion is perpendicular to the current orientation of the target vehicle; A second processing module, configured to calculate the central angle corresponding to the arc formed by the current pose and the target point on the circle; A third processing module, configured to determine the target detection area corresponding to the central angle for the switching laser radar; A fourth processing module, configured to perform target detection on the target detection area by using the switching laser radar to generate a target detection result.

9. An electronic device, characterized in that, Comprising: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the method according to any one of claims 1-7.

Images