WO2021189479A1 - 路基传感器的位姿校正方法、装置和路基传感器 - Google Patents

路基传感器的位姿校正方法、装置和路基传感器 Download PDF

Info

Publication number
WO2021189479A1
WO2021189479A1 PCT/CN2020/081848 CN2020081848W WO2021189479A1 WO 2021189479 A1 WO2021189479 A1 WO 2021189479A1 CN 2020081848 W CN2020081848 W CN 2020081848W WO 2021189479 A1 WO2021189479 A1 WO 2021189479A1
Authority
WO
WIPO (PCT)
Prior art keywords
point cloud
pose
current
acquisition device
current frame
Prior art date
Application number
PCT/CN2020/081848
Other languages
English (en)
French (fr)
Inventor
牟加俊
Original Assignee
深圳市速腾聚创科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市速腾聚创科技有限公司 filed Critical 深圳市速腾聚创科技有限公司
Priority to CN202080005468.3A priority Critical patent/CN113748693B/zh
Priority to PCT/CN2020/081848 priority patent/WO2021189479A1/zh
Publication of WO2021189479A1 publication Critical patent/WO2021189479A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Definitions

  • This application relates to the field of automatic driving, and in particular to a method and device for posture correction of a roadbed sensor, and a roadbed sensor.
  • Subgrade sensors are generally installed on both sides or above the road.
  • the subgrade sensors are equipped with point cloud collection devices (such as subgrade sensors, depth cameras, etc.), and the subgrade sensors detect the road conditions on the road through the point cloud collection devices. Due to external vibration, bad weather or other factors, the position of the roadbed sensor may shift, which will cause the roadbed sensor to fail to detect effective road conditions normally, which will affect the normal use of the roadbed sensor, for example: the original roadbed sensor can be 360 degrees Monitoring the road conditions of the road, due to the inclination of the roadbed sensor due to external influences, the point cloud collection device can only detect the road conditions of some roads. In related technologies, the location of subgrade sensors is generally checked manually by hand.
  • the problem with manual checking methods is that the efficiency is low, and it takes a lot of time to check a large number of subgrade sensors in a large area, and the labor cost is high. ; At the same time, the accuracy of manual inspection is not high, and there may be missing inspections.
  • the technical problem to be solved by the embodiments of the present application is to provide a method and device for posture correction of a roadbed sensor, and a roadbed sensor, which can be based on the current posture of the current frame point cloud in the point cloud map generated according to the current position.
  • the deviation between the posture and the reference posture automatically adjusts the posture of the roadbed sensor to improve the efficiency and accuracy of the posture adjustment.
  • this application provides a method for posture correction of roadbed sensors, including:
  • the mechanical device is controlled to adjust the point cloud acquisition device from the current pose to the reference pose.
  • the method before acquiring the point cloud of the current frame scanned and generated by the point cloud acquisition device, the method further includes:
  • Each point cloud is collected in n fields of view by the point cloud acquisition device; wherein there is an overlap area between two adjacent fields of view in the n fields of view, and n is an integer greater than 1;
  • the point cloud map is obtained by stitching the n point clouds based on a point cloud registration algorithm.
  • the sum of the horizontal angles of the n fields of view is greater than 360 degrees.
  • the acquisition of the current frame point cloud scanned and generated by the point cloud acquisition device includes:
  • it also includes:
  • the pose abnormality prompt information is sent to the user terminal, and the pose abnormality information indicates the pose of the point cloud collection device An exception occurs.
  • it also includes:
  • the determining the current pose of the point cloud acquisition device in a preset point cloud map according to the current frame point cloud includes:
  • this application provides a posture correction device for roadbed sensors, including:
  • the acquiring unit is used to acquire the current frame point cloud scanned and generated by the point cloud acquisition device;
  • a posture determination unit configured to determine the current posture of the point cloud acquisition device in a preset point cloud map according to the current frame point cloud;
  • An adjustment calculation unit configured to calculate a pose adjustment parameter when the offset between the current pose and the preset reference pose is greater than the offset threshold
  • the control unit is configured to control a mechanical device to adjust the point cloud acquisition device from the current pose to the reference pose based on the pose adjustment parameter.
  • attitude correction device for a roadbed sensor.
  • the attitude correction device includes: a receiver, a transmitter, a memory, and a processor; wherein the memory stores a set of program codes, and the processor uses Calling the program code stored in the memory to execute the posture correction method of the roadbed sensor described in the above aspects.
  • the implementation of the device can be referred to the implementation of the method, and the repetitions No longer.
  • Another aspect of the present application provides a computer-readable storage medium having instructions stored in the computer-readable storage medium, which when run on a computer, cause the computer to execute the methods described in the above aspects.
  • Another aspect of the present application provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the methods described in the above aspects.
  • the current pose of the point cloud acquisition device in the preset point cloud map is determined according to the current frame point cloud; the offset between the current pose and the preset reference pose is greater than
  • the pose adjustment parameters are calculated; based on the pose adjustment parameters, the mechanical device is driven to adjust the point cloud acquisition device from the current pose to the reference pose, so as to automatically correct the pose of the roadbed sensor and solve the artificial The inefficiency and inaccuracy caused by pose adjustment.
  • FIG. 1 is a schematic diagram of the deployment of roadbed sensors provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a method for posture correction of a roadbed sensor according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of the principle of the field of view provided by this embodiment.
  • FIGS. 4 and 5 are schematic diagrams of the principle of point cloud splicing provided by embodiments of the present application.
  • Fig. 6 is a schematic structural diagram of a pose-based correction device provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of another structure of a pose-based correction device provided by an embodiment of the present application.
  • Roadbed sensors include a pose correction device, a point cloud acquisition device and a mechanical device.
  • the point cloud acquisition device can detect road conditions on the road. For example, the point cloud acquisition device is used to periodically emit detection signals, and the detection signals encounter vehicles on the road. After 104, an echo signal is generated, and the point cloud acquisition device generates a point cloud based on the echo signal; the point cloud acquisition device may be a lidar or a depth camera.
  • the mechanical device can be a device that performs activities with six degrees of freedom.
  • the mechanical device can be a robotic arm or a six-degree-of-freedom platform.
  • the mechanical device can drive the point cloud acquisition device to translate along the x-axis, y-axis, and z-axis, as well as around The x-axis, y-axis, and z-axis are rotated.
  • the pose correction device is used to perform subsequent processing on the point cloud collected by the point cloud acquisition device, such as determining the pose and calculating the amount of pose adjustment.
  • FIG. 2 is a pose correction method provided by an embodiment of the present application. The method includes but is not limited to the following steps:
  • S201 Acquire a point cloud of the current frame scanned and generated by the point cloud acquisition device.
  • the point cloud acquisition device can periodically scan, and a frame of point cloud is generated after each scan, and the pose correction device acquires the current frame point cloud generated by the point cloud acquisition device in the current period.
  • the point cloud can be a 3D point cloud. , That is, the point cloud includes three-dimensional space coordinates (based on the coordinate system of the point cloud acquisition device) and echo intensity.
  • the number and density of point clouds are related to the performance of the point cloud collection device, for example: the more lines of the point cloud collection device, the greater the density of the point cloud; the larger the field of view of the point cloud collection device, the greater the number of point clouds .
  • the points that are too close may fall on the mechanical device, and the points that are too far away are already very sparse, these two types of points have little effect on pose recognition, in order to reduce the amount of calculations
  • the above two types of points are filtered.
  • the specific method includes: the pose correction device is preset with a distance interval, and the point cloud acquisition device performs a scan within the full range to obtain the first point cloud, and then according to the distance interval The first point cloud is filtered, and the distances corresponding to the filtered point clouds all fall within the distance interval, and the filtered point cloud is taken as the current frame point cloud.
  • the point cloud acquisition device is a lidar
  • the full range of the lidar is 0 to 20 meters
  • the lidar scans the first point cloud corresponding to the full range in the current period.
  • the preset distance interval of Lidar is 1m ⁇ 5m. Lidar traverses the distance corresponding to each point in the first point cloud, and takes the point whose distance falls within the distance interval of 1m ⁇ 5m as the point cloud of the current frame.
  • the lens of the point cloud collection device may be blocked by foreign objects, which will affect the detection effect of the point cloud collection device and cannot accurately reflect the situation in the field of view.
  • the lens of the device in order to detect the point cloud collection Whether the lens of the device is blocked, count the number of point clouds of the current frame collected by the point cloud collection device in the current cycle in the full range, and when the number of point clouds of the current frame is less than the preset number, send a blocking prompt message to the user terminal,
  • the occlusion prompt information is used to prompt the user that the point cloud collection device is occluded.
  • the preset number is related to the number of lines of the point cloud acquisition device, the size of the field of view, and the scanning frequency.
  • the preset number is 10000, and when the number of point clouds of the current frame collected by the point cloud collection device in the current cycle is less than 10000, the shielding prompt information is sent to the mobile terminal pre-bound to the user.
  • the type of the shielding prompt information can be a short message , Instant messaging messages, e-mails, or multimedia messages, etc., the embodiments of this application are not limited.
  • S202 Determine the current pose of the point cloud collection device in a preset point cloud map according to the current frame point cloud.
  • the pose correction device is pre-stored or pre-configured with a point cloud map.
  • the point cloud map is obtained by splicing multi-frame point clouds collected by the point cloud collection device under the reference pose. Debug the pose of the point cloud acquisition device to reach the reference pose, and then the point cloud acquisition device collects n point clouds under n fields of view.
  • the field of view represents the scanning range of the point cloud acquisition device, and the range of the field of view is determined by the horizontal angle.
  • the horizontal angle is -30 degrees to +30 degrees, and the vertical angle is -15 degrees to +15 degrees; two adjacent fields of view in n fields of view overlap each other, that is, two adjacent fields
  • the point clouds collected in the field of view overlap each other, and one field of view corresponds to one point cloud.
  • n point clouds are stitched to obtain a complete point cloud map.
  • the sum of the horizontal angles of the n fields of view is greater than 360 degrees, that is, the point cloud acquisition device can scan in a horizontal direction of 360 degrees.
  • the lidar collects point clouds in 6 fields of view, and obtains point cloud 1, point cloud 2, point cloud 3, point cloud 4, point cloud 5, and point cloud 6, respectively.
  • point cloud 1 point cloud 2
  • point cloud 3 point cloud 4
  • point cloud 5 point cloud 6
  • point cloud 6 point cloud 6
  • Point A is a point in the overlap area.
  • a point cloud map is obtained by splicing multiple point clouds based on a point cloud registration algorithm.
  • the point cloud configuration algorithm can be ICP (Iterative Closest Point) or NDT (Normal Distributions Transform). , Normal distribution transformation) algorithm.
  • point cloud A and point cloud B are 3D point clouds, so point cloud A and point cloud B both have contour features, point cloud A is fixed, point cloud B constantly adjusts its pose (position and orientation), current point cloud A
  • point cloud A and the point cloud B are successfully spliced, and the spliced point cloud is shown in FIG. 5.
  • the method for determining the current pose of the point cloud collection frame in the point cloud map according to the current frame point cloud includes: determining the intersection ratio area of the current frame point cloud and the corresponding point cloud map Cross and cross ratio area; calculate the pose transformation relationship between the cross ratio area in the current frame point cloud and the cross ratio area in the point cloud map based on the point cloud registration algorithm; according to the pose transformation The relationship calculates the current pose.
  • the point cloud registration algorithm can be an ICP algorithm or an NDT algorithm.
  • the process of using the ICP algorithm to determine the current pose includes:
  • the translation vector t is only the difference in the center of gravity of the two point sets, which can be determined by the center of gravity point and the rotation matrix in the two coordinate systems.
  • the process of using the NDT algorithm to determine the current pose includes:
  • the NDT registration score (score) is obtained by adding the probability density calculated for each grid.
  • the point cloud registration process can refer to the process of constructing a point cloud map in Figure 4 and Figure 5.
  • the pose of the current frame point cloud is constantly adjusted to make the current point cloud IOU coincides with the IOU in the point cloud map
  • the pose calculated above is the pose of the point cloud of the current frame
  • the pose can be represented by parameters of 6 dimensions (x, y, z, ⁇ , ⁇ , ⁇ )
  • the coordinate system of the pose can be the coordinate system of the roadbed sensor, (x, y, z) that is the freedom of movement along the three rectangular coordinate axes of x, y, z, ( ⁇ , ⁇ , ⁇ ) around these three Rotational degrees of freedom of the coordinate axis.
  • the offset threshold includes a translation offset threshold and/or an angle offset threshold
  • the reference pose is the pose when the point cloud acquisition device generates the point cloud map.
  • the pose mechanism can calculate the pose adjustment parameters between the current pose and the preset reference pose according to the spatial geometric relationship.
  • the pose adjustment parameters include the amount of rotation (rx, ry, rz) and the amount of translation (dx, dy) , Dz), the amount of rotation indicates the angle of x-axis, y-axis, or z-axis rotation, and the amount of translation indicates the distance of translation along the x-axis, y-axis or z-axis, so that the current pose of the roadbed sensor can be adjusted to the reference pose.
  • the method further includes:
  • the pose abnormality prompt information is sent to the user terminal, and the pose abnormality information indicates the pose of the point cloud collection device An exception occurs.
  • the type of the posture abnormal prompt information may be a short message, an instant messaging message, an email or a multimedia message, etc., which is not limited in the embodiment of the present application.
  • S204 Control a mechanical device based on the pose adjustment parameter to adjust the point cloud acquisition device from the current pose to the reference pose.
  • the pose correction device sends a control signal to the mechanical device.
  • the control signal instructs the mechanical device to translate and rotate according to the pose adjustment parameters calculated in S204.
  • the mechanical device can be a six-degree-of-freedom mechanical arm or platform, etc., the mechanical device
  • the point cloud acquisition device is driven to perform the pose adjustment, so that the point cloud acquisition device is adjusted from the current pose to the reference pose.
  • the current pose of the point cloud acquisition device in the preset point cloud map is determined according to the current frame point cloud; the offset between the current pose and the preset reference pose is greater than the offset
  • the pose adjustment parameters are calculated; based on the pose adjustment parameters, the mechanical device is driven to adjust the point cloud acquisition device from the current pose to the reference pose, so as to automatically correct the pose of the roadbed sensor and solve the problem of manual processing. Inefficiency and inaccuracy caused by pose adjustment.
  • the device 3 shown in FIG. 6 can implement the pose correction method of the roadbed sensor in the embodiment shown in FIG. 2.
  • the device 3 includes an acquisition unit 301, a pose determination unit 302, an adjustment calculation unit 303 and a control unit 304.
  • the acquiring unit 301 is configured to acquire the current frame point cloud scanned and generated by the point cloud acquisition device;
  • the pose determining unit 302 is configured to determine the current pose of the point cloud acquisition device in a preset point cloud map according to the current frame point cloud;
  • the adjustment calculation unit 303 is configured to calculate the pose adjustment parameter when the offset between the current pose and the preset reference pose is greater than the offset threshold;
  • the control unit 304 is configured to control a mechanical device to adjust the point cloud acquisition device from the current pose to the reference pose based on the pose adjustment parameter.
  • the device 3 further includes:
  • the map generating unit is used to collect point clouds in n fields of view through the point cloud acquisition device; wherein there is an overlap area between two adjacent fields of view in the n fields of view, and n is an integer greater than 1. ;
  • the point cloud map is obtained by stitching the n point clouds based on a point cloud registration algorithm.
  • the sum of the horizontal angles of the n fields of view is greater than 360 degrees.
  • the acquiring unit 301 is specifically configured to:
  • the device 3 further includes:
  • the prompting unit is configured to send a pose abnormality prompt information to the user terminal when the offset between the current pose and the preset reference pose is greater than the offset threshold, and the pose abnormality information represents a point cloud The pose of the acquisition device is abnormal.
  • the prompting unit is further configured to: when the number of point clouds in the current frame point cloud is less than a preset number, send shielding prompt information to the user terminal, where the shielding prompt information is used to indicate the The point cloud collection device is blocked.
  • the pose determination unit 302 is specifically configured to:
  • the device 3 may be a field-programmable gate array (FPGA), a dedicated integrated chip, a system on chip (SoC), and a central processor unit (CPU) that implement related functions.
  • FPGA field-programmable gate array
  • SoC system on chip
  • CPU central processor unit
  • NP network processor
  • MCU micro-controller unit
  • PLD programmable logic device
  • the foregoing describes in detail a pose correction method of a roadbed sensor according to an embodiment of the present application.
  • the following provides a pose correction device (hereinafter referred to as device 4) according to an embodiment of the present application.
  • Fig. 7 is a schematic structural diagram of a device provided by an embodiment of the application, hereinafter referred to as device 4, which can be integrated with the roadbed sensor of the above-mentioned embodiment.
  • the device includes: a memory 402, a processor 401, and a transmitter. 404 and receiver 403.
  • the memory 402 may be an independent physical unit, and may be connected to the processor 401, the transmitter 404, and the receiver 403 through a bus.
  • the memory 402, the processor 401, the transmitter 404, and the receiver 401 can also be integrated together and implemented by hardware.
  • the transmitter 404 is used for transmitting signals, and the receiver 403 is used for receiving signals.
  • the memory 402 is used to store a program that implements the above method embodiment or each module of the device embodiment, and the processor 401 calls the program to execute the operation of the above method embodiment.
  • the device may also only include a processor.
  • the memory for storing the program is located outside the device, and the processor is connected to the memory through a circuit/wire for reading and executing the program stored in the memory.
  • the processor may be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.
  • CPU central processing unit
  • NP network processor
  • the processor may further include a hardware chip.
  • the above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.
  • the memory may include volatile memory (volatile memory), such as random-access memory (RAM); the memory may also include non-volatile memory (non-volatile memory), such as flash memory (flash memory) , A hard disk drive (HDD) or a solid-state drive (solid-state drive, SSD); the memory may also include a combination of the foregoing types of memory.
  • volatile memory such as random-access memory (RAM)
  • non-volatile memory such as flash memory (flash memory)
  • flash memory flash memory
  • HDD hard disk drive
  • solid-state drive solid-state drive
  • the sending unit or transmitter executes the steps sent by the foregoing method embodiments
  • the receiving unit or receiver executes the steps received by the foregoing method embodiments
  • other steps are executed by other units or processors.
  • the sending unit and the receiving unit can form a transceiver unit
  • the receiver and transmitter can form a transceiver.
  • the embodiment of the present application also provides a computer storage medium storing a computer program, and the computer program is used to execute the pose correction method of the roadbed sensor provided in the above-mentioned embodiment.
  • the embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, cause the computer to execute the method for correcting the pose of the roadbed sensor provided in the above-mentioned embodiments.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

Abstract

本申请公开了一种路基传感器的位姿校正方法、装置和路基传感器。本申请根据当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；在当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；基于位姿调整参数驱动机械装置将点云采集装置由所述当前位姿调整为所述基准位姿，实现自动校正路基传感器的位姿，提高路基传感器位姿校正的效率和精度。

Description

路基传感器的位姿校正方法、装置和路基传感器 技术领域
本申请涉及自动驾驶领域，尤其涉及一种路基传感器的位姿校正方法、装置和路基传感器。
背景技术
路基传感器一般安装于道路的两侧或上方，路基传感器上设置有点云采集装置(例如：路基传感器、深度相机等)，路基传感器通过点云采集装置探测道路上的路况。由于外界振动、恶劣天气或其他因素影响，路基传感器的位置可能会发生偏移，这样会导致路基传感器无法正常探测有效的路况，从而影响到路基传感器的正常使用，例如：原本路基传感器可以360度监控道路的路况，由于外界影响路基传感器发生倾斜，点云采集装置只能探测到部分道路的路况。在相关技术中，一般通过人工来排查路基传感器的位置是否发生异常，人工排查的方式存在的问题是：效率较低，排查大范围内数量众多的路基传感器视需要耗费大量时间，人力成本很高；同时人工排查的准确度不高，可能出现漏查的情况。
发明内容
本申请实施例所要解决的技术问题在于，提供一种路基传感器的位姿校正方法、装置和路基传感器，可以基于根据扫描生成的当前帧点云在点云地图中的当前位姿，根据当前位姿和基准位姿之间偏差自动调整路基传感器的位姿，提高位姿调整的效率和准确度。
第一方面，本申请提供了一种路基传感器的位姿校正方法，包括：
获取点云采集装置扫描生成的当前帧点云；
根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；
在当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；
基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
在一种可能的设计中，所述获取点云采集装置扫描生成的当前帧点云之前，还包括：
通过所述点云采集装置在n个视场内各自采集点云；其中，n个视场中相邻的两个视场之间存在重合区域，n为大于1的整数；
基于点云配准算法将所述n个点云进行拼接得所述点云地图。
在一种可能的设计中，n个视场的水平角度之和大于360度。
在一种可能的设计中，所述获取点云采集装置扫描生成的当前帧点云包括：
获取点云采集装置当前周期在全量程范围内扫描得到的第一点云；
根据预设的距离区间在所述第一点云中进行筛选得到当前帧点云。
在一种可能的设计中，还包括：
在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，向用户终端发送位姿异常提示信息，所述位姿异常信息表示点云采集装置的位姿发生异常。
在一种可能的设计中，还包括：
在所述当前帧点云中点云数量小于预设数量时，向用户终端发送遮挡提示信息，所述遮挡提示信息用于表示所述点云采集装置发生遮挡。
在一种可能的设计中，所述根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿，包括：
确定所述当前帧点云的交并比区域和所述点云地图中对应的交并比区域；
基于点云配准算法计算所述当前帧点云中的并交比区域和所述点云地图中的并交比区域之间的位姿变换关系；
根据所述位姿变换关系计算所述当前位姿。
第二方面，本申请提供了一种路基传感器的位姿校正装置，包括：
获取单元，用于获取点云采集装置扫描生成的当前帧点云；
姿态确定单元，用于根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；
调整量计算单元，用于在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；
控制单元，用于基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
本申请的又一方面公开了一种路基传感器的姿态校正装置，姿态校正装置包括：接收器、发射器、存储器和处理器；其中，所述存储器中存储一组程序代码，且所述处理器用于调用所述存储器中存储的程序代码，执行上述各方面所述的路基传感器的位姿校正方法。
基于同一申请构思，由于该装置解决问题的原理以及有益效果可以参见上述各可能的距离补偿装置的方法实施方式以及所带来的有益效果，因此该装置的实施可以参见方法的实施，重复之处不再赘述。
本申请的又一方面提了供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
本申请的又一方面提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
在本申请实施例中，根据当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；在当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；基于位姿调整参数驱动机械装置将点云采集装置由所述当前位姿调整为所述基准位姿，实现自动校正路基传感器的位姿，解决人工进行位姿调整带来的效率低和不准确的问题。
附图说明
为了更清楚地说明本申请实施例或背景技术中的技术方案，下面将对本申请实施例或背景技术中所需要使用的附图进行说明。
图1是本申请实施例提供的路基传感器的部署示意图；
图2是本申请实施例提供的一种路基传感器的位姿校正方法的流程示意图；
图3是本实施例提供的视场的原理示意图；
图4和图5是本申请实施例提供的点云拼接的原理示意图；
图6是本申请实施例提供的一种基于位姿校正装置的结构示意图；
图7是本申请实施例提供的一种基于位姿校正装置的另一结构示意图。
具体实施方式
为使得本申请实施例的发明目的、特征、优点能够更加的明显和易懂，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而非全部实施例。基于本申请中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在本申请的描述中，需要理解的是，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本申请中的具体含义。
参见图1，为本申请实施例提供的路基传感器的部署示意图，路基传感器101～103部署在道路的两侧。路基传感器包括位姿校正装置、点云采集装置和机械装置，点云采集装置可以探测道路上的路况，例如：点云采集装置用于周期性地发射探测信号，探测信号遇到道路上的车辆104后生成回波信号，点云采集装置根据回波信号生成点云；点云采集装置可以为激光雷达或深度相机等。机械装置可以为进行六自由度进行活动的装置，机械装置可以是机械臂或六自由度平台，机械装置可以带动点云采集装置沿着x轴、y轴和z轴方向进行平移，以及绕着x轴、y轴和z轴进行旋转。位姿校正装置用于对点云采集装置采集到的点云进行后续的处理，例如：位姿的确定和位姿调整量的计算等。
请参见图2，图2是本申请实施例提供的一种位姿校正方法，该方法包括但不限于如下步骤：
S201、获取点云采集装置扫描生成的当前帧点云。
其中，点云采集装置可以周期性地进行扫描，每次扫描后生成一帧点云，位姿校正装置获取点云采集装置在当前周期扫描生成的当前帧点云，点云可以是3D点云，即点云包括三维空间坐标(基于点云采集装置的坐标系)和回波强度。点云的数量和密度与点云采集装置的性能有关，例如：点云采集装置的线数越多，点云的密度越大；点云采集装置的视场越大，点云的数量越多。
在一个或多个实施例中，由于距离过近的点可能落在机械装置上，距离过远的点已经非常稀疏，这两种类型的点对位姿识别的影响不大，为了降低运算量，本实施例将上述两种类型的点进行过滤，具体方法包括：位姿校正装置预先设置有距离区间，点云采集装置在全量程范围内进行一次扫描得到第一点云后，根据距离区间对第一点云进行筛选，筛选后的点云对应的距离均落在距离区间，将筛选后的点云作为当前帧点云。
例如：点云采集装置为激光雷达，激光雷达的全量程范围为0米～20米，激光雷达在当前周期扫描全量程范围对应的第一点云。激光雷达预设的距离区间为1m～5m，激光雷达 遍历第一点云中各个点对应的距离，将距离落在距离区间1m～5m的点作为当前帧点云。
在一个或多个实施例中，点云采集装置的镜头可能会被异物遮挡，这样会影响点云采集装置的探测效果，无法准确的反映视场内的情况，本实施例为了探测点云采集装置的镜头是否被遮挡，统计点云采集装置在当前周期采集在全量程范围采集的当前帧点云的数量，在当前帧点云的数量小于预设数量时，向用户终端发送遮挡提示信息，遮挡提示信息用于提示用户点云采集装置被遮挡。预设数量与点云采集装置的线数、视场大小和扫描频率有关。例如：预设数量为10000，点云采集装置在当前周期采集到的当前帧点云的数量小于10000时，向用户预先绑定的移动终端发送遮挡提示信息，遮挡提示信息的类型可以是短消息、即时通信消息、电子邮件或彩信等，本申请实施例不作限制。
S202、根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿。
其中，位姿校正装置预存储或预配置有点云地图，点云地图是点云采集装置在基准位姿下采集到的多帧点云拼接得到的，例如：维护人员在路基传感器安装完毕之后对调试点云采集装置的位姿以达到基准位姿，然后点云采集装置在n个视场下采集得到n个点云，视场表示点云采集装置的扫描范围，视场的范围由水平角度和垂直角度决定，例如：水平角度为-30度～+30度，垂直角度为-15度～+15度；n个视场中相邻的两个视场相互重合，即相邻的两个视场采集到的点云相互重合，一个视场对应一个点云，根据点云配准算法将n个点云进行拼接得到完整的点云地图。进一步的，n个视场的水平角度之和大于360度，即点云采集装置可以在360度的水平方向上进行扫描。
参见图3所示，激光雷达在6个视场内采集点云，分别得到点云1、点云2、点云3、点云4、点云5和点云6，6个点云中相邻的两个点云之间存在重合区域，例如，点云2和点云3之间存在重合区域，点A为重合区域中的一个点，将点云1～点云6进行拼接得到静态的点云地图。
在一个或多个实施例中，基于点云配准算法对多个点云进行拼接得到点云地图，点云配置算法可以是ICP(Iterative Closest Point，迭代最近点)算法或NDT(Normal Distributions Transform，正态分布转换)算法。
例如：参见图4和图5所示，针对点云A和点云B的拼接过程进行说明：点云A和点云B可以进行拼接的条件是二者存在IOU(Intersection-over-Union，交并比区域)，IOU也可称重合区域或共同区域，IOU区域是点云A和点云B进行拼接的线索。点云A和点云B为3D点云，因此点云A和点云B均具有轮廓特征，点云A固定不动，点云B不断调整其位姿(位置和朝向)，当前点云A中的IOU和点云B中的IOU处于相同位姿时(如图5所示的情形)，那么点云A和点云B拼接成功，拼接后的点云为图5所示。
在本实施例中，根据当前帧点云确定点云采集帧在点云地图中的当前位姿的方法包括：确定所述当前帧点云的交并比区域和所述点云地图中对应的交并比区域；基于点云配准算法计算所述当前帧点云中的并交比区域和所述点云地图中的并交比区域之间的位姿变换关系；根据所述位姿变换关系计算所述当前位姿。其中，点云配准算法可以为ICP算法或NDT算法。
其中，在本实施例中，利用ICP算法的确定当前位姿的过程包括：
1)根据当前帧点云中的点坐标，在点云地图上搜索相应就近点点集。
2)计算两个点集(当前帧点云和点云地图)的重心位置坐标，并进行点集中心化生成新的点集。
3)由新的点集计算正定矩阵N，并计算N的最大特征值及其最大特征向量。
4)由于最大特征向量等价于残差平方和最小时的旋转四元数，将四元数转换为旋转矩阵R。
5)在旋转矩阵R确定后，由平移向量t仅仅是两个点集的重心差异，可以通过两个坐标系中的重心点和旋转矩阵确定。
6)由当前帧点云Plk计算旋转后的点云P’lk。通过当前帧点云Plk与点云P’lk计算距离平方和值为fk+1，以连续两次距离平方和之差绝对值作为迭代判断数值。
7)当迭代判断数值大于一个阈值时，就停止迭代，否则重复1至6步，直到满足条件后停止迭代。
其中，在本实施例中，利用NDT算法确定当前位姿的过程包括：
1)将点云地图所占的空间划分成指定大小(CellSize)的网格或体素(Voxel)；并计算每个网格的多维正态分布参数。
2)初始化变换参数p(赋予零值或者使用里程计数据赋值)。
3)对于要配准的当前帧点云，通过变换T将其转换到点云地图的网格中。
4)根据正态分布参数计算每个转换点的概率密度。
5)计算NDT配准得分，NDT配准得分(score)通过对每个网格计算出的概率密度相加得到。
6)根据牛顿优化算法对目标函数-score-score进行优化，即寻找变换参数p使得score的值最大。
7)跳转到第3步继续执行，直到达到收敛条件为止。
例如：点云配准过程可参照图4和图5的构建点云地图的过程，当前帧点云和精度地图之间同样存在IOU，不断调整当前帧点云的位姿，使当前点云的IOU和点云地图中的IOU重合，那么上述计算的位姿即为当前帧点云的位姿，位姿可以使用6个维度的参数来表示(x，y，z，α，β，γ)，位姿的坐标系可以是路基传感器的坐标系，(x，y，z)即沿x、y、z三个直角坐标轴方向的移动自由度，(α，β，γ)绕这三个坐标轴的转动自由度。
S203、在当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数。
其中，偏移量阈值包括平移偏移阈值和/或角度偏移阈值，基准位姿即点云采集装置生成点云地图时的位姿。位姿机械装置可以根据空间几何关系计算当前位姿和预设的的基准位姿之间的位姿调整参数，位姿调整参数包括旋转量(rx，ry，rz)和平移量(dx，dy，dz)，旋转量表示饶x轴、y轴或z轴旋转的角度，平移量表示沿x轴、y轴或z轴平移的距离，以便于将路基传感器当前位姿调整为基准位姿。
在一个或多个实施例中，所述方法还包括：
在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，向用户终端发送位姿异常提示信息，所述位姿异常信息表示点云采集装置的位姿发生异常。位姿异常提示信息的类型可以是短消息、即时通信消息、电子邮件或彩信等，本申请实施例不作限制。
S204、基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
其中，位姿校正装置向机械装置发送控制信号，控制信号指示机械装置根据S204中计算得到的位姿调整参数进行平移和旋转，机械装置可以为一个六自由度的机械臂或平台等，机械装置根据S204计算得到的位姿调整参数带动点云采集装置进行位姿调整，以使点云采 集装置由当前位姿调整为基准位姿。
根据图2的描述，根据当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；在当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；基于位姿调整参数驱动机械装置将点云采集装置由所述当前位姿调整为所述基准位姿，实现自动校正路基传感器的位姿，解决人工进行位姿调整带来的效率低和不准确的问题。
上述详细阐述了本申请实施例的一种路基传感器的位姿校正方法，下面提供了本申请实施例的一种路基传感器的位姿校正装置(以下简称装置3)。
图6所示的装置3可以实现图2所示实施例的路基传感器的位姿校正方法，装置3包括获取单元301、位姿确定单元302、调整量计算单元303和控制单元304。
获取单元301，用于获取点云采集装置扫描生成的当前帧点云；
位姿确定单元302，用于根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；
调整量计算单元303，用于在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；
控制单元304，用于基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
在一个或多个实施例中，装置3还包括：
地图生成单元，用于通过所述点云采集装置在n个视场内各自采集点云；其中，n个视场中相邻的两个视场之间存在重合区域，n为大于1的整数；
基于点云配准算法将所述n个点云进行拼接得所述点云地图。
在一个或多个实施例中，所述n个视场的水平角度之和大于360度。
在一个或多个实施例中，所述获取单元301具体用于：
获取点云采集装置当前周期在全量程范围内扫描得到的第一点云；
根据预设的距离区间在所述第一点云中进行筛选得到当前帧点云。
在一个或多个实施例中，装置3还包括：
提示单元，用于在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，向用户终端发送位姿异常提示信息，所述位姿异常信息表示点云采集装置的位姿发生异常。
在一个或多个实施例中，提示单元还用于：在所述当前帧点云中点云数量小于预设数量时，向用户终端发送遮挡提示信息，所述遮挡提示信息用于表示所述点云采集装置发生遮挡。
在一个或多个实施例中，位姿确定单元302具体用于：
确定所述当前帧点云的交并比区域和所述点云地图中对应的交并比区域；
基于点云配准算法计算所述当前帧点云中的并交比区域和所述点云地图中的并交比区域之间的位姿变换关系；
根据所述位姿变换关系计算所述当前位姿。
本申请实施例和图1～图5的方法实施例基于同一构思，其带来的技术效果也相同，具体过程可参照图1～图5的方法实施例的描述，此处不再赘述。
所述装置3可以为实现相关功能的现场可编程门阵列(field-programmable gate array，FPGA)，专用集成芯片，系统芯片(system on chip，SoC)，中央处理器(central processor unit，CPU)，网络处理器(network processor，NP)，数字信号处理电路，微位姿校正装 置(micro controller unit，MCU)，还可以采用可编程逻辑装置(programmable logic device，PLD)或其他集成芯片。
上述详细阐述了本申请实施例的一种路基传感器的位姿校正方法，下面提供了本申请实施例的一种位姿校正装置(以下简称装置4)。
图7为本申请实施例提供的一种装置结构示意图，以下简称装置4，装置4可以集成于上述实施例的路基传感器，如图4所示，该装置包括：存储器402、处理器401、发射器404以及接收器403。
存储器402可以是独立的物理单元，与处理器401、发射器404以及接收器403可以通过总线连接。存储器402、处理器401、发射器404以及接收器401也可以集成在一起，通过硬件实现等。
发射器404用于发射信号，接收器403用于接收信号。
存储器402用于存储实现以上方法实施例，或者装置实施例各个模块的程序，处理器401调用该程序，执行以上方法实施例的操作。
可选地，当上述实施例的路基传感器的位姿校正方法中的部分或全部通过软件实现时，装置也可以只包括处理器。用于存储程序的存储器位于装置之外，处理器通过电路/电线与存储器连接，用于读取并执行存储器中存储的程序。
处理器可以是中央处理器(central processing unit，CPU)，网络处理器(network processor，NP)或者CPU和NP的组合。
处理器还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。
存储器可以包括易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；存储器也可以包括非易失性存储器(non-volatile memory)，例如快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；存储器还可以包括上述种类的存储器的组合。
上述实施例中，发送单元或发射器执行上述各个方法实施例发送的步骤，接收单元或接收器执行上述各个方法实施例接收的步骤，其它步骤由其他单元或处理器执行。发送单元和接收单元可以组成收发单元，接收器和发射器可以组成收发器。
本申请实施例还提供了一种计算机存储介质，存储有计算机程序，该计算机程序用于执行上述实施例提供的路基传感器的位姿校正方法。
本申请实施例还提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述实施例提供的路基传感器的位姿校正方法。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实 施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。

Claims (11)

  1. 一种路基传感器的位姿校正方法，其特征在于，包括：
    获取点云采集装置扫描生成的当前帧点云；
    根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿；
    在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；
    基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
  2. 根据权利要求1所述的方法，所述获取点云采集装置扫描生成的当前帧点云之前，还包括：
    通过所述点云采集装置在n个视场内各自采集点云；其中，n个视场中相邻的两个视场之间存在重合区域，n为大于1的整数；
    基于点云配准算法将所述n个点云进行拼接得所述点云地图。
  3. 根据权利要求2所述的方法，其特征在于，所述n个视场的水平角度之和大于360度。
  4. 根据权利要求1所述的方法，其特征在于，所述获取点云采集装置扫描生成的当前帧点云包括：
    获取点云采集装置当前周期在全量程范围内扫描得到的第一点云；
    根据预设的距离区间在所述第一点云中进行筛选得到当前帧点云。
  5. 根据权利要求1所述的方法，其特征在于，还包括：
    在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，向用户终端发送位姿异常提示信息，所述位姿异常信息表示点云采集装置的位姿发生异常。
  6. 根据权利要求1所述的方法，其特征在于，还包括：
    在所述当前帧点云中点云数量小于预设数量时，向用户终端发送遮挡提示信息，所述遮挡提示信息用于表示所述点云采集装置发生遮挡。
  7. 根据根据权利要求1所述的方法，其特征在于，所述根据所述当前帧点云确定所述点云采集装置在预设的点云地图中的当前位姿，包括：
    确定所述当前帧点云的交并比区域和所述点云地图中对应的交并比区域；
    基于点云配准算法计算所述当前帧点云中的并交比区域和所述点云地图中的并交比区域之间的位姿变换关系；
    根据所述位姿变换关系计算所述当前位姿。
  8. 一种路基传感器的位姿校正装置，其特征在于，包括：
    获取单元，用于获取点云采集装置扫描生成的当前帧点云；
    位姿确定单元，用于根据所述当前帧点云确定所述点云采集装置在预设的点云地图中 的当前位姿；
    调整量计算单元，用于在所述当前位姿和预设的基准位姿之间的偏移量大于偏移量阈值时，计算位姿调整参数；
    控制单元，用于基于所述位姿调整参数控制机械装置将所述点云采集装置由所述当前位姿调整为所述基准位姿。
  9. 一种计算机程序产品，其特征在于，所述计算机程序产品包括指令，当所述计算机程序产品在计算机上运行时，使得计算机执行如权利要求1至6任意一项所述的方法。
  10. 一种路基传感器的位姿校正装置，其特征在于，包括处理器和存储器，存储器用于存储计算机程序或指令，所述处理器用于执行所述存储器中的计算机程序或指令实现如权利要求1至7任意一项所述的方法。
  11. 一种路基传感器，其特征在于，包括：如权利要求8或9所述的位姿校正装置、点云采集装置和机械装置；其中，所述机械装置用于承载所述点云采集装置。
PCT/CN2020/081848 2020-03-27 2020-03-27 路基传感器的位姿校正方法、装置和路基传感器 WO2021189479A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080005468.3A CN113748693B (zh) 2020-03-27 2020-03-27 路基传感器的位姿校正方法、装置和路基传感器
PCT/CN2020/081848 WO2021189479A1 (zh) 2020-03-27 2020-03-27 路基传感器的位姿校正方法、装置和路基传感器

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/081848 WO2021189479A1 (zh) 2020-03-27 2020-03-27 路基传感器的位姿校正方法、装置和路基传感器

Publications (1)

Publication Number Publication Date
WO2021189479A1 true WO2021189479A1 (zh) 2021-09-30

Family

ID=77889897

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081848 WO2021189479A1 (zh) 2020-03-27 2020-03-27 路基传感器的位姿校正方法、装置和路基传感器

Country Status (2)

Country Link
CN (1) CN113748693B (zh)
WO (1) WO2021189479A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115235525A (zh) * 2021-12-07 2022-10-25 上海仙途智能科技有限公司 传感器检测方法、装置、电子设备及可读储存介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116413702A (zh) * 2021-12-30 2023-07-11 上海禾赛科技有限公司 激光雷达位姿的诊断方法、激光雷达及自动驾驶车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107167788A (zh) * 2017-03-21 2017-09-15 深圳市速腾聚创科技有限公司 获取激光雷达校准参数、激光雷达校准的方法及系统
US10127434B2 (en) * 2016-07-15 2018-11-13 Tyco Fire & Security Gmbh Techniques for built environment representations
CN110084116A (zh) * 2019-03-22 2019-08-02 深圳市速腾聚创科技有限公司 路面检测方法、装置、计算机设备和存储介质
CN110260867A (zh) * 2019-07-29 2019-09-20 浙江大华技术股份有限公司 一种机器人导航中位姿确定、纠正的方法、设备及装置
CN110879400A (zh) * 2019-11-27 2020-03-13 炬星科技（深圳）有限公司 激光雷达与imu融合定位的方法、设备及存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201116961D0 (en) * 2011-09-30 2011-11-16 Bae Systems Plc Fast calibration for lidars
CN104091321B (zh) * 2014-04-14 2016-10-19 北京师范大学 适用于地面激光雷达点云分类的多层次点集特征的提取方法
CN105976353B (zh) * 2016-04-14 2020-01-24 南京理工大学 基于模型和点云全局匹配的空间非合作目标位姿估计方法
CN107564062B (zh) * 2017-08-16 2020-06-19 清华大学 位姿异常检测方法及装置
US11475351B2 (en) * 2017-11-15 2022-10-18 Uatc, Llc Systems and methods for object detection, tracking, and motion prediction
CN108932736B (zh) * 2018-05-30 2022-10-11 南昌大学 二维激光雷达点云数据处理方法以及动态机器人位姿校准方法
CN109544630B (zh) * 2018-11-30 2021-02-02 南京人工智能高等研究院有限公司 位姿信息确定方法和装置、视觉点云构建方法和装置
CN109633665A (zh) * 2018-12-17 2019-04-16 北京主线科技有限公司 交通场景稀疏激光点云拼接方法
CN110084832B (zh) * 2019-04-25 2021-03-23 亮风台（上海）信息科技有限公司 相机位姿的纠正方法、装置、系统、设备和存储介质
CN110658530B (zh) * 2019-08-01 2024-02-23 北京联合大学 一种基于双激光雷达数据融合的地图构建方法、系统及地图

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10127434B2 (en) * 2016-07-15 2018-11-13 Tyco Fire & Security Gmbh Techniques for built environment representations
CN107167788A (zh) * 2017-03-21 2017-09-15 深圳市速腾聚创科技有限公司 获取激光雷达校准参数、激光雷达校准的方法及系统
CN110084116A (zh) * 2019-03-22 2019-08-02 深圳市速腾聚创科技有限公司 路面检测方法、装置、计算机设备和存储介质
CN110260867A (zh) * 2019-07-29 2019-09-20 浙江大华技术股份有限公司 一种机器人导航中位姿确定、纠正的方法、设备及装置
CN110879400A (zh) * 2019-11-27 2020-03-13 炬星科技（深圳）有限公司 激光雷达与imu融合定位的方法、设备及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115235525A (zh) * 2021-12-07 2022-10-25 上海仙途智能科技有限公司 传感器检测方法、装置、电子设备及可读储存介质

Also Published As

Publication number Publication date
CN113748693B (zh) 2023-09-15
CN113748693A (zh) 2021-12-03

Similar Documents

Publication Publication Date Title
JP6967715B2 (ja) カメラ校正方法、カメラ校正プログラム及びカメラ校正装置
JP6975929B2 (ja) カメラ校正方法、カメラ校正プログラム及びカメラ校正装置
WO2021189468A1 (zh) 激光雷达的姿态校正方法、装置和系统
CN111598770B (zh) 一种基于三维数据和二维图像的物体检测方法和装置
WO2021189479A1 (zh) 路基传感器的位姿校正方法、装置和路基传感器
JP6649743B2 (ja) 一致性評価装置および一致性評価方法
JP2022515225A (ja) センサキャリブレーション方法及び装置、記憶媒体、キャリブレーションシステム並びにプログラム製品
JP2014169990A (ja) 位置姿勢計測装置及び方法
CN111142514B (zh) 一种机器人及其避障方法和装置
JP2016197287A (ja) 情報処理装置、情報処理方法、プログラム
CN104517318A (zh) 三维量测模拟取点系统及方法
CN112381026A (zh) 航道岸线检测方法、系统、装置和存储介质
JP2013205175A (ja) ３次元対象面認識装置および方法、ならびにプログラム
JP2017524122A (ja) モバイルプラットフォームの変位を計測する方法及び装置
US20230267593A1 (en) Workpiece measurement method, workpiece measurement system, and program
CN110597249A (zh) 一种机器人及其回充定位方法和装置
AU2022259832A1 (en) Target detection in a point cloud
EP4229588A1 (en) System and method for extracting and measuring shapes of objects having curved surfaces with a vision system
CN116524109B (zh) 一种基于WebGL的三维桥梁可视化方法及相关设备
CN115046498B (zh) 一种单目旋转结构光三维测量系统标定方法
CN115507840A (zh) 一种栅格地图构建方法、栅格地图构建装置及电子设备
CN117387572A (zh) 水平度校验方法、终端和计算机可读存储介质
CN112084854B (zh) 一种障碍物检测方法、障碍物检测装置及机器人
CN112818428B (zh) 一种用于cad模型面结构光全自动扫描路径规划方法
JP6548789B2 (ja) 位置姿勢計測装置及び方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20926576

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11/01/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20926576

Country of ref document: EP

Kind code of ref document: A1