Shadow area adjustment method, device, vehicle and readable storage medium
By acquiring and analyzing the lidar point cloud data, combining the driver's position information, and automatically adjusting the shadowed area, the problem of misalignment between obstacles and shadowed areas during vehicle driving is solved, and the accuracy and safety of driving decisions are improved.
Patent Information
- Application Number
- CN202310620189.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-29
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2043-05-29
Smart Images
Figure CN116645417B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle driving technology, and in particular to a shadow area adjustment method, device, vehicle and readable storage medium. Background Art
[0002] When a vehicle is driving, if there are obstacles such as pillars, other vehicles, or pedestrians nearby, the laser radar light will reach the background environment only after it reaches the edge of the obstacle, so a corresponding shadow area will be formed at this time, such as Figure 1 Generally, the closer the obstacle is to the vehicle, the larger the shadow area will become.
[0003] However, since the angle of the presented photo is inconsistent with that of the LiDAR, and the angle of the LiDAR is also inconsistent with that of the driver, there is an obvious "misalignment" phenomenon between the obstacles and the shadow areas in the presented point cloud, which will have a serious impact on the driver's driving decision. If it is a single obstacle, the above problem can be solved by adjusting the angle of the photo. However, in actual driving, most of the time there is more than one obstacle, and manually adjusting the angle of the photo by the driver will cause driving safety problems. Therefore, it is necessary to propose a method that can automatically adjust multiple obstacles and their shadow areas. Summary of the invention
[0004] In view of this, embodiments of the present application provide a shadow area adjustment method, device, vehicle, and readable storage medium.
[0005] In a first aspect, an embodiment of the present application provides a shadow area adjustment method, comprising:
[0006] Get the point cloud data sampled by the laser radar;
[0007] Determine a shadow area existing in a sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the existing shadow area;
[0008] If there is an obstacle, determine the obstacle area according to the point cloud data;
[0009] According to the position information of the driver, a point cloud map presented to the driver is obtained by combining the obstacle area and the shadow area.
[0010] In some embodiments, determining a shadow area in a sampling area based on the point cloud data, and determining whether there is an obstacle in the sampling area according to the shadow area, comprises:
[0011] Compare the currently acquired point cloud data with the previous point cloud data to determine whether there is a shadow area in the sampling area;
[0012] When it exists, if the shadow area satisfies the first constraint condition, and the point cloud data currently corresponding to the shadow area and the point cloud data corresponding to the previous shadow area satisfy the second constraint condition, it is confirmed that there is an obstacle in the sampling area.
[0013] In some embodiments, the first constraint condition includes: the area of the shadow region is not less than a preset area threshold, and / or the duration of the shadow region is not less than a preset time threshold.
[0014] In some embodiments, the second constraint condition includes: a distance between point cloud data currently corresponding to the shadow area and point cloud data previously corresponding to the shadow area is not less than a preset distance threshold.
[0015] In some embodiments, comparing the currently acquired point cloud data with the previous point cloud data to determine whether there is a shadow area in the sampling area includes:
[0016] The currently acquired point cloud data is compared with the point cloud data at any time within the previously preset time period. If a point cloud can be sampled at the same sampling position at the previous moment but cannot be sampled at the next moment, the area where the sampling position is located is determined to be a shadow area.
[0017] In some embodiments, the step of obtaining a point cloud map presented to the driver based on the driver's position information and combining the obstacle area and the shadow area includes:
[0018] Based on the position information of the driver, relative position information between the driver and the obstacle area is obtained, wherein the relative position information includes a relative position and a deviation angle;
[0019] Based on the relative position information, the shadow area is adjusted to be centered on the driver and projected toward the rear area of the obstacle area;
[0020] A point cloud image including the adjusted shadow area is presented to the driver.
[0021] In some embodiments, presenting the point cloud image formed by the adjusted shadow area to the driver includes:
[0022] According to the adjusted shadow area, extracting the closest point cloud data having the same position as the point cloud data existing in the adjusted shadow area from the historical point cloud data;
[0023] The adjusted shadow area is filled with the closest point cloud data, and a point cloud image including the adjusted shadow area filled with the point cloud data is presented to the driver.
[0024] In a second aspect, an embodiment of the present application further provides a shadow area adjustment device, comprising:
[0025] The acquisition module is used to obtain the point cloud data sampled by the laser radar;
[0026] A perception module, used to determine a shadow area existing in a sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the existing shadow area;
[0027] A determination module, used to determine the obstacle area according to the point cloud data if there is an obstacle;
[0028] The adjustment module is used to obtain a point cloud map presented to the driver based on the driver's position information in combination with the obstacle area and the shadow area.
[0029] In a third aspect, an embodiment of the present application further provides a vehicle, comprising a laser radar, a processor and a memory, wherein the laser radar is used to collect point cloud data of the space where the vehicle is located, the memory stores a computer program, and the processor is used to execute the computer program to implement the shadow area adjustment method described in the right.
[0030] In a fourth aspect, an embodiment of the present application further provides a readable storage medium storing a computer program, which implements the shadow area adjustment method when executed on a processor.
[0031] The embodiments of the present application have the following beneficial effects:
[0032] The shadow area adjustment method of the present application obtains the point cloud data collected by the laser radar, and determines whether there is a shadow area in the sampling area, and then determines whether there is an obstacle in the sampling area. If there is an obstacle, the obstacle area is determined according to the point cloud data; according to the driver's position information, the obstacle area and the shadow area are combined to obtain a point cloud map presented to the driver. By automatically adjusting the shadow area, the obvious "misalignment" phenomenon between the obstacle and the shadow area in the point cloud map presented to the driver can be effectively solved, thereby avoiding the serious impact of the shadow area on driving decisions, improving decision accuracy and driving safety, etc. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0034] Figure 1 A schematic diagram showing the shadow area formed;
[0035] Figure 2 A schematic diagram showing that the shadow area of an embodiment of the present application is obviously misaligned;
[0036] Figure 3 A first flow chart of the shadow area adjustment method according to an embodiment of the present application is shown;
[0037] Figure 4 A schematic diagram showing that the shadow area of an embodiment of the present application does not need to be adjusted;
[0038] Figure 5 A second flow chart of the shadow area adjustment method according to an embodiment of the present application is shown;
[0039] Figure 6 A schematic diagram showing an embodiment of the present application after the shadow area is adjusted;
[0040] Figure 7 A schematic structural diagram of a shadow area adjustment device according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.
[0042] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0043] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.
[0044] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.
[0045] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0046] For the convenience of understanding, the background technology is now described in detail.
[0047] In the field of intelligent driving, when a vehicle equipped with a laser radar is driving, if there are obstacles such as pillars, other vehicles, pedestrians, etc. near the vehicle, the laser radar light will be blocked by the obstacles during the projection process, forming a shadow area (such as Figure 1 In addition, since the laser radar light will not reach the background environment until it scans the edge of the obstacle, the boundary of the corresponding shadow area will be formed at this time. Generally, the closer the obstacle is to the vehicle, the larger the shadow area will become.
[0048] However, relative to the obstacle, since the angle at which the LiDAR projects to the obstacle is different from the angle at which the driver looks at the obstacle, and the 3D point cloud data is displayed on the screen, there is an obvious "misalignment" between the obstacle and the shadow area in the presented point cloud (e.g. Figure 2 ). The above-mentioned “misalignment” phenomenon is inconsistent with the situation where the driver looks at the obstacle, which will have a serious impact on the driver’s driving decision. If it is a single obstacle, the driver can adjust the display angle of the point cloud map on the screen so that the angle presented in the point cloud map is consistent with the angle at which the driver looks at the obstacle, thereby solving the above problem. However, in actual driving, most of the time there is more than one obstacle in the scanning area of the lidar, and there are driving safety issues when the driver adjusts the angle of the photo. It is understandable that if the driver makes decisions such as obstacle avoidance based on the point cloud image, misjudgment problems will often occur, which can also cause more serious impacts on people or vehicles.
[0049] Based on this, this embodiment proposes a shadow area adjustment method, which combines the point cloud data collected by the laser radar to judge the obstacle situation during the vehicle driving process, and when it is judged that there is an obstacle, the driver's position information and obstacle information are combined to automatically adjust the shadow area corresponding to the obstacle, so that there is no misalignment between the shadow area and the obstacle in the visual point cloud image presented to the driver. In other words, it is to emit rays from the driver's perspective and project them onto the obstacle, so that the formed shadow area will not have obvious position offset, thereby providing a more accurate basis for the driver's driving decision, that is, improving the decision accuracy; at the same time, since the entire process can be automatically adjusted without the need for manual operation by the driver, driving safety can be guaranteed.
[0050] The laser radar in this embodiment is not limited to a specific type, and can be a mechanical laser radar, a hybrid solid-state laser radar or other types of laser radar. Among them, the mechanical laser radar mainly changes the light path by rotating the transceiver module and projects it to the target area. The hybrid solid-state laser radar mainly changes the light path by rotating the scanning module (MEMS galvanometer or prism) and projects it to the target area.
[0051] The shadow area adjustment method is described in detail below with reference to specific embodiments.
[0052] Please refer to Figure 3 , exemplary, the shadow area adjustment method includes steps S110 to S140:
[0053] S110, obtaining point cloud data sampled by the laser radar.
[0054] Exemplarily, by installing a laser radar on a vehicle, spatial point cloud data can be collected in real time during the vehicle's driving process, and then the vehicle's control system can perform corresponding processing based on the point cloud data acquired in real time, thereby improving the safety of the driver or the autonomous driving process.
[0055] Generally, the laser radar can perform cloud point sampling in the entire field of view area (i.e., sampling area) that it can scan according to a set sampling frequency. For example, the sampling area may include the road area where the vehicle is traveling and the surrounding area other than the road area.
[0056] S120, determining a shadow area existing in a sampling area based on the point cloud data, and determining whether there is an obstacle in the sampling area according to the existing shadow area.
[0057] The shadow area is mainly formed because the light emitted by the laser radar is projected onto the obstacle and blocked by the obstacle. Only the light projected onto the edge of the obstacle will further reach the background environment of the obstacle to form the boundary of the shadow area. Therefore, the blocked areas will form corresponding shadow areas. In this embodiment, it is first determined whether there is a shadow area, and then it is determined whether there is an obstacle that needs to be adjusted in the shadow area.
[0058] Exemplarily, the currently acquired point cloud data is compared with the point cloud data at any time within the previously preset time period to determine whether there is a shadow area in the sampling area. For example, the currently acquired point cloud data can be compared with the point cloud data of any second in the previous few seconds, and preferably, the point cloud data of the previous second can be selected for comparison; if there is a point cloud that can be sampled at the same sampling position at the previous moment but cannot be sampled at the next moment, the area where the sampling position is located can be defined as a shadow area. It can be understood that the number of shadow areas here may be one or more, depending on the vehicle environment at the time.
[0059] Furthermore, if there is a shadow area, it is further determined whether there is an obstacle in the sampling area. Specifically, if the shadow area satisfies the first constraint condition, and the point cloud data currently corresponding to the shadow area and the point cloud data corresponding to the previous shadow area satisfy the second constraint condition, it is confirmed that there is an obstacle in the sampling area.
[0060] The first constraint condition may be a constraint on the range and / or duration of the shadow area. For example, the first constraint condition may be: the area of the shadow area is not less than a preset area threshold, that is, only when it is determined that the area of the shadow area meets a certain area size, further processing will be performed. On the contrary, if the shadow area is too small, no corresponding processing may be performed.
[0061] For ease of understanding, an example is given. Assumption 1: There is a tree that is less than 3 meters away from the vehicle. Since the distance between the tree and the vehicle is relatively close, a large shadow area will be formed due to the tree. Therefore, this tree should be regarded as an obstacle. Assumption 2: There is a tree that is more than 100 meters away from the vehicle. Since the distance between the tree and the vehicle is relatively far, a large shadow area will not be formed. There is no need to regard this tree as an obstacle, and it can be temporarily regarded as a background environment. It should be noted that the advantage of judging obstacles by the size of the shadow area rather than point cloud clustering recognition is that the obstacles obtained by point cloud clustering recognition do not necessarily affect driving (such as large trees and billboards at a distance). The size of the shadow area can more realistically reflect which obstacles are more worthy of the driver's attention for current driving. Secondly, since the vehicle is constantly driving, the current obstacle recognition is only for the current point cloud image. That is, based on the continuous driving of the vehicle, the qualitative judgment of the obstacle will also change continuously. The above judgment is a judgment process that may be constantly changing. It is understandable that the preset area threshold can be obtained by an algorithm based on various input parameters (such as speed, driving environment, vehicle model, etc.), or it can be determined based on the driver's subjective judgment, and no specific limitation is made here.
[0062] For another example, the first constraint condition may also be: the duration of the shadow area is not less than a preset time threshold. It is understandable that if the shadow area appears for too short a time, for example, for some road signs / billboards erected in the air or on the roadside, then such shadow areas may not be processed accordingly.
[0063] For ease of understanding, an example is given below. Assume a scenario: There is a large billboard on the roadside in front of the vehicle. Since the billboard itself is on the roadside, it is only at the edge of the point cloud image. Although the billboard will cause the shadow area to appear, as the vehicle moves forward, the billboard continues to retreat relative to the vehicle. The billboard will soon no longer be in the sampling area of the lidar, and there will be no problem of the billboard causing the shadow area. Therefore, by monitoring the duration of the shadow area, the impact of the above-mentioned items / areas on the vehicle can be evaluated. In the example, if the shadow area lasts for a short time, it can be considered that there is no obstacle such as a "billboard" in the sampling area. It is understandable that the preset time threshold can be obtained by the algorithm based on various input parameters (such as speed, driving environment, vehicle model, etc.), or it can be determined based on the driver's subjective judgment, and no specific limitation is made here.
[0064] As an optional manner, the first constraint condition may also be that both the size of the shadow area and the duration cannot be too short are satisfied, so as to determine the shadow area that meets the condition.
[0065] Therefore, after determining the target shadow area, it is necessary to further determine whether the obstacles corresponding to these shadow areas are misaligned. In this embodiment, the distance between the obstacle and the background environment can be used to determine.
[0066] For example, the second constraint condition may include: the distance between the point cloud data currently corresponding to the shadow area and the point cloud data corresponding to the previous shadow area is not less than a preset distance threshold, that is, the distance between the obstacle and the background environment is not too small, as mentioned above Figure 2 As shown in . It can be understood that if the distance between the obstacle and the background environment is very short, for example, the shadow area is only slightly larger than the obstacle, it seems as if there is an extra edge, such as Figure 4 As shown, it basically does not affect the driver's judgment of obstacles, so there is no need to make adjustments.
[0067] For ease of understanding, an example is given below. Assume a scenario: There are trees less than 1 meter away from the background wall (background environment), because the distance between the trees and the background wall is short. The longer the distance between the obstacle and the background environment, the larger the area of the shadow area; the shorter the distance between the obstacle and the background environment, the smaller the area of the shadow area. Therefore, when the distance between the tree and the background wall is shorter, the shadow area corresponding to the tree is also smaller. Even if there is a "misalignment" phenomenon, the offset of the "misalignment" will be within a smaller range, and the impact on the driver is lower. Therefore, the shadow area formed by this tree does not need to be adjusted. It is understandable that the preset distance threshold can be obtained by the algorithm based on various input parameters (such as speed, driving environment, vehicle model, etc.), or it can be determined based on the driver's subjective judgment, and no specific limitation is made here.
[0068] It can be understood that the scanning frequency of the laser radar used in current intelligent driving is generally not less than 1FPS (that is, no less than 1 frame of point cloud image is generated per second). In each frame of the point cloud image, the shadow area of the obstacle needs to be analyzed and adjusted according to the analysis results. If the shadow areas of all obstacles in each frame of the point cloud image are adjusted, it will impose a high burden on the intelligent driving system of the car, reduce the refresh rate of the point cloud image on the screen, and even some point cloud images may be lost. In intelligent driving, from a safety perspective, there are very high practical requirements for the refresh rate of the point cloud image, and the loss of the point cloud image needs to be avoided as much as possible. Therefore, for the point cloud image of the current frame, if there is an obstacle that does not temporarily have an adverse effect on the driver's decision, its shadow image can be adjusted. The above measures can effectively reduce the burden on the system, thereby effectively ensuring the refresh rate of the point cloud image on the screen, preventing the loss of the point cloud image, and avoiding the driver from making bad decisions.
[0069] S130: If an obstacle exists, determine the obstacle area according to the point cloud data.
[0070] Exemplarily, after determining the existence of a target obstacle, the area where the obstacle is located can be obtained according to the acquired point cloud data. The obstacle can be one or more, and correspondingly, the obstacle area can also be one or more corresponding areas.
[0071] It can be understood that the shadow area is formed because the light emitted by the laser radar is blocked by obstacles. The boundary of the shadow area is generated when the laser radar light scans the edge of the obstacle and reaches the background environment. Therefore, the vehicle's control system itself can know the area where the obstacle is located, but in the assisted driving process, the intelligent driving system only plays an auxiliary role to the driver, and the driver has the highest authority over driving decisions. Therefore, the geographic information that the driver can obtain based on the laser radar is limited to the point cloud image presented on the screen, and the driver himself cannot directly perceive all the point cloud data. This embodiment does not solve the problem that the system cannot perceive obstacles, but the driver's decision-making is affected by the visual misalignment caused by angle differences.
[0072] S140, obtaining a point cloud map presented to the driver based on the driver's position information and in combination with the obstacle area and the shadow area.
[0073] Exemplarily, after the position information of the obstacle area is determined, it is necessary to further determine the relative position and angle information between the obstacle and the driver, so as to adjust the projection of the subsequent shadow area.
[0074] In one embodiment, if Figure 5 As shown, step S140 includes:
[0075] S141, based on the position information of the driver, obtaining relative posture information between the driver and the obstacle area, wherein the relative posture information includes a relative position and a deviation angle.
[0076] Usually, the driver's position is usually fixed during driving, and the position of the lidar is also fixed. Therefore, after the position of the obstacle area is known, the relative posture information between the driver and the obstacle can be calculated based on the relative posture information between the lidar and the driver's seat through posture matrix conversion, etc.
[0077] S142: Based on the relative position information, the shadow area is adjusted to be centered on the driver and projected toward the rear area of the obstacle area.
[0078] It can be understood that the above relative posture information includes the relative position (distance) between the driver and the obstacle area and the deviation angle in visual observation. Therefore, after obtaining the relative posture information, the shadow area corresponding to the obstacle can be adjusted so that the shadow area, obstacle, and driver in the visual image presented to the driver are a straight line, that is, the shadow area is adjusted to the shadow area caused by the ray projected from the driver's perspective onto the obstacle, such as Figure 6 shown.
[0079] S143: presenting a point cloud image including the adjusted shadow area to the driver.
[0080] In one embodiment, when constructing the above-mentioned point cloud map, the closest point cloud data having the same position as the point cloud data existing in the adjusted shadow area can be extracted from the historical point cloud data based on the adjusted shadow area; then, the adjusted shadow area is filled with the extracted closest point cloud data, and the point cloud map including the point cloud data filled in the adjusted shadow area is presented to the driver.
[0081] It can be understood that after extracting relevant point cloud data from historical point cloud data and supplementing it into the shadow area, the above-mentioned shadow area can effectively avoid misjudgment of the driver.
[0082] The shadow area adjustment method of this embodiment determines whether there is a shadow area in the sampling area by obtaining the point cloud data collected by the laser radar, and then determines whether there is an obstacle in the sampling area. If there is an obstacle, the obstacle area is determined according to the point cloud data; according to the driver's position information, the obstacle area and the shadow area are combined to obtain a point cloud map presented to the driver. By automatically adjusting the shadow area, the obvious "misalignment" phenomenon between the obstacle and the shadow area in the point cloud map presented to the driver can be effectively solved, thereby avoiding the serious impact of the shadow area on driving decisions, improving decision accuracy and driving safety, etc.
[0083] Please refer to Figure 7 Based on the method of the above embodiment, this embodiment proposes a shadow area adjustment device 100. Exemplarily, the shadow area adjustment device 100 includes:
[0084] An acquisition module 110 is used to acquire point cloud data sampled by a laser radar;
[0085] A perception module 120, configured to determine a shadow area existing in a sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the existing shadow area;
[0086] A determination module 130, for determining an obstacle area according to the point cloud data if an obstacle exists;
[0087] The adjustment module 140 is used to obtain a point cloud map presented to the driver based on the driver's position information in combination with the obstacle area and the shadow area.
[0088] Furthermore, the perception module 120 is used to determine a shadow area in the sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the shadow area, including:
[0089] The currently acquired point cloud data is compared with the previous point cloud data to determine whether there is a shadow area in the sampling area; if there is, if the shadow area satisfies the first constraint condition, and the point cloud data currently corresponding to the shadow area and the point cloud data corresponding to the previous shadow area satisfy the second constraint condition, it is confirmed that there is an obstacle in the sampling area.
[0090] The first constraint condition includes: the area of the shadow area is not less than a preset area threshold, and / or the duration of the shadow area is not less than a preset time threshold.
[0091] The second constraint condition includes: the distance between the point cloud data currently corresponding to the shadow area and the point cloud data previously corresponding to the shadow area is not less than a preset distance threshold.
[0092] Furthermore, the adjustment module 140 is used to obtain a point cloud map presented to the driver based on the driver's position information, in combination with the obstacle area and the shadow area, including:
[0093] Based on the position information of the driver, relative posture information between the driver and the obstacle area is obtained, and the relative posture information includes a relative position and a deviation angle; based on the relative posture information, the shadow area is adjusted to be centered on the driver and projected toward the rear area of the obstacle area; and a point cloud image including the adjusted shadow area is presented to the driver.
[0094] In some embodiments, the point cloud map formed by the adjusted shadow area is presented to the driver, including: according to the adjusted shadow area, extracting the closest point cloud data having the same position as the point cloud data existing in the adjusted shadow area from the historical point cloud data; filling the adjusted shadow area with the closest point cloud data, and presenting the point cloud map including the point cloud data filled in the adjusted shadow area to the driver.
[0095] It can be understood that the device of this embodiment corresponds to the method of the above embodiment, and the options of the steps and methods in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.
[0096] The present application also provides a vehicle, which exemplarily includes a laser radar, a processor and a memory, wherein the laser radar is used to collect point cloud data of the space where the vehicle is located, the memory stores a computer program, and the processor runs the computer program to enable the vehicle device to execute the above-mentioned shadow area adjustment method or the functions of each module in the above-mentioned laser radar adjustment device.
[0097] The present application also provides a readable storage medium for storing the computer program used in the above-mentioned vehicle.
[0098] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0099] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0100] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.
[0101] It should be noted that the embodiments of the present application may involve the collection and use of the geographical environment. In actual applications, the collected data of the geographical environment can be used in the scheme described in this article within the scope permitted by applicable laws and regulations in accordance with the applicable laws and regulations of the country where the application is located (for example, obtaining permission from government departments, etc.).
[0102] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A shadow area adjustment method, characterized in that: include: Get the point cloud data sampled by the laser radar; Determine a shadow area existing in a sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the existing shadow area; If there is an obstacle, determine the obstacle area according to the point cloud data; Based on the position information of the driver, relative position information between the driver and the obstacle area is obtained, wherein the relative position information includes a relative position and a deviation angle; Based on the relative position information, the shadow area is adjusted to be centered on the driver and projected toward the rear area of the obstacle area; presenting a point cloud image including the adjusted shadow area to the driver; The presenting of the point cloud image formed by the adjusted shadow area to the driver includes: According to the adjusted shadow area, extracting the closest point cloud data having the same position as the point cloud data existing in the adjusted shadow area from the historical point cloud data; The adjusted shadow area is filled with the closest point cloud data, and a point cloud image including the adjusted shadow area filled with the point cloud data is presented to the driver.
2. The shadow area adjustment method according to claim 1, characterized in that: The determining of a shadow area in a sampling area based on the point cloud data, and determining whether there is an obstacle in the sampling area according to the shadow area, comprises: Compare the currently acquired point cloud data with the previous point cloud data to determine whether there is a shadow area in the sampling area; When it exists, if the shadow area satisfies the first constraint condition, and the point cloud data currently corresponding to the shadow area and the point cloud data corresponding to the previous shadow area satisfy the second constraint condition, it is confirmed that there is an obstacle in the sampling area.
3. The shadow area adjustment method according to claim 2, characterized in that: The first constraint condition includes: the area of the shadow region is not less than a preset area threshold, and / or the duration of the shadow region is not less than a preset time threshold.
4. The shadow area adjustment method according to claim 2, characterized in that: The second constraint condition includes: a distance between point cloud data currently corresponding to the shadow area and point cloud data previously corresponding to the shadow area is not less than a preset distance threshold.
5. The shadow area adjustment method according to claim 2, characterized in that: The step of comparing the currently acquired point cloud data with the previous point cloud data to determine whether there is a shadow area in the sampling area includes: The currently acquired point cloud data is compared with the point cloud data at any time within the previously preset time period. If a point cloud can be sampled at the same sampling position at the previous moment but cannot be sampled at the next moment, the area where the sampling position is located is determined to be a shadow area.
6. A shadow area adjustment device, characterized in that: include: The acquisition module is used to obtain the point cloud data sampled by the laser radar; A perception module, used to determine a shadow area existing in a sampling area based on the point cloud data, and determine whether there is an obstacle in the sampling area according to the existing shadow area; A determination module, used to determine the obstacle area according to the point cloud data if there is an obstacle; an adjustment module, configured to obtain relative posture information between the driver and the obstacle area based on the position information of the driver, wherein the relative posture information includes a relative position and a deviation angle; based on the relative posture information, adjust the shadow area to an area centered on the driver and projected toward the rear of the obstacle area; and present a point cloud image including the adjusted shadow area to the driver; The presenting of the point cloud image formed by the adjusted shadow area to the driver includes: According to the adjusted shadow area, extracting the closest point cloud data having the same position as the point cloud data existing in the adjusted shadow area from the historical point cloud data; The adjusted shadow area is filled with the closest point cloud data, and a point cloud image including the adjusted shadow area filled with the point cloud data is presented to the driver.
7. A vehicle, characterized in that: The vehicle includes a laser radar, a processor and a memory, the laser radar is used to collect point cloud data of the space where the vehicle is located, the memory stores a computer program, and the processor is used to execute the computer program to implement the shadow area adjustment method described in any one of claims 1-5.
8. A readable storage medium, characterized in that: The device stores a computer program, which, when executed on a processor, implements the shadow area adjustment method according to any one of claims 1 to 5.