Simulation-based Object Detection Method, Electronic Device and Storage Medium

Abstract

An embodiment of the present invention discloses a simulation-based target detection method, an electronic device, and a storage medium. The method is applied to a simulation model for detecting target objects based on lidar. The method includes: when a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model is detected, receiving a first type of ray sent by the target object in the scene simulation model; wherein the target object is within the visible range of the lidar in the target vehicle; determining a detection result of the target object according to the intersection data between the first type of ray and a second type of ray obtained in advance. In the embodiment of the present invention, the lidar receives the first type of ray sent by the target object in the scene simulation model and determines the detection result of the target object according to the intersection data between the first type of ray and the second type of ray, which can solve the problem of low scanning efficiency of the simulation lidar and improve the lidar simulation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle lidar simulation, and particularly to a simulation-based target detection method, an electronic device, and a storage medium. Background Art

[0002] Virtual simulation testing is a core part of accelerating the research and development process of autonomous driving and ensuring product safety. Virtual simulation testing is to complete the testing of autonomous driving algorithms by constructing a virtual scene, simulating vehicle dynamics and sensors. The input of the planning and control module in the autonomous driving algorithm is the target-level scene description. Therefore, only by completing the target-level simulation of the scene can the simulation testing of the planning and control module be completed. And lidar is an important sensor in the autonomous system. Therefore, completing the target detection simulation of lidar plays an important role in the function verification of the planning and control module in the autonomous driving algorithm.

[0003] Currently, there are mainly two lidar target detection simulation methods. One is not to simulate the scanning process of the lidar, that is, directly use the target ground truth in the virtual simulation scene. The advantage of this method is extremely high simulation efficiency, and the disadvantage is that it cannot solve the problem of occlusion culling. The other is to simulate the scanning process of the lidar, that is, in the virtual simulation scene, by calculating the intersection points of the lidar rays and three-dimensional objects to determine whether the target is scanned. This method has low simulation efficiency.

[0004] Disclosure

[0005] In view of this, the present invention provides a simulation-based target detection method, an electronic device, and a storage medium, which can solve the problem of low scanning efficiency of the simulated lidar and improve the lidar simulation efficiency.

[0006] According to one aspect of the present invention, an embodiment of the present invention provides a simulation-based target detection method, which is applied to a simulation model for detecting a target object based on lidar. Among them, the simulation model for detecting a target object based on lidar includes: a scene simulation model and a vehicle simulation model; the method includes:

[0007] When a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model is detected, receiving a first type of ray sent by the target object in the scene simulation model; wherein, the target object is within the visible range of the lidar in the target vehicle;

[0008] Determining the detection result of the target object according to the intersection point data between the first type of ray and the second type of ray obtained in advance.

[0009] According to another aspect of the present invention, an embodiment of the present invention further provides a simulation-based target detection device, which is applied to a simulation model for detecting a target object based on lidar. Among them, the simulation model for detecting a target object based on lidar includes: a scene simulation model and a vehicle simulation model; the device includes:

[0010] A first ray receiving module, configured to receive a first type of ray sent by a target object in the scene simulation model when detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model; wherein, the target object is within the visible range of the lidar in the target vehicle;

[0011] A detection result determination module, configured to determine a detection result of the target object according to intersection point data between the first type of ray and a second type of ray obtained in advance.

[0012] According to another aspect of the present invention, an embodiment of the present invention further provides an electronic device, the electronic device includes:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the simulation-based target detection method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the simulation-based target detection method according to any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention is to receive a first type of ray sent by a target object in the scene simulation model when detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model; wherein, the target object is within the visible range of the lidar in the target vehicle, and determine the detection result of the target object according to the intersection point data between the first type of ray and the second type of ray obtained in advance. In the embodiment of the present invention, the lidar receives the first type of ray sent by the target object in the scene simulation model and determines the detection result of the target object according to the intersection point data between the first type of ray and the second type of ray, which can solve the problem of low scanning efficiency of the simulation lidar and improve the lidar simulation efficiency.

[0018] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. Description of the Drawings

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 Flowchart of a simulation-based object detection method provided by an embodiment of the present invention;

[0021] Figure 2 Flowchart of another simulation-based object detection method provided by an embodiment of the present invention;

[0022] Figure 3 Flowchart of yet another simulation-based object detection method provided by an embodiment of the present invention;

[0023] Figure 4 Structural framework diagram of a simulation-based object detection model provided by an embodiment of the present invention;

[0024] Figure 5 Flowchart of a simulation-based object detection model provided by an embodiment of the present invention;

[0025] Figure 6 Flowchart of still another simulation-based object detection method provided by an embodiment of the present invention;

[0026] Figure 7 Structural block diagram of a simulation-based object detection device provided by an embodiment of the present invention;

[0027] Figure 8 Structural schematic diagram of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0028] To enable those skilled in the art to better understand the solutions of the present invention, the following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, rather than all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] It should be noted that terms such as "target" in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] In one embodiment, Figure 1 FIG. is a flowchart of a simulation-based target detection method provided by an embodiment of the present invention. This embodiment is applicable to the situation of simulating lidar target detection. This method can be executed by a simulation-based target detection device, which can be implemented in the form of hardware and / or software, and the simulation-based target detection device can be configured in an electronic device. The simulation-based target detection method is applied to a simulation model for detecting a target object based on a lidar. Among them, the simulation model for detecting a target object based on a lidar includes: a scene simulation model and a vehicle simulation model. As Figure 1 shown, the method includes:

[0031] S110. When a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model is detected, receive a first type of ray sent by the target object in the scene simulation model.

[0032] Among them, the target object is within the visible range of the lidar in the target vehicle.

[0033] Among them, the vehicle simulation model can be understood as a model for simulating a vehicle. The vehicle simulation model can simulate relevant position, speed information, angle information, etc. of the vehicle, and output the simulated information accordingly. The target vehicle movement instruction can be understood as relevant instruction information for the vehicle to travel, which can be an instruction for the target vehicle to move forward, an instruction for the target vehicle to reverse, or an instruction for the target vehicle to turn. This embodiment does not limit this here. The scene simulation model can be understood as a relevant model for scene simulation, which can include relevant scene models, traffic models, and pedestrian models in the current scene. Among them, the scene model can include green belts, trees, and signs, etc., the traffic model can include vehicles, various lines, and relevant signs, etc., and the pedestrian model can include various pedestrians.

[0034] In this embodiment, the target object can be understood as an object within the visible range of the lidar in the scene simulation model. It should be noted that the form of the target object is a three-dimensional model object, and the three-dimensional model is a polygonal representation of the object, which can be in the form of solid geometry, for example. All target objects have certain feature points, and the visible number of their key feature points is at least one. The target object movement instruction can be understood as a relevant instruction for the target object to move in the scene simulation model. For example, it can be a walking pedestrian, a moving vehicle, and various floating objects, etc. The first type of ray can be understood as a ray sent by each key feature point of the target object in the scene simulation model to the vehicle-mounted radar. It should be noted that each key feature point of the target object can correspond to a first type of ray, and at this time, it can be understood that the first type of ray of the target object is at least 1.

[0035] In this embodiment, the simulation model for detecting the target object based on the lidar can include a scene simulation model and a vehicle simulation model. In the case of detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model, the first type of ray sent by each key feature point of the target object in the scene simulation model to the vehicle-mounted lidar can be received. In this embodiment, the simulation model for detecting the target object based on the lidar performs corresponding simulations in units of steps. Among them, the step can be understood as within a preset time, for example, it can be 1 second or 3 seconds. This embodiment does not limit this here.

[0036] S120. Determine the detection result of the target object according to the intersection data between the first type of ray and the second type of ray obtained in advance.

[0037] Among them, the second type of ray can be understood as a ray sent by each feature key point of the reference object in the scene simulation model to the lidar in the target vehicle. Each key feature point of the reference object can correspond to a second type of ray. The reference object can be understood as an object other than the target object. It should be noted that the reference object is also within the visible range of the lidar in the target vehicle and is different from the target object. The reference object can be a dynamic object, such as a moving vehicle, or a static object, such as a stationary pedestrian, etc. The visible number of the feature points of the reference object needs to be at least one. The intersection data can be understood as the intersection data between the first type of ray sent by the target object and the second type of ray sent by the reference object, which can be the number of intersections between the first type of ray and the second type of ray, or the relevant characterization data indicating whether there is an intersection between the first type of ray and the second type of ray. This embodiment does not limit this here. The detection result can be understood as the detection result of the target object, and the detection result can be that the target object is detected successfully or that the target object is detected failed.

[0038] In this embodiment, based on the first type of rays sent by the target object to the vehicle-mounted lidar in the scenario simulation model and the second type of rays sent by the reference object to the vehicle-mounted lidar, the intersection data between the first type of rays and the pre-acquired second type of rays can be determined, and the detection result of the target object can be determined through the intersection data. Specifically, the first type of rays emitted by each key feature point of the target object and the second type of rays emitted by each key feature point of the reference object can be used to determine the number of intersections between the first type of rays and the second type of rays, and the detection result of the target object can be determined based on the number of intersections and the total number of the first type of rays.

[0039] The technical solution of the embodiment of the present invention is to receive the first type of rays sent by the target object in the scenario simulation model when a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scenario simulation model is detected; wherein, the target object is within the visible range of the lidar in the target vehicle, and the detection result of the target object is determined according to the intersection data between the first type of rays and the pre-acquired second type of rays. In the embodiment of the present invention, the lidar can receive the first type of rays sent by the target object in the scenario simulation model and determine the detection result of the target object according to the intersection data between the first type of rays and the second type of rays, which can solve the problem of low scanning efficiency of the simulation lidar and improve the lidar simulation efficiency.

[0040] In one embodiment, Figure 2 FIG. is a flowchart of another simulation-based target detection method provided by an embodiment of the present invention. On the basis of the above embodiments, the specific method of simulation-based target detection is further refined, as Figure 2 shown, the simulation-based target detection method in this embodiment may specifically include the following steps:

[0041] S210. Determine the visibility of the key feature points of each object within the visible range of the lidar.

[0042] Among them, the key feature points can be understood as the key feature points of each object within the visible range of the lidar. An object can have one or more key feature points, which can be determined according to relevant attribute information such as the size, position, and angle of the object within the visible range. Exemplarily, the number of key feature points of a tree is 16, and the number of key feature points of a vehicle is 10.

[0043] In this embodiment, according to the relevant physical parameters of the lidar, such as the scanning angle range of the lidar, the visibility of the key feature points of each object within the visible range that can be determined. Exemplarily, within the visible range of the lidar, there is a pedestrian and a vehicle. When the pedestrian is completely blocked by the vehicle, the key feature points of the pedestrian are all within the invisible range; when the pedestrian is partially blocked by the vehicle, some of the key feature points of the pedestrian are within the visible range and some are within the invisible range; when the pedestrian is not blocked by the vehicle at all, all the key feature points of the pedestrian are within the visible range.

[0044] S220. Determine the elimination situation of the object according to the visibility situation.

[0045] Among them, elimination can be understood as making corresponding identifications of the objects to identify the objects that need to be eliminated.

[0046] In this embodiment, according to the visibility of the key feature points of each object within the visible range of the lidar, the relevant elimination situation of the object can be determined. Specifically, when the key feature points of the object within the visible range are all invisible, it can be considered that the object is completely blocked at this time. For the completely blocked object, corresponding elimination can be carried out, such as making corresponding marks on the objects that are all invisible, storing all the objects that need to be eliminated together for elimination, or eliminating them individually. This embodiment does not make any restrictions here.

[0047] S230. Obtain the key feature points of each object in the scene simulation model.

[0048] In this embodiment, the key feature points of each object under each scene model, traffic model, and pedestrian model can be obtained from the scene simulation model, so as to store the mapping relationship between the key feature points and the corresponding objects in a preset storage space.

[0049] S240. Store the mapping relationship between the key feature points and the corresponding objects in a preset storage space.

[0050] Among them, the mapping relationship can be understood as the corresponding relationship between the key feature points of each object under the scene model, traffic model, and pedestrian model and the corresponding objects. This mapping relationship can map the key feature points to the corresponding objects. The preset storage space can be understood as the storage space pre-set in the lidar.

[0051] In this embodiment, by obtaining the key feature points of each object in the scene simulation model, the mapping relationship between the key feature points of each object and the corresponding objects can be stored in a preset storage space, so that the lidar can perform corresponding identifications.

[0052] S250. Receive the second type of rays sent by the reference object in the reception scenario simulation model; wherein, the reference object is within the visible range of the lidar in the target vehicle and is different from the target object.

[0053] Among them, the reference object can be understood as other objects except the target object within the visible range of the lidar. It can be understood that the reference object is within the visible range of the lidar in the target vehicle and is different from the target object. The reference object can be a dynamic object, such as a moving vehicle, or a static object, such as a stationary pedestrian, etc. The reference object also has certain key feature points, and the visible number of the key feature points needs to be at least one.

[0054] It should be noted that the reference object can also be used as the target object. That is, after determining its detection result based on the first type of rays drawn from the key feature points of the target object, the target object can be used as the reference object, and a random one can be selected from the reference objects as the target object, and the above method can be used to determine the detection result of the randomly selected target object from the reference objects until the detection of all reference objects is completed.

[0055] In this embodiment, the lidar can be used to receive the second type of rays sent by the reference object within the visible range of the lidar of the target vehicle in the scene simulation model, so as to determine the corresponding intersection data with the first type of rays sent by the target object in the scene simulation model.

[0056] S260. When detecting the movement instruction of the target vehicle in the vehicle simulation model and / or the movement instruction of the target object in the scene simulation model, receive the first type of rays sent by the target object in the scene simulation model.

[0057] S270. Determine the detection result of the target object according to the intersection data between the first type of rays and the second type of rays obtained in advance.

[0058] In this embodiment, the execution order of S230 and S240 has no precedence over the execution order of S250. S230 and S240 can be executed first and then S250; S250 can also be executed first and then S230 and S240; S230, S240, and S250 can also be executed simultaneously. This embodiment does not make any restrictions here.

[0059] In the above technical solution of this embodiment, by determining the visibility of the key feature points of each object within the visible range of the lidar and determining the elimination of the object according to the visibility, the problem of eliminating occluded objects is solved, ensuring the accuracy of object recognition; by obtaining the key feature points of each object in the scene simulation model and storing the mapping relationship between the key feature points and the corresponding objects in a preset storage space, in the case of detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model, receiving the first type of ray sent by the target object in the scene simulation model, and determining the detection result of the target object according to the intersection data between the first type of ray and the previously obtained second type of ray, further solving the problem of low scanning efficiency of the simulation lidar and improving the lidar simulation efficiency.

[0060] In one embodiment, Figure 3 As shown in the flowchart of another simulation-based target detection method provided by an embodiment of the present invention. On the basis of the above embodiments, this embodiment further refines receiving the first type of ray sent by the target object in the scene simulation model and determining the detection result of the target object according to the intersection data between the first type of ray and the previously obtained second type of ray, as Figure 3 shown. The simulation-based target detection method in this embodiment may specifically include the following steps:

[0061] S310. When detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model, receive the first type of ray sent by each key feature point of the target object in the scene simulation model.

[0062] In this embodiment, when detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model, receive the first type of ray sent by each key feature point of the target object in the scene simulation model to the lidar in the target vehicle, so as to determine the number of intersections between the first type of ray and the previously obtained second type of ray.

[0063] S320. Determine the number of intersections between the first type of ray and the previously obtained second type of ray.

[0064] In this embodiment, since each key feature point of the target object can correspond to a first type of ray, the number of the first type of rays of the target object can be determined by the key feature points of the target object; since each key feature point of the reference object can correspond to a second type of ray, the number of the second type of rays of the reference object can be determined by the key feature points of the reference object. Also, since each first type of ray emitted by each key feature point of the target object will intersect with each second type of ray emitted by each key feature point of the reference object, the maximum number of intersection points obtained at this time is the product of the first type of rays and the second type of rays.

[0065] It should be noted that when the number of intersection points between the first type of rays of the target object and the second type of rays of the pre-acquired reference object is zero, it can be considered that there is no intersection between the first type of rays of the target object and the second type of rays of the reference object; when the number of intersection points between the first type of rays of the target object and the second type of rays of the pre-acquired reference object is greater than zero, it can be considered that there is an intersection between the first type of rays of the target object and the second type of rays of the reference object. Through the existing intersection points between the first type of rays and the second type of rays of the reference object, the number of intersection points between the first type of rays and the second type of rays of the reference object can be determined.

[0066] S330. Determine the detection result of the target object according to the number of intersection points and the total number of the first type of rays.

[0067] Among them, the total number of the first type of rays can be determined by the key feature points of the target object, and the total number of the key feature points corresponding to the target object is the total number of the first type of rays. Exemplarily, if the number of key feature points corresponding to the target object is 8, it can be considered that the total number of the first type of rays is 8.

[0068] In this embodiment, the detection result of the target object can be determined based on the number of intersection points between the first type of rays and the second type of rays and the total number of the first type of rays. Specifically, the number of intersection points can be compared with the total number of the first type of rays correspondingly. When the number of intersection points is the same as the total number of the first type of rays, it is determined that the detection result of the target object is not successfully detected; when the number of intersection points is less than the total number of the first type of rays, it is determined that the detection result of the target object is successfully detected.

[0069] In one embodiment, determining the detection result of the target object according to the number of intersection points and the total number of the first type of rays includes:

[0070] When the number of intersection points is the same as the total number of the first type of rays, it is determined that the detection result of the target object is not successfully detected;

[0071] When the number of intersection points is less than the total number of the first type of rays, determine that the detection result of the target object is successful detection.

[0072] In this embodiment, when the number of intersection points between the first type of rays and the second type of rays is the same as the total number of the first type of rays, it can be determined that the detection result of the target object is unsuccessful detection; when the number of intersection points between the first type of rays and the second type of rays is less than the total number of the first type of rays, it can be determined that the detection result of the target object is successful detection. Exemplarily, when the number of intersection points between the first type of rays of the target object and the second type of rays of the pre-acquired reference object is 4, and at this time the total number of the first type of rays of the target object is also 4, it can be explained that the target object is completely blocked, and at this time, the target object can be marked for rejection; when the number of intersection points between the first type of rays of the target object and the second type of rays of the pre-acquired reference object is 6, and at this time the first type of rays of the target object is less than 6, it means that the target object can be detected.

[0073] In one embodiment, when the number of intersection points is the same as the total number of the first type of rays, it further includes:

[0074] Mark the target object for rejection.

[0075] In this embodiment, when the number of intersection points is the same as the total number of the first type of rays, it can be understood at this time that all the rays of the target object have intersection points with one or more other reference objects, that is, the target object is completely blocked by other reference objects, and the target object needs to be marked for rejection. This embodiment does not limit the way of marking for rejection. The way of rejection can store all the objects to be rejected together for rejection, or can be rejected individually. This embodiment does not limit this here.

[0076] In one embodiment, for better understanding of the target detection method based on simulation, Figure 4 This is a structural framework diagram of a target detection model based on simulation provided by an embodiment of the present invention. As Figure 4As shown in the figure, the structure of the simulation-based target detection model includes: a scene simulation model 420, a vehicle simulation model 410, and a radar model 430. Among them, the radar is an in-vehicle radar. The scene simulation model 420 includes a scene model, a traffic model, and a pedestrian model. The output of the scene simulation model 420 is the scene elements in the scene model. For example, it can be the corresponding positions, speeds, relevant feature points, and bounding boxes of various objects in the scene simulation model 420. Among them, the bounding box is an algorithm for solving the optimal bounding space of a discrete point set. The basic idea is to approximately replace complex geometric objects with geometric bodies that are slightly larger in volume and have simple characteristics. The vehicle simulation model 410 includes a vehicle model. The output of the vehicle simulation model 410 is information such as the position, speed, and angle of the vehicle. The output of the radar model 430 is relevant information such as the relevant positions and speeds of the targets in each scene model.

[0077] In this embodiment, after the vehicle position in the vehicle simulation model 410 is updated, it can simulate and output the position, angle, and speed of the vehicle. Since in the scene simulation model 420, each object has corresponding key feature points, when the vehicle moves one step, the scene elements of this step will also change and send the relevant scene element information to the radar model 430. Figure 5 The flowchart of a simulation-based target detection model provided by an embodiment of the present invention is as follows. The specific process is as follows:

[0078] a1. Simulate the vehicle for one step.

[0079] a2. Simulate the scene for one step.

[0080] a3. Simulate the radar for one step.

[0081] a4. Determine whether the simulation is over. If it is over, stop executing; if not, return to execute a1.

[0082] In one embodiment, Figure 6 The flowchart of another simulation-based target detection method provided by an embodiment of the present invention is as follows. The specific execution steps are as follows:

[0083] S610. Determine whether the target object is within the visible range of the in-vehicle radar. If so, execute S620; if not, re-determine the visible range.

[0084] S620. Determine whether the key feature points of each object within the visible range of the lidar are all invisible. If so, execute S630; if not, execute S640.

[0085] S630. Remove the marker.

[0086] S640. Receive the first type of rays sent by the target object in the reception scenario simulation model and find the intersection points with the second type of rays sent by the reference object in the reception scenario simulation model.

[0087] S650. Determine whether both the first type of rays and the second type of rays have intersection points. If so, execute S660; if not, execute S630.

[0088] S660. Target detection is successful.

[0089] In one embodiment, Figure 7 is a structural block diagram of a simulation-based target detection device provided by an embodiment of the present invention. This device is applicable to the situation of simulating lidar target detection and can be implemented by hardware / software. It can be configured in an electronic device to implement a simulation-based target detection method in an embodiment of the present invention. This device is applied to a simulation model for detecting a target object based on lidar. Among them, the simulation model for detecting a target object based on lidar includes: a scene simulation model and a vehicle simulation model; as Figure 7 shown, the device includes: a first ray receiving module 710 and a detection result determining module 720.

[0090] Among them, the first ray receiving module 710 is configured to receive the first type of rays sent by the target object in the scene simulation model when detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model; wherein, the target object is within the visible range of the lidar in the target vehicle;

[0091] The detection result determining module 720 is configured to determine the detection result of the target object according to the intersection point data between the first type of rays and the second type of rays obtained in advance.

[0092] In an embodiment of the present invention, through the first ray receiving module, when detecting a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model, the first ray receiving module receives the first type of rays sent by the target object in the scene simulation model; wherein, the target object is within the visible range of the lidar in the target vehicle. Through the detection result determining module, the detection result of the target object is determined according to the intersection point data between the first type of rays and the second type of rays obtained in advance, solving the problem of low scanning efficiency of the simulation lidar and improving the lidar simulation efficiency.

[0093] In one embodiment, the simulation-based target detection method further includes:

[0094] A key feature point acquisition module, configured to acquire the key feature points of each object in the scene simulation model;

[0095] A storage module for storing the mapping relationship between the key feature points and the corresponding objects in a preset storage space.

[0096] In one embodiment, the simulation-based target detection method further includes:

[0097] A visibility determination module for determining the visibility of the key feature points of each object within the visible range of the lidar before receiving the first type of ray sent by the target object in the scene simulation model;

[0098] An elimination situation determination module for determining the elimination situation of the object according to the visibility.

[0099] In one embodiment, the simulation-based target detection method further includes:

[0100] A second ray receiving module for receiving the second type of ray sent by the reference object in the scene simulation model; wherein, the reference object is within the visible range of the lidar in the target vehicle and is different from the target object.

[0101] In one embodiment, the first ray receiving module 710 includes:

[0102] A first ray receiving unit for the first type of ray sent by each key feature point of the target object in the scene simulation model.

[0103] In one embodiment, the detection result determination module 720 includes:

[0104] An intersection point determination unit for determining the number of intersection points between the first type of ray and the second type of ray obtained in advance;

[0105] A result determination unit for determining the detection result of the target object according to the number of intersection points and the total number of the first type of rays.

[0106] In one embodiment, the result determination unit includes:

[0107] A first detection result determination subunit for determining that the detection result of the target object is not successfully detected when the number of intersection points is the same as the total number of the first type of rays;

[0108] A second detection result determination subunit for determining that the detection result of the target object is successfully detected when the number of intersection points is less than the total number of the first type of rays.

[0109] In one embodiment, the first detection result determination subunit includes:

[0110] An elimination subunit, configured to perform an elimination marking on the target object when the number of intersections is the same as the total number of the first type of rays.

[0111] The simulation-based target detection device provided by an embodiment of the present invention can execute the simulation-based target detection method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution of the method.

[0112] In one embodiment, Figure 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, as Figure 8 shown, which shows a schematic structural diagram of an electronic device that can be used to implement the embodiments of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0113] As Figure 8 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0114] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the simulation-based object detection method.

[0116] In some embodiments, the simulation-based object detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the simulation-based object detection method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the simulation-based object detection method by any other suitable means (e.g., by means of firmware).

[0117] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processors of general-purpose computers, special-purpose computers, or other programmable data processing devices, such that when the computer programs are executed by the processors, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0121] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0122] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0123] It should be understood that various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0124] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A simulation-based object detection method, characterized in that, A simulation model applied to detecting a target object based on lidar, wherein the simulation model for detecting a target object based on lidar includes: a scene simulation model and a vehicle simulation model; the method includes: When a target vehicle movement instruction in the vehicle simulation model and / or a target object movement instruction in the scene simulation model is detected, receiving a first type of ray sent by the target object in the scene simulation model; wherein the target object is within the visible range of the lidar in the target vehicle; Determining a detection result of the target object according to intersection point data between the first type of ray and a second type of ray obtained in advance; the second type of ray is a ray sent by each feature key point of a reference object in the scene simulation model to the lidar in the target vehicle; Wherein, the determining the detection result of the target object according to the intersection point data between the first type of ray and the second type of ray obtained in advance includes: Determining the number of intersection points between the first type of ray and the second type of ray obtained in advance; Determining the detection result of the target object according to the number of intersection points and the total number of the first type of rays.

2. The method according to claim 1, characterized in that The method further includes: Obtaining key feature points of each object in the scene simulation model; Storing the mapping relationship between the key feature points and the corresponding objects into a preset storage space.

3. The method according to claim 1, wherein Before receiving the first type of ray sent by the target object in the scene simulation model, it further includes: Determining the visibility of the key feature points of each object within the visible range of the lidar; Determining the culling situation of the object according to the visibility.

4. The method according to claim 1, wherein The method further includes: Receiving a second type of ray sent by a reference object in the scene simulation model; wherein the reference object is within the visible range of the lidar in the target vehicle and is different from the target object.

5. The method according to claim 2, wherein The receiving the first type of ray sent by the target object in the scene simulation model includes: Receiving the first type of ray sent by each key feature point of the target object in the scene simulation model.

6. The method according to claim 1, wherein The determining the detection result of the target object according to the number of intersection points and the total number of the first type of rays includes: When the number of intersection points is the same as the total number of the first type of rays, determining that the detection result of the target object is unsuccessful detection; When the number of intersection points is less than the total number of the first type of rays, determining that the detection result of the target object is successful detection.

7. The method according to claim 6, wherein When the number of intersection points is the same as the total number of the first type of rays, it further includes: Performing a culling mark on the target object.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the simulation-based target detection method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the simulation-based object detection method according to any one of claims 1-7 when executed by a processor.

Images