Target processing method based on laser radar, storage medium and electronic equipment

Abstract

The invention discloses a target processing method based on a laser radar, a storage medium and electronic equipment, and the method comprises the steps: carrying out the data collection of a direction in which a radar window of the laser radar is located through the laser radar, and obtaining the point cloud data of a target frame; target detection is carried out based on the target frame point cloud data, a target object area is obtained, the target object area is a position area of a target object on the radar window, and the target object is an object to be cleaned on the radar window; and cleaning the target object area to clean the target object. According to the invention, the cleaning efficiency of the laser radar can be improved.

Description

Technical Field

[0001] This application relates to the technical field of lidar, and in particular, to a target processing method, a storage medium, and an electronic device based on lidar. Background Art

[0002] When there are pollutants on the radar window of the lidar, the pollutants will seriously affect the point cloud effect and the accuracy of ranging. Therefore, it is necessary to clean the radar window to solve the pollutant problem. Currently, the way to clean the radar window is to clean the entire radar window. However, the way of cleaning the entire radar window has the problem of low cleaning efficiency. Summary of the Invention

[0003] Embodiments of this application provide a target processing method, a storage medium, and an electronic device based on lidar to at least solve the problem that the cleaning efficiency of the radar window is low due to cleaning the entire radar window in the related art of the target processing method based on lidar.

[0004] According to one aspect of the embodiments of this application, a target processing method based on lidar is provided, including: collecting data on the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data; performing target detection based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window; cleaning the target object area to clean the target object.

[0005] As an optional solution, the collecting data on the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data includes: when the preset detection mode of the lidar is the first detection mode and the lidar is in the first pose, collecting data on the direction where the radar window is located through the lidar to obtain the first frame of point cloud data; after the pose of the lidar changes from the first pose to the second pose, collecting data on the direction where the radar window is located through the lidar to obtain the second frame of point cloud data; where the target frame point cloud data includes the first frame of point cloud data and the second frame of point cloud data.

[0006] As an alternative solution, performing object detection based on the target frame point cloud data to obtain a target object area includes: performing object detection on the first frame point cloud data to obtain first position information of a reference object, where the first position information is used to represent a first position area where the reference object is located; performing object detection on the second frame point cloud data to obtain second position information of the reference object, where the second position information of the reference object is used to represent a second position area where the reference object is located; performing coordinate transformation on the first position area according to a pose transformation amount between the first pose and the second pose to obtain a predicted position area, where the predicted position area is a predicted position area where the reference object is located when the lidar is in the second pose; in a case where the second position area is inconsistent with the predicted position area, determining the target object area based on the second position area and the predicted position area.

[0007] As an alternative solution, the first position area, the second position area, and the predicted position area are all position areas of the reference object on the radar window: in a case where the second position area is inconsistent with the predicted position area, determining the target object area based on the second position area and the predicted position area includes: in a case where the second position area is inconsistent with the predicted position area, determining a non-overlapping area between the second position area and the predicted position area as the target object area.

[0008] As an alternative solution, the lidar is an optical phased array OPA lidar; after determining the target object area based on the second position area and the predicted position area, the method further includes: performing edge contour detection on the target object area through the OPA lidar to obtain a contour detection result, where the contour detection result is used to represent an object contour of the target object; updating the target object area to an area identified by the object contour of the target object to obtain the updated target object area.

[0009] As an alternative solution, after collecting data in the direction where the radar window is located through the lidar, the method further includes: detecting a set of device parameters of the target device where the lidar is located in real time through an inertial measurement unit, where the set of device parameters includes at least one of the following: attitude, heading angle, speed; in a case where it is determined that the target device has moved and / or its angle has deflected based on the set of device parameters of the target device, determining that the pose of the lidar has changed from the first pose to the second pose.

[0010] As an alternative solution, after the lidar collects data in the direction where the radar window is located, the method further includes: controlling the lidar to perform a pose transformation by a control component to change the pose of the lidar from the first pose to the second pose.

[0011] As an alternative solution, the performing target detection based on the target frame point cloud data to obtain a target object area includes: when the preset detection mode of the lidar is the second detection mode, extracting point cloud data matching the window distance from the target frame point cloud data based on the window distance of the radar window to obtain window point cloud data, and performing target detection on the window point cloud data to obtain the target object area; where the window distance is the distance between the lidar and the radar window, and the window distance is determined based on extracting the window distance information of the radar window from the configuration information of the lidar.

[0012] According to another aspect of the embodiments of the present application, there is provided a target processing device based on a lidar, including: an acquisition unit, configured to collect data in the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data; a detection unit, configured to perform target detection based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of a target object on the radar window, and the target object is an object to be cleaned on the radar window; a cleaning unit, configured to clean the target object area to clean the target object.

[0013] According to still another aspect of the embodiments of the present application, there is provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it executes the steps in any one of the above method embodiments.

[0014] According to still another aspect of the embodiments of the present application, there is provided an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute the steps in any one of the above method embodiments through the computer program.

[0015] In the embodiments of the present application, data is collected in the direction where the radar window of the lidar itself is located through the lidar to obtain target frame point cloud data; target detection is performed based on the target frame point cloud data to determine the target object area where the object to be cleaned on the radar window is located, so as to only clean the target object area to clean the target object, improving the cleaning efficiency of the radar window, and further solving the problem that the cleaning efficiency of the radar window is low due to cleaning the entire radar window in the related art's target processing method based on a lidar. Description of the Drawings

[0016] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0018] Figure 1 is a schematic flowchart of an optional lidar-based target processing method according to an embodiment of this application;

[0019] Figure 2 is a schematic diagram of the target frame point cloud of an optional lidar-based target processing method according to an embodiment of this application;

[0020] Figure 3 is a schematic diagram of the target frame point cloud of another optional lidar-based target processing method according to an embodiment of this application;

[0021] Figure 4 is a schematic diagram of the target frame point cloud of yet another optional lidar-based target processing method according to an embodiment of this application;

[0022] Figure 5 is a schematic structural diagram of an optional lidar-based target processing device according to an embodiment of this application;

[0023] Figure 6 is a schematic flowchart of another optional lidar-based target processing method according to an embodiment of this application;

[0024] Figure 7 is a schematic block diagram of the structure of an optional lidar-based target processing device according to an embodiment of this application;

[0025] Figure 8 is a schematic block diagram of the computer system of an optional electronic device according to an embodiment of this application. Detailed implementation manners

[0026] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes 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 that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0028] When there are pollutants on the lidar window, it will seriously affect the point cloud effect and the accuracy of ranging. At present, in the related art, most lidars use the overall cleaning method to solve the problem of pollutants on the lidar window. However, the method of overall cleaning the lidar window cannot finely perceive the position and shape of the pollutants, resulting in low cleaning efficiency.

[0029] To solve at least part of the above problems, the embodiments of this application collect data on the lidar window through the lidar to obtain target frame point cloud data, and then perform target detection based on the target frame point cloud data to determine the target object area with pollutants or dirt, so as to perform targeted cleaning on the target object area, improving the cleaning efficiency of the lidar window.

[0030] The embodiments of this application provide a target processing method, a storage medium, and an electronic device based on lidar, which can improve the cleaning efficiency of the lidar window. The following describes an exemplary application of the electronic device provided by the embodiments of this application. Optionally, the above-mentioned target processing method based on lidar can be executed independently by a processing device (for example, a terminal or a server), or jointly executed by the lidar and the processing device, or executed by other devices other than the lidar and the processing device.

[0031] As an optional implementation manner, take the lidar executing the target processing method based on lidar in this embodiment as an example. As Figure 1As shown, the process of the above lidar-based target processing method may include the following steps.

[0032] In step S102, data is collected in the direction where the radar window of the lidar is located through the lidar, and target frame point cloud data is obtained.

[0033] The lidar itself emits light for detection in the direction where the radar window of the lidar is located to collect data, and target frame point cloud data is obtained.

[0034] Here, when there are contaminants on the radar window, the target frame point cloud data is used to accurately reflect the location and shape of the contaminants on the window.

[0035] In some embodiments, point cloud data refers to a set of vectors in a three-dimensional coordinate system; the target frame point cloud data is a set of data used to indicate the coordinates and shape of the target object when the lidar collects data at the target frame rate.

[0036] For example, when the lidar is implemented as an optical phased array (OPA) radar, data is collected in the direction where the radar window of the lidar is located through the dense scanning of the OPA lidar (e.g., 0.1 degree or 0.05 degree) to obtain the accurate position, size, and shape of the contaminants, and corresponding measures are taken for cleaning.

[0037] Through the embodiments provided by the present application, the lidar itself is used to collect data on the radar window of the lidar to obtain target frame point cloud data, so as to facilitate the subsequent determination of the location and shape of the contaminants.

[0038] In step S104, target detection is performed based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window.

[0039] Here, target detection is performed based on the target frame point cloud data to determine the target object area where there is a target object on the radar window, and the target object area is converted into corresponding position coordinates to facilitate the determination of the accurate shape and specific position of the target object on the radar window.

[0040] Through the embodiments provided by the present application, target detection can be performed based on the target frame point cloud data to obtain the specific position of the contaminants on the radar window.

[0041] In step S106, the target object area is cleaned to clean the target object.

[0042] After determining the specific position of the target object on the radar window, the target object area is precisely cleaned by a cleaning component preset on the lidar to clean the target object. Here, the relative position of the target object can be represented by a coordinate system with the center of the radar window as the origin.

[0043] In some embodiments, corresponding preset cleaning schemes can be adopted according to the specific position, size, etc. of the target object on the radar window of the lidar, which is not limited in this application.

[0044] Through the embodiments provided in this application, it is possible to accurately clean the position on the radar window of the lidar where the target object is located, improving the cleaning efficiency.

[0045] In an exemplary embodiment, data is collected on the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data, including:

[0046] S11, when the preset detection mode of the lidar is the first detection mode and the lidar is in the first pose, data is collected on the direction where the radar window is located through the lidar to obtain the first frame of point cloud data;

[0047] S12, after the pose of the lidar changes from the first pose to the second pose, data is collected on the direction where the radar window is located through the lidar to obtain the second frame of point cloud data;

[0048] Among them, the target frame point cloud data includes the first frame of point cloud data and the second frame of point cloud data.

[0049] Since when the lidar is in the same pose, the data collection direction of the lidar is certain and there may be data collection blind spots, it is necessary to perform multiple data collections through different poses to make the target frame point cloud data more comprehensive.

[0050] In some embodiments, the preset first detection mode of the lidar can be to select a preset number of different poses and collect data on the direction where the radar window is located through the lidar to determine the target frame point cloud data in different pose cases.

[0051] In some embodiments, the pose of the lidar is associated with a set of device parameters of the lidar. For example, a set of device parameters includes at least one of the following: attitude, heading angle, speed; in the case of determining that the lidar has moved and / or the angle has deflected based on a set of device parameters of the target device, it is determined that the pose of the lidar has changed from the first pose to the second pose.

[0052] Through the embodiments provided in this application, data collection is performed on the radar window of the lidar based on different lidar poses, which can avoid data collection blind spots caused by a single pose.

[0053] In an exemplary embodiment, target detection is performed based on the target frame point cloud data to obtain a target object area, including:

[0054] S21, perform target detection on the first frame of point cloud data to obtain the first position information of the reference object, where the first position information is used to represent the first position area where the reference object is located;

[0055] S22, perform target detection on the second frame of point cloud data to obtain the second position information of the reference object, where the second position information of the reference object is used to represent the second position area where the reference object is located;

[0056] S23, perform coordinate transformation on the first position area according to the pose transformation amount between the first pose and the second pose to obtain a predicted position area, where the predicted position area is the predicted position area where the reference object is located when the lidar is in the second pose;

[0057] S24, in the case where the second position area is inconsistent with the predicted position area, determine the target object area based on the second position area and the predicted position area.

[0058] Perform target detection on the first frame of point cloud data obtained by data collection when the lidar is in the first pose to obtain the first position information (actual position information) representing the first position area where the reference object is located, and perform target detection on the second frame of point cloud data obtained by data collection when the lidar is in the second pose to obtain the second position information (actual position information) representing the second position area where the reference object is located.

[0059] Here, the pose transformation amount between the first pose and the second pose can be determined according to the first position information and the second position information of the same reference object, so as to perform coordinate transformation according to the pose transformation amount based on the first position information to obtain the predicted position area (that is, the position area where the reference object is located when the lidar is in the second pose). At this time, if the predicted position area is inconsistent with the actual second position area, it means that due to the presence of contaminants on the radar window of the lidar, the actual second frame of point cloud data has changed, resulting in a change in the shape or position of the reference object.

[0060] In some embodiments, when the second position area corresponding to the reference object is consistent with the predicted position area, it indicates that there is no pollutant exceeding the preset threshold in the current two areas of the lidar's radar window under the pose change conditions in the current time period. The preset threshold can be a reflectivity threshold, an object area threshold, etc., which is not limited in this application.

[0061] In an exemplary embodiment, the first position area, the second position area, and the predicted position area are all position areas of the reference object on the radar window of the lidar;

[0062] In the case where the second position area is inconsistent with the predicted position area, based on the second position area and the predicted position area, determining the target object area includes:

[0063] S31. In the case where the second position area is inconsistent with the predicted position area, determine the non-overlapping area between the second position area and the predicted position area as the target object area.

[0064] In actual application scenarios, there are pollutants in some areas of the lidar's radar window. Therefore, based on the second position area (corresponding to the actual position area of the lidar in the second pose) and the predicted position area (the predicted position area obtained by coordinate transformation according to the pose transformation amount based on the first position information) of the same reference target, there are overlapping areas and non-overlapping areas.

[0065] Among them, due to the change in the refractive index (reflectivity) of the radar window caused by the pollutants in the lidar's radar window, the second position area and the predicted position area of the same reference target are offset (i.e., cannot overlap).

[0066] In some embodiments, refer to Figure 2 , Figure 2 The point cloud data on the left is the point cloud data at the first pose at the first moment, and the point cloud data on the right is the point cloud data at the second pose after the device deflects by a preset angle. At this time, if the predicted point cloud data determined according to the deflection angle change amount and the point cloud data at the first pose is consistent with the point cloud data at the second pose above, it indicates that there is no pollutant in the current two areas.

[0067] In some embodiments, refer to Figure 3 , Figure 3On the left is the point cloud data in the first pose at the second moment, and on the right is the point cloud data in the second pose after the device moves backward by a preset distance. At this time, the predicted point cloud data determined according to the backward movement distance and the point cloud data in the first pose should show that the two objects are reduced in size in a corresponding proportion; however, in the actual point cloud data in the second pose, only a single reference object is reduced in size by a preset proportion, and the other reference object is not reduced in size according to the preset proportion. Then, it is determined that there are pollutants in the area where the second reference object is located, and the area where the second reference object is located is determined as the target object area.

[0068] In some embodiments, refer to Figure 4 , Figure 4 On the left is the point cloud data in the first pose at the first moment, and on the right is the point cloud data in the second pose after the device moves backward by a preset distance. At this time, the predicted point cloud data determined according to the backward movement distance and the point cloud data in the first pose should show that the two reference objects are reduced in size in a corresponding proportion; and the sizes of the two reference objects presented in the actual point cloud data in the second pose are the same as the sizes of the two reference objects in the predicted point cloud data. Then, it is determined that the radar windows (window panes) in the current two regions are clean regions.

[0069] Through the embodiments provided by the present application, it is possible to accurately locate the area where the corresponding target object is located by comparing the actual position of the reference object area after pose transformation with the predicted position of the reference object area based on the pose transformation amount.

[0070] In an exemplary embodiment, the lidar is an optical phased array OPA lidar; after determining the target object area based on the second position area and the predicted position area, the above method further includes:

[0071] S41, performing edge contour detection on the target object area through the OPA lidar to obtain a contour detection result, where the contour detection result is used to represent the object contour of the target object;

[0072] S42, updating the target object area to the area identified by the object contour of the target object to obtain an updated target object area.

[0073] After determining the target object area where the target object is located, performing edge contour detection on the target object area through the OPA lidar to determine the actual shape of the target object and updating the target object area to the area identified by the object contour of the target object. While increasing the position accuracy of the target object, it is also possible to determine the category of the target object according to the object contour of the target object.

[0074] In some embodiments, based on the updated target object area, the shape of the target object and the surface area of the target object on the radar window are determined to facilitate subsequent selection of corresponding cleaning strategies.

[0075] For example, when the lidar is implemented as an OPA lidar, edge contour detection is performed on the direction where the radar window of the lidar is located through dense scanning of the OPA lidar (e.g., 0.1 degrees or 0.05 degrees) to obtain the precise position size and precise shape of the pollutant, so as to take corresponding measures for cleaning.

[0076] In some embodiments, determining the edge position of the target object (obstacle object) and starting to scan the target object area from the edge position can improve the accuracy of edge contour detection.

[0077] Through the embodiments provided by the present application, after determining the target object area where the target object is located, edge contour detection is performed on the target object area to facilitate subsequent determination of the category, area, etc. of the target object.

[0078] In an exemplary embodiment, after data collection is performed on the direction where the radar window is located through the lidar, the above method further includes:

[0079] S51, real-time detection of a set of device parameters of the target device where the lidar is located is performed through an inertial measurement unit, where the set of device parameters includes at least one of the following: attitude, heading angle, speed;

[0080] S52, in the case where it is determined that the target device has moved and / or deflected based on a set of device parameters of the target device, it is determined that the pose of the lidar has changed from the first pose to the second pose.

[0081] Here, the attitude, heading angle, and speed of the lidar are captured in real time through the inertial measurement unit to determine whether the device has moved and / or deflected; when it is determined that there is an offset, the position of the obstacle (reference object) in the current target frame point cloud data is read, and coordinate conversion is performed based on the obstacle position and deflection information in the saved previous target frame point cloud data to generate a predicted obstacle position relative to the current obstacle information, and based on the comparison result between the predicted obstacle position and the current actual obstacle position, it is determined whether there is a pollutant on the radar window of the current lidar.

[0082] In some embodiments, the inertial measurement unit (abbreviated as IMU) is mainly used to detect and measure acceleration, tilt, shock, vibration, rotation, and multi-degree-of-freedom motion. It generally refers to a device that uses an accelerometer and a gyroscope to measure the single-axis, biaxial, or triaxial attitude angle (or angular rate) and acceleration of an object.

[0083] In an exemplary embodiment, after data acquisition of the direction where the radar window is located by the lidar, the above method further includes:

[0084] S61, controlling the lidar to perform a pose transformation through a control component, so as to change the pose of the lidar from a first pose to a second pose.

[0085] Here, the control component is used to control the lidar to perform a pose transformation of a target pose. Here, the pose transformation can be one of a transformation of attitude, heading angle, and speed.

[0086] In an exemplary embodiment, target detection is performed based on target frame point cloud data to obtain a target object area, including:

[0087] S71, when the preset detection mode of the lidar is the second detection mode, based on the window distance of the radar window, extract the point cloud data matching the window distance from the target frame point cloud data to obtain window point cloud data, and perform target detection on the window point cloud data to obtain a target object area;

[0088] Wherein, the window distance is the distance between the lidar and the radar window, and the window distance is determined based on the window distance information of the radar window extracted from the configuration information of the lidar.

[0089] Here, when the window contaminant is outside the proximal blind area of the lidar, filter the window point cloud data based on the window distance, and calculate the position area of the contaminant according to the window point cloud data.

[0090] When the lidar and the radar window are within a preset window distance range, it may cause the distance between the lidar and the radar window to be too close (there is a proximal blind area), resulting in the lidar being unable to accurately collect the target frame point cloud data on the radar window. At this time, select the second detection mode, extract the point cloud data matching the window distance from the already collected target frame point cloud data based on the window distance of the radar window, and calculate the position area of the contaminant according to the window point cloud data.

[0091] In some embodiments, referring to Figure 5 , the lidar device includes a radar window, an optical chip, a radar housing, and an IMU position detection unit.

[0092] Wherein, the optical chip is used to emit laser to perform data acquisition on the radar window, and the normal light emission situation (no contaminant) is as Figure 5 shown.

[0093] In some embodiments, referring to Figure 6 , the target processing method based on lidar provided by the embodiments of the present application includes the following steps:

[0094] In step 1, the lidar device is powered on to collect point cloud data.

[0095] In step 2, the currently acquired point cloud data and the pose data detected by the IMU position detection unit are saved.

[0096] In step 3, the point cloud data is processed and the positions of obstacles in the point cloud data are marked.

[0097] In step 4, it is judged according to the IMU position detection unit whether there is a change in the heading angle or movement of the lidar device.

[0098] If so, step 5 is executed; if not, return to step 2.

[0099] In step 5, point cloud data prediction is performed according to the initial pose of the lidar device and the amount of pose change.

[0100] In step 6, it is judged whether the predicted point cloud data is consistent with the point cloud data of the current pose.

[0101] Here, it can also be judged according to the positions of obstacles in the point cloud data.

[0102] If so, return to step 2; if not, execute step 7.

[0103] In step 7, the non-overlapping area of obstacles indicated by the inconsistent point cloud data is marked and cleaned as the pollutant area.

[0104] Through the above steps of the embodiments of the present application, it is possible to accurately detect the position of pollutants by scanning at a very small angle with a lidar device (such as an OPA lidar).

[0105] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0106] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present application.

[0107] According to another aspect of the embodiments of the present application, a target processing device based on lidar is further provided. The device is used to implement the target processing method based on lidar provided in the above embodiments, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0108] Figure 7 is a structural block diagram of an optional target processing device based on lidar according to the embodiments of the present application. As Figure 7 shown, the device includes:

[0109] An acquisition unit 702, configured to collect data in the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data;

[0110] A detection unit 704, configured to perform target detection based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window;

[0111] A cleaning unit 706, configured to clean the target object area to clean the target object.

[0112] Through the embodiments of the present application, data is collected in the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data; target detection is performed based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window; the target object area is cleaned to clean the target object. The cleaning efficiency of the radar window is improved, and thus the problem that the cleaning efficiency of the radar window is low due to cleaning the entire radar window in the related art of the target processing method based on lidar is solved.

[0113] As an alternative solution, the acquisition unit includes:

[0114] The first acquisition module is configured to, when the preset detection mode of the lidar is the first detection mode and the lidar is in the first pose, collect data in the direction where the radar window is located through the lidar to obtain the first frame of point cloud data;

[0115] The second acquisition module is configured to, after the pose of the lidar changes from the first pose to the second pose, collect data in the direction where the radar window is located through the lidar to obtain the second frame of point cloud data; wherein, the target frame of point cloud data includes the first frame of point cloud data and the second frame of point cloud data.

[0116] As an alternative solution, the detection unit includes:

[0117] The first detection module is configured to perform target detection on the first frame of point cloud data to obtain the first position information of the reference object, wherein the first position information is used to represent the first position area where the reference object is located;

[0118] The second detection module is configured to perform target detection on the second frame of point cloud data to obtain the second position information of the reference object, wherein the second position information of the reference object is used to represent the second position area where the reference object is located;

[0119] The transformation module is configured to perform coordinate transformation on the first position area according to the pose transformation amount between the first pose and the second pose to obtain the predicted position area, wherein the predicted position area is the predicted position area where the reference object is located when the lidar is in the second pose;

[0120] The first determination module is configured to, when the second position area is inconsistent with the predicted position area, determine the target object area based on the second position area and the predicted position area.

[0121] As an alternative solution, the first position area, the second position area, and the predicted position area are all the position areas of the reference object on the radar window; the first determination module includes:

[0122] The determination sub-module is configured to, when the second position area is inconsistent with the predicted position area, determine the non-overlapping area between the second position area and the predicted position area as the target object area.

[0123] As an alternative solution, the lidar is an optical phased array OPA radar; after determining the target object area based on the second position area and the predicted position area, the above device further includes:

[0124] An outline detection unit for performing edge outline detection on a target object area through an OPA radar to obtain an outline detection result, where the outline detection result is used to represent the object outline of the target object;

[0125] An update unit for updating the target object area to the area identified by the object outline of the target object to obtain an updated target object area.

[0126] As an optional solution, after data collection is performed on the direction where the radar window is located through a lidar, the above device further includes:

[0127] A real-time detection unit for performing real-time detection on a set of device parameters of a target device where the lidar is located through an inertial measurement unit, where the set of device parameters includes at least one of the following: attitude, heading angle, speed;

[0128] A determination unit for determining that the pose of the lidar changes from a first pose to a second pose when it is determined based on a set of device parameters of the target device that the target device has moved and / or deflected in angle.

[0129] As an optional solution, after data collection is performed on the direction where the radar window is located through a lidar, the above device further includes:

[0130] A pose transformation unit for controlling the lidar to perform pose transformation through a control component to change the pose of the lidar from a first pose to a second pose.

[0131] As an optional solution, the detection unit includes:

[0132] An extraction module for, when the preset detection mode of the lidar is the second detection mode, extracting point cloud data matching the window distance from the target frame point cloud data based on the window distance of the radar window to obtain window point cloud data, and performing target detection on the window point cloud data to obtain a target object area; where the window distance is the distance between the lidar and the radar window, and the window distance is determined based on the window distance information of the radar window extracted from the configuration information of the lidar.

[0133] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it executes the steps in any one of the above method embodiments.

[0134] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, read-only memory (ROM), random access memory (RAM), mobile hard disks, magnetic disks, or optical discs that can store computer programs.

[0135] According to another aspect of the embodiments of the present application, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to execute the steps in any of the above method embodiments through the computer program.

[0136] In an exemplary embodiment, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0137] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details are not described herein again.

[0138] According to yet another aspect of the embodiments of the present application, a computer program product is provided. The computer program product includes computer programs / instructions, and the computer programs / instructions include program codes for executing the methods shown in the flowcharts. In such an embodiment, refer to Figure 8 , the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit 801, various functions provided by the embodiments of the present application are executed. The above serial numbers of the embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0139] Refer to Figure 8 , Figure 8 is a block diagram of the computer system of an optional electronic device according to the embodiments of the present application.

[0140] Figure 8 Schematically shows a block diagram of the computer system structure of the electronic device for implementing the embodiments of the present application. As Figure 8As shown, computer system 800 includes a central processing unit 801 (CPU), which can perform various appropriate actions and processes according to programs stored in read-only memory 802 (ROM) or programs loaded from storage section 808 into random access memory 803 (RAM). In random access memory 803, various programs and data required for system operation are also stored. The central processing unit 801, read-only memory 802, and random access memory 803 are connected to each other via bus 804. Input / output interface 805 (Input / Output interface, i.e., I / O interface) is also connected to bus 804.

[0141] The following components are connected to input / output interface 805: input section 806 including a keyboard, a mouse, etc.; output section 807 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; storage section 808 including a hard disk, etc.; and communication section 809 including a network interface card such as a local area network card, a modem, etc. Communication section 809 performs communication processing via a network such as the Internet. Drive 810 is also connected to input / output interface 805 as needed. Removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on drive 810 as needed so that a computer program read from it can be installed into storage section 808 as needed.

[0142] In particular, according to an embodiment of the present application, the processes described in each method flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit 801, various functions defined in the system of the present application are executed.

[0143] It should be noted that Figure 8 The computer system 800 of the electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0144] Obviously, those skilled in the art should understand that the various modules or steps of the embodiments of the present application described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0145] The above are only the preferred embodiments of the present application and are not used to limit the embodiments of the present application. For those skilled in the art, the embodiments of the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

1. A target processing method based on lidar, characterized in that Including: Collecting data on the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data; Performing target detection based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window; Cleaning the target object area to clean the target object.

2. The method according to claim 1, wherein The step of collecting data on the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data includes: When the preset detection mode of the lidar is the first detection mode and the lidar is in the first pose, collecting data on the direction where the radar window is located through the lidar to obtain the first frame point cloud data; After the pose of the lidar changes from the first pose to the second pose, collecting data on the direction where the radar window is located through the lidar to obtain the second frame point cloud data; Wherein, the target frame point cloud data includes the first frame point cloud data and the second frame point cloud data.

3. The method according to claim 2, wherein The step of performing target detection based on the target frame point cloud data to obtain a target object area includes: Performing target detection on the first frame point cloud data to obtain the first position information of the reference object, where the first position information is used to represent the first position area where the reference object is located; Performing target detection on the second frame point cloud data to obtain the second position information of the reference object, where the second position information of the reference object is used to represent the second position area where the reference object is located; Performing coordinate transformation on the first position area according to the pose transformation amount between the first pose and the second pose to obtain a predicted position area, where the predicted position area is the predicted position area where the reference object is located when the lidar is in the second pose; In the case where the second position area is inconsistent with the predicted position area, determining the target object area based on the second position area and the predicted position area.

4. The method according to claim 3, wherein The first position area, the second position area, and the predicted position area are all the position areas of the reference object on the radar window; The step of determining the target object area based on the second position area and the predicted position area in the case where the second position area is inconsistent with the predicted position area includes: In the case where the second position area is inconsistent with the predicted position area, determining the non-overlapping area between the second position area and the predicted position area as the target object area.

5. The method according to claim 3, characterized in that, The lidar is an optical phased array OPA lidar; after determining the target object area based on the second position area and the predicted position area, the method further includes: Performing edge contour detection on the target object area through the OPA lidar to obtain a contour detection result, where the contour detection result is used to represent the object contour of the target object. Update the target object area to the area identified by the object contour of the target object to obtain the updated target object area.

6. The method according to any one of claims 2 to 5, characterized in that, After the lidar collects data in the direction where the radar window is located, the method further includes: Real-time detection of a set of device parameters of the target device where the lidar is located through an inertial measurement unit, where the set of device parameters includes at least one of the following: attitude, heading angle, speed; In the case where it is determined that the target device has moved and / or deflected in angle based on a set of device parameters of the target device, determine that the pose of the lidar changes from the first pose to the second pose.

7. The method according to any one of claims 2 to 5, characterized in that, After the lidar collects data in the direction where the radar window is located, the method further includes: Control the lidar to perform a pose transformation through a control component to change the pose of the lidar from the first pose to the second pose.

8. The method according to claim 1, wherein The target detection based on the target frame point cloud data to obtain a target object area includes: In the case where the preset detection mode of the lidar is the second detection mode, based on the window distance of the radar window, extract point cloud data matching the window distance from the target frame point cloud data to obtain window point cloud data, and perform target detection on the window point cloud data to obtain the target object area; Wherein, the window distance is the distance between the lidar and the radar window, and the window distance is determined based on the window distance information of the radar window extracted from the configuration information of the lidar.

9. A target processing device based on lidar, characterized in that, Includes: An acquisition unit for collecting data in the direction where the radar window of the lidar is located through the lidar to obtain target frame point cloud data; A detection unit for performing target detection based on the target frame point cloud data to obtain a target object area, where the target object area is the position area of the target object on the radar window, and the target object is the object to be cleaned on the radar window; A cleaning unit for cleaning the target object area to clean the target object.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, where the program, when running, executes the steps of the method according to any one of claims 1 to 7.

11. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the steps of the method according to any one of claims 1 to 7 through the computer program.

Images