Laser radar ghosting filtering method and device and electronic equipment

Abstract

The invention provides a laser radar ghosting filtering method and apparatus, and an electronic device. The method comprises the steps of obtaining original point cloud information during operation of a laser radar; marking the high-reflectivity point cloud in the original point cloud information based on a preset reflectivity threshold to obtain a marked point cloud; determining a high-reflection point cloud area according to the mark point cloud; determining a target wire harness area according to the wire harness of the laser radar corresponding to the high-reflection point cloud area; determining ghosting point cloud in the original point cloud information according to the distance between the target wire harness area and the laser radar and the distance between the high-reflection point cloud area and the laser radar; and deleting the ghosting point cloud from the original point cloud information to obtain to-be-identified point cloud data. According to the method, the high-reflectivity point clouds in the original point cloud information are marked and further screened, so that the ghosting point clouds are determined, and the sensing precision can be improved after the ghosting point clouds are filtered out.

Description

Technical Field

[0001] The present invention relates to the technical field of laser detection, and in particular to a method, device and electronic device for filtering ghost images of lidar. Background Art

[0002] With the development of technology, the research and development and manufacturing cost of lidar is getting lower and lower, and the popularity is getting higher and higher. There are also more and more lidars installed on vehicles to assist in autonomous driving. However, in actual application scenarios, there will be some objects with relatively high reflectivity, such as cone barrels, rearview mirrors, traffic signs, etc., which are inescapable objects with relatively high reflectivity, generally referred to as high-reflectivity objects. The appearance of objects with high reflectivity often results in ghost image phenomena, that is, in addition to imaging at the true position of the high-reflectivity object, the point cloud output by the radar is also likely to form a false image similar to the shape and size of the high-reflectivity object at other positions, thus causing the perception error accuracy to be relatively low. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device and electronic device for filtering ghost images of lidar, so as to alleviate the technical problem that in addition to imaging at the true position of the high-reflectivity object, the point cloud output by the lidar is also likely to form a false image similar to the shape and size of the high-reflectivity object at other positions, thus causing the perception error accuracy to be relatively low, and improve the perception accuracy of the lidar.

[0004] In a first aspect, an embodiment of the present invention provides a method for filtering ghost images of lidar, including: obtaining the original point cloud information when the lidar is running; marking the high-reflectivity point cloud in the original point cloud information based on a preset reflectivity threshold to obtain marked point cloud; determining the high-reflectivity point cloud region according to the marked point cloud; determining the target beam region according to the beam of the lidar corresponding to the high-reflectivity point cloud region; determining the ghost point cloud in the original point cloud information according to the target beam region, the high-reflectivity point cloud region and the distance between the high-reflectivity point cloud region and the lidar; deleting the ghost point cloud from the original point cloud information to obtain the point cloud data to be recognized.

[0005] In a preferred embodiment of the present invention, the step of determining the ghost point cloud in the original point cloud information according to the target beam region, the high-reflectivity point cloud region and the distance between the high-reflectivity point cloud region and the lidar includes: setting a distance error threshold according to the distance between the high-reflectivity point cloud region and the lidar and a preset error step; screening the second target point cloud greater than the distance error threshold in the first target point cloud corresponding to the target beam region; determining the ghost point cloud in the original point cloud information according to the second target point cloud.

[0006] In a preferred embodiment of the present invention, the preset error step is 3 cm.

[0007] In a preferred embodiment of the present invention, the step of determining the ghost point cloud in the original point cloud information according to the above-mentioned second target point cloud includes: determining the ghost point cloud region in the original point cloud information according to the above-mentioned second target point cloud; screening a first target ghost region with a reflectivity less than a preset reflectivity from the above-mentioned ghost point cloud region; screening the peripheral point cloud of the above-mentioned first target ghost region; screening, from the above-mentioned peripheral point cloud, the target peripheral point cloud whose distance from the reflection point of the corresponding beam of the above-mentioned peripheral point cloud is zero or greater than a preset distance; and determining the ghost point cloud in the original point cloud information according to the second target ghost region corresponding to the above-mentioned target peripheral point cloud.

[0008] In a preferred embodiment of the present invention, the step of determining the ghost point cloud in the original point cloud information according to the second target ghost region corresponding to the above-mentioned target peripheral point cloud includes: performing a division operation on the number of points in the above-mentioned second target ghost region and the number of points in the above-mentioned high-reflectivity point cloud region to obtain a ratio; determining whether the above-mentioned ratio conforms to a preset multiple relationship; if so, determining the points in the above-mentioned second target ghost region as the ghost point cloud in the original point cloud information.

[0009] In a preferred embodiment of the present invention, the above-mentioned multiple relationship is 0.5 times to 3 times.

[0010] In a preferred embodiment of the present invention, the above-mentioned preset reflectivity threshold is 230%.

[0011] In a preferred embodiment of the present invention, after the step of deleting the above-mentioned ghost point cloud from the original point cloud information to obtain the point cloud data to be recognized, the method further includes: determining the perception result of the lidar according to the above-mentioned point cloud data to be recognized.

[0012] In a second aspect, an embodiment of the present invention further provides a lidar ghost filtering method, including: a data acquisition module, configured to acquire the original point cloud information during the operation of the lidar; a high-reflectivity marking module, configured to mark the high-reflectivity point cloud in the above-mentioned original point cloud information based on a preset reflectivity threshold to obtain marked point cloud; a high-reflectivity point cloud region determination module, configured to determine a high-reflectivity point cloud region according to the above-mentioned marked point cloud; a beam region determination module, configured to determine a target beam region according to the beam of the lidar corresponding to the above-mentioned high-reflectivity point cloud region; a ghost point cloud determination module, configured to determine the ghost point cloud in the above-mentioned original point cloud information according to the above-mentioned target beam region, the above-mentioned high-reflectivity point cloud region, and the distance of the lidar; and a ghost point cloud filtering module, configured to delete the above-mentioned ghost point cloud from the above-mentioned original point cloud information to obtain the point cloud data to be recognized.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the laser radar ghost filtering method in Shangshuyuan.

[0014] An embodiment of the present invention provides a method, apparatus, and electronic device for filtering laser radar ghosts, including: obtaining original point cloud information during the operation of the laser radar; marking high-reflectivity point clouds in the original point cloud information based on a preset reflectivity threshold to obtain marked point clouds; determining high-reflectivity point cloud regions according to the marked point clouds; determining target beam regions according to the beam lines of the laser radar corresponding to the high-reflectivity point cloud regions; determining ghost point clouds in the original point cloud information according to the target beam regions, the high-reflectivity point cloud regions, and the distance from the laser radar; and deleting the ghost point clouds from the original point cloud information to obtain point cloud data to be recognized. By marking the high-reflectivity point clouds in the original point cloud information and further screening, the ghost point clouds can be determined. After filtering out the ghost point clouds, the perception accuracy can be improved.

[0015] Other features and advantages disclosed in this embodiment will be described in the subsequent specification, or some features and advantages can be inferred from the specification or determined without doubt, or can be known by implementing the above technologies of the present disclosure.

[0016] To make the above objects, features, and advantages of the present disclosure more obvious and understandable, the following specific preferred embodiments are given and described in detail in conjunction with the accompanying drawings. Description of the Drawings

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic flowchart of a method for filtering laser radar ghosts provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic flowchart of another method for filtering laser radar ghosts provided by an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of a device for filtering laser radar ghosts provided by an embodiment of the present invention;

[0021] Figure 4Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0022] Icon 31 - Data acquisition module; 32 - High reflectivity marking module; 33 - High reflection point cloud area determination module; 34 - Harness area determination module; 35 - Ghost point cloud determination module; 36 - Ghost point cloud filtering module; 41 - Processor; 42 - Memory; 43 - Bus; 44 - Communication interface. Detailed implementation manners

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0024] In the actual application scenarios of lidar, there are some objects with high reflectivity, such as cone barrels, rearview mirrors, traffic signs, etc., which are unavoidable objects with high reflectivity, generally referred to as high - reflection objects. The appearance of objects with high reflectivity often results in ghosting phenomena, that is, in addition to imaging at the true position of the high - reflection, the point cloud output by the lidar is also likely to form a false image similar in shape and size to the high - reflection object at other positions, thereby causing low perception accuracy.

[0025] Based on this, the embodiments of the present invention provide a lidar ghost filtering method, device, and electronic device. This method marks the high - reflectivity point cloud in the above - mentioned original point cloud information and then further screens it to determine the ghost point cloud. After filtering out the ghost point cloud, the perception accuracy can be improved. For the convenience of understanding the embodiments of the present invention, a lidar ghost filtering method disclosed in the embodiments of the present invention will be introduced in detail first.

[0026] Embodiment 1

[0027] In this embodiment, Figure 1 Schematic flow chart of a lidar ghost filtering method provided by an embodiment of the present invention.

[0028] As Figure 1 can be seen, the lidar ghost filtering method includes:

[0029] Step S101: Obtain the original point cloud information when the lidar is running.

[0030] In this embodiment, by parsing the network data packets transmitted by the lidar, when the frame header data is parsed, the point cloud data in the data packet is cached. After caching one frame of data each time, the point cloud is processed. A complete set of original point cloud information is constructed based on the information such as the laser beam number, angle, reflectivity, and distance included in the point cloud packet.

[0031] Step S102: Mark the high-reflectivity point cloud in the above original point cloud information based on a preset reflectivity threshold to obtain marked point cloud.

[0032] In this embodiment, according to past experience, target objects with a reflectivity higher than 230% are prone to generating ghost images. Thus, the high-reflectivity point clouds that meet the conditions are marked, and an algorithm is used to mark adjacent marked high-reflectivity points as a whole high-reflectivity area. The specific method for marking the high-reflectivity area is to determine whether the points above, below, left, and right of the marked point cloud are marked point clouds. If so, they are marked as the initial point cloud area, and the diffusion judgment continues in the up, down, left, and right directions. The finally calibrated area includes all the marked point clouds within this area, which is called the high-reflectivity point cloud area.

[0033] Step S103: Determine the high-reflectivity point cloud area based on the above marked point cloud.

[0034] Step S104: Determine the target beam area according to the beam of the lidar corresponding to the above high-reflectivity point cloud area.

[0035] Step S105: Determine the ghost point cloud in the above original point cloud information according to the above target beam area, the above high-reflectivity point cloud area, and the distance from the above lidar.

[0036] In this embodiment, according to the lidar test phenomenon, the beam where the ghost image is located basically coincides with the beam where the high-reflectivity area is located, only the horizontal angles are different. Calculate the range of the laser beam covered by the high-reflectivity position and expand one beam upward and downward respectively. The final beam range is recorded as the beam area where the ghost image may be generated. In addition, according to the cause of the ghost image generation, the distance from the ghost image to the radar is approximately the same as the distance from the high-reflectivity area to the radar, with a small error. An algorithm is used to mark the points in the beam area with a distance information error less than the distance error threshold from the high-reflectivity position as possible ghost points, and adjacent possible ghost points are marked as an area where a ghost image may be generated.

[0037] Furthermore, the ghost reflectivity is generally below 5%. First, identify the regions that meet the ghost reflectivity index in the regions where ghosts may occur, and mark the regions where low-reflection ghosts may exist. Second, determine whether the regions where low-reflection ghosts may exist are independent of other point clouds. If the distance between the outermost point clouds in this region and the adjacent points outside the same beam is greater than the independent distance threshold, or the distance between adjacent points is 0, then this region is an independent region where low-reflection ghosts may exist. To reduce the probability of misjudging point clouds, the number of point clouds in the region is additionally judged. As the mirror image of high reflection, a ghost has the same number of point clouds as high reflection. Considering energy loss and beam crosstalk, the number of points of a ghost is generally 0.5 to 3 times that of high reflection. Determine the independent regions where low-reflection ghosts may exist within this quantity range as the final ghost point clouds.

[0038] Step S106: Delete the above-mentioned ghost point clouds from the above-mentioned original point cloud information to obtain the point cloud data to be recognized.

[0039] The embodiment of the present invention provides a method for filtering ghosts of a lidar, including: obtaining the original point cloud information during the operation of the lidar; marking the high-reflectivity point clouds in the above-mentioned original point cloud information based on a preset reflectivity threshold to obtain marked point clouds; determining the high-reflection point cloud regions according to the above-mentioned marked point clouds; determining the target beam regions according to the beams of the lidar corresponding to the above-mentioned high-reflection point cloud regions; determining the ghost point clouds in the above-mentioned original point cloud information according to the above-mentioned target beam regions, the above-mentioned high-reflection point cloud regions, and the distance from the above-mentioned lidar; and deleting the above-mentioned ghost point clouds from the above-mentioned original point cloud information to obtain the point cloud data to be recognized. By marking the high-reflectivity point clouds in the above-mentioned original point cloud information and further screening, the ghost point clouds are determined. After filtering out the ghost point clouds, the perception accuracy can be improved.

[0040] Embodiment 2

[0041] Based on Embodiment 1, Figure 2 is a schematic flowchart of another method for filtering ghosts of a lidar provided by an embodiment of the present invention.

[0042] As Figure 2 can be seen, this method includes:

[0043] Step S201: Obtain the original point cloud information during the operation of the lidar.

[0044] Step S202: Mark the high-reflectivity point clouds in the above-mentioned original point cloud information based on a preset reflectivity threshold to obtain marked point clouds.

[0045] Here, the above-mentioned preset reflectivity threshold is 230%.

[0046] Step S203: Determine the high-reflection point cloud regions according to the above-mentioned marked point clouds.

[0047] Step S204: Determine a target beam region according to the beam of the lidar corresponding to the above-mentioned high-reflection point cloud region.

[0048] Step S205: Set a distance error threshold according to the distance between the above-mentioned high-reflection point cloud region and the lidar and a preset error step size. Here, the above-mentioned preset error step size is 3 cm.

[0049] Step S206: In the first target point cloud corresponding to the above-mentioned target beam region, filter out the second target point cloud greater than the above-mentioned distance error threshold.

[0050] Step S207: Determine the ghost point cloud in the above-mentioned original point cloud information according to the above-mentioned second target point cloud.

[0051] In this embodiment, the above-mentioned step S207 includes the following steps A1-A5:

[0052] Step A1: Determine the ghost point cloud region in the above-mentioned original point cloud information according to the above-mentioned second target point cloud.

[0053] Step A2: Filter out the first target ghost region with a reflectivity less than the preset reflectivity from the above-mentioned ghost point cloud region.

[0054] Step A3: Filter out the peripheral point cloud of the above-mentioned first target ghost region.

[0055] Step A4: From the above-mentioned peripheral point cloud, filter out the target peripheral point cloud whose distance from the reflection point of the beam corresponding to the above-mentioned peripheral point cloud is zero or greater than the preset distance.

[0056] Step A5: Determine the ghost point cloud in the above-mentioned original point cloud information according to the second target ghost region corresponding to the above-mentioned target peripheral point cloud.

[0057] In this embodiment, the above-mentioned step A5 includes: First, perform a division operation on the number of points in the above-mentioned second target ghost region and the number of points in the above-mentioned high-reflection point cloud region to obtain a ratio. Then, determine whether the above-mentioned ratio meets the preset multiple relationship. Finally, if so, determine the points in the above-mentioned second target ghost region as the ghost point cloud in the above-mentioned original point cloud information.

[0058] Here, the above-mentioned multiple relationship is 0.5 times to 3 times.

[0059] Step S208: Delete the above-mentioned ghost point cloud from the above-mentioned original point cloud information to obtain the point cloud data to be recognized.

[0060] In this embodiment, after the above-mentioned step S208, the method further includes: determining the perception result of the lidar according to the above-mentioned point cloud data to be recognized.

[0061] An embodiment of the present invention provides a method for filtering ghost points of a lidar, including: obtaining original point cloud information during the operation of the lidar; marking high-reflectivity point clouds in the original point cloud information based on a preset reflectivity threshold to obtain marked point clouds; determining a high-reflectivity point cloud region according to the marked point clouds; determining a target beam region according to the beam of the lidar corresponding to the high-reflectivity point cloud region; setting a distance error threshold according to the distance between the high-reflectivity point cloud region and the lidar and a preset error step size; screening second target point clouds greater than the distance error threshold in the first target point cloud corresponding to the target beam region; determining ghost point clouds in the original point cloud information according to the second target point clouds; and deleting the ghost point clouds from the original point cloud information to obtain point cloud data to be recognized. By marking the high-reflectivity point clouds in the original point cloud information and further setting a distance error threshold to screen the second target point clouds greater than the distance error threshold, and then determining ghost point clouds based on the second target point clouds, after filtering the ghost point clouds, the perception accuracy can be further improved.

[0062] Embodiment 3

[0063] Based on the above embodiment, Figure 3 It is a schematic structural diagram of a lidar ghost point filtering device provided by an embodiment of the present invention.

[0064] As can be seen from Figure 3 the figure, the device includes:

[0065] A data acquisition module 31, configured to obtain original point cloud information during the operation of the lidar.

[0066] A high-reflectivity marking module 32, configured to mark high-reflectivity point clouds in the original point cloud information based on a preset reflectivity threshold to obtain marked point clouds.

[0067] A high-reflectivity point cloud region determination module 33, configured to determine a high-reflectivity point cloud region according to the marked point clouds.

[0068] A beam region determination module 34, configured to determine a target beam region according to the beam of the lidar corresponding to the high-reflectivity point cloud region.

[0069] A ghost point cloud determination module 35, configured to determine ghost point clouds in the original point cloud information according to the target beam region, the distance between the high-reflectivity point cloud region and the lidar.

[0070] A ghost point cloud filtering module 36, configured to delete the ghost point clouds from the original point cloud information to obtain point cloud data to be recognized.

[0071] Among them, the data acquisition module 31, the high reflectivity marking module 32, the high reflection point cloud region determination module 33, the wire harness region determination module 34, the ghost point cloud determination module 35, and the ghost point cloud filtering module 36 are connected in sequence.

[0072] In one implementation, the above-mentioned ghost point cloud determination module 35 is further configured to set a distance error threshold according to the distance between the above-mentioned high reflection point cloud region and the lidar and a preset error step size; in the first target point cloud corresponding to the above-mentioned target wire harness region, screen the second target point cloud greater than the above-mentioned distance error threshold; according to the above-mentioned second target point cloud, determine the ghost point cloud in the above-mentioned original point cloud information.

[0073] In one implementation, the above-mentioned ghost point cloud determination module 35 is further configured to determine the ghost point cloud region in the above-mentioned original point cloud information according to the above-mentioned second target point cloud; screen the first target ghost region with a reflectivity less than the preset reflectivity from the above-mentioned ghost point cloud region; screen the peripheral point cloud of the above-mentioned first target ghost region; from the above-mentioned peripheral point cloud, screen the target peripheral point cloud whose distance from the reflection point of the wire harness corresponding to the above-mentioned peripheral point cloud is zero or greater than the preset distance; according to the above-mentioned second target ghost region corresponding to the above-mentioned target peripheral point cloud, determine the ghost point cloud in the above-mentioned original point cloud information.

[0074] In one implementation, the above-mentioned ghost point cloud determination module 35 is further configured to perform a division operation on the number of points in the above-mentioned second target ghost region and the number of points in the above-mentioned high reflection point cloud region to obtain a ratio; determine whether the above-mentioned ratio meets a preset multiple relationship; if so, determine the points in the above-mentioned second target ghost region as the ghost point cloud in the above-mentioned original point cloud information.

[0075] In one implementation, the ghost point cloud filtering module 36 is further configured to determine the perception result of the lidar according to the above-mentioned point cloud data to be recognized.

[0076] The lidar ghost filtering device provided by the embodiments of the present invention has the same implementation principle and the same technical effects as those of the foregoing lidar ghost filtering method embodiments. For the sake of brief description, for the parts not mentioned in the embodiments of the above-mentioned lidar ghost filtering device, reference may be made to the corresponding contents in the foregoing method embodiments.

[0077] The embodiments of the present invention also provide an electronic device, as Figure 4 shown, is a schematic structural diagram of the electronic device. Among them, the electronic device includes a processor 41 and a memory 42. The memory 42 stores machine-executable instructions that can be executed by the processor 41, and the processor 41 executes the machine-executable instructions to implement the above-mentioned lidar ghost filtering method.

[0078] In Figure 4In the illustrated embodiment, the electronic device further includes a bus 43 and a communication interface 44. Among them, the processor 41, the communication interface 44, and the memory 42 are connected through the bus.

[0079] Among them, the memory 42 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 44 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus can be an ISA bus, a PCI bus, an EISA bus, etc. The above bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 4 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0080] The processor 41 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 41 or the instructions in the form of software. The above-mentioned processor 41 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by the hardware decoding processor, or executed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor 41 reads the information in the memory 42 and combines its hardware to complete the steps of the lidar ghost filtering method in the foregoing embodiments.

[0081] An embodiment of the present invention also provides a machine-readable storage medium storing machine-executable instructions, which, when called and executed by a processor, cause the processor to implement the above-mentioned lidar ghost filtering method. For specific implementation, reference can be made to the foregoing method embodiments, which will not be elaborated herein.

[0082] The computer program product of the lidar ghost filtering method, lidar ghost filtering device and electronic device provided by the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the above program code can be used to execute the above-mentioned lidar ghost filtering method in the foregoing method embodiments. For specific implementation, reference can be made to the method embodiments, which will not be elaborated herein.

[0083] Unless otherwise specifically stated, the relative steps, numerical expressions and values of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0084] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs that can store program code.

[0085] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, and are not intended to limit it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the above-mentioned claims.

Claims

1. A method for filtering ghost images of a lidar, characterized in that, Including: Obtain the original point cloud information during the operation of the lidar; Mark the high-reflectivity point cloud in the original point cloud information based on a preset reflectivity threshold to obtain the marked point cloud; Determine the high-reflectivity point cloud area according to the marked point cloud; Determine the target beam area according to the beam of the lidar corresponding to the high-reflectivity point cloud area; Determine the ghost point cloud in the original point cloud information according to the target beam area, the high-reflectivity point cloud area, and the distance from the high-reflectivity point cloud area to the lidar; Delete the ghost point cloud from the original point cloud information to obtain the point cloud data to be recognized.

2. The method for filtering ghost images of a lidar according to claim 1, wherein, The step of determining the ghost point cloud in the original point cloud information according to the target beam area, the high-reflectivity point cloud area, and the distance from the high-reflectivity point cloud area to the lidar includes: Set a distance error threshold according to the distance from the high-reflectivity point cloud area to the lidar and a preset error step size; In the first target point cloud corresponding to the target beam area, screen the second target point cloud greater than the distance error threshold; Determine the ghost point cloud in the original point cloud information according to the second target point cloud.

3. The method for filtering ghost images of a lidar according to claim 2, wherein, The preset error step size is 3 cm.

4. The method for filtering ghost images of a lidar according to claim 2, wherein The step of determining the ghost point cloud in the original point cloud information according to the second target point cloud includes: Determine the ghost point cloud area in the original point cloud information from the second target point cloud; Screen the first target ghost area with a reflectivity less than the preset reflectivity from the ghost point cloud area; Screen the peripheral point cloud of the first target ghost area; From the peripheral point cloud, screen the target peripheral point cloud where the distance of the reflection point of the beam corresponding to the peripheral point cloud is zero or greater than the preset distance; Determine the ghost point cloud in the original point cloud information according to the second target ghost area corresponding to the target peripheral point cloud.

5. The method for filtering ghost images of a lidar according to claim 4, characterized in that, The step of determining the ghost point cloud in the original point cloud information according to the second target ghost area corresponding to the target peripheral point cloud includes: Perform a division operation on the number of points in the second target ghost area and the number of points in the high-reflectivity point cloud area to obtain a ratio; Judge whether the ratio meets the preset multiple relationship; If so, determine the points in the second target ghost area as the ghost point cloud in the original point cloud information.

6. The method for filtering ghost images of a lidar according to claim 5, wherein The multiple relationship is 0.5 times to 3 times.

7. The method for filtering ghost images of a lidar according to claim 1, wherein The preset reflectivity threshold is 230%.

8. The method for filtering ghost images of a lidar according to claim 1, wherein After the step of deleting the ghost point cloud from the original point cloud information to obtain the point cloud data to be recognized, the method further includes: Determine the perception result of the lidar according to the point cloud data to be recognized.

9. A method for filtering ghost images of a lidar, characterized in that, Including: A data acquisition module for obtaining the original point cloud information during the operation of the lidar; A high-reflectivity marking module for marking the high-reflectivity point cloud in the original point cloud information based on a preset reflectivity threshold to obtain the marked point cloud; A high-reflectivity point cloud area determination module for determining the high-reflectivity point cloud area according to the marked point cloud; A beam area determination module for determining the target beam area according to the beam of the lidar corresponding to the high-reflectivity point cloud area; A ghost point cloud determination module, configured to determine ghost point clouds in the original point cloud information according to the distance between the target beam region, the high-reflection point cloud region and the lidar; A ghost point cloud filtering module, configured to delete the ghost point clouds from the original point cloud information to obtain point cloud data to be recognized.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the lidar ghost filtering method according to any one of claims 1 to 8.

Images