WO2022267434A1 - 获取物体点云数据的系统及方法 - Google Patents

获取物体点云数据的系统及方法 Download PDF

Info

Publication number
WO2022267434A1
WO2022267434A1 PCT/CN2021/143974 CN2021143974W WO2022267434A1 WO 2022267434 A1 WO2022267434 A1 WO 2022267434A1 CN 2021143974 W CN2021143974 W CN 2021143974W WO 2022267434 A1 WO2022267434 A1 WO 2022267434A1
Authority
WO
WIPO (PCT)
Prior art keywords
infrared light
target object
point cloud
cloud data
light emitting
Prior art date
Application number
PCT/CN2021/143974
Other languages
English (en)
French (fr)
Inventor
刘亦芃
杜国光
赵开勇
Original Assignee
达闼机器人股份有限公司
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 达闼机器人股份有限公司 filed Critical 达闼机器人股份有限公司
Publication of WO2022267434A1 publication Critical patent/WO2022267434A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/143—Sensing or illuminating at different wavelengths
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Definitions

  • the present disclosure relates to the field of computer vision, and in particular, to a system and method for acquiring object point cloud data.
  • 3D detection and positioning of the object is required at the algorithm level.
  • the best method for 3D detection and positioning is to use the point cloud data of the object or deep learning algorithms in other 3D data formats or the traditional ICP (Iterative Closest Point, iterative closest point algorithm) registration method.
  • Deep learning algorithms require a large number of 3D models as support, and ICP registration also requires a complete point cloud model to build a database. No matter which algorithm requires object 3D models as support.
  • 3D models can be obtained through 3D scanning, but this method is costly and cannot handle transparent and reflective surfaces; it can also be achieved through MVS (Multi-View Stereo, multi-view stereo geometry), but MVS relies on image features and cannot handle Objects with poorly textured surfaces are slow to process.
  • MVS Multi-View Stereo, multi-view stereo geometry
  • the present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.
  • the embodiment of the first aspect of the present disclosure proposes a system for acquiring object point cloud data, the system includes: an infrared light emitting device, an infrared light receiving device, a photoelectric converter, and a storage table;
  • the infrared light emitting device, the storage table and the infrared light receiving device are sequentially arranged in the same linear direction;
  • the storage table includes a storage table body and a turntable that is rotatable relative to the storage table body, and the turntable is used to place a target object;
  • the infrared light receiving device is used to receive the infrared light emitted by the infrared light emitting device to the target object on the turntable in a rotating state;
  • the photoelectric converter is connected to the infrared light receiving device, and the photoelectric conversion device is used to photoelectrically convert the infrared light to obtain multiple images, and the multiple images are used to obtain the points of the target object cloud data.
  • the system further includes a synchronous translation device, the synchronous translation device includes a base and two mutually parallel slide plates slidable relative to the base;
  • the infrared light emitting device and the infrared light receiving device are respectively arranged on the two mutually parallel slide plates, so that the infrared light emitting device and the infrared light receiving device can move along the horizontal direction of the target object and/or vertical swipe synchronously.
  • the infrared light emitting direction of the infrared light emitting device is parallel to the object placement surface of the turntable.
  • the infrared light emitting device includes an infrared emitting array, and the infrared emitting array is composed of a plurality of infrared light emitting units.
  • the infrared light receiving device includes an infrared receiving array, and the infrared receiving array is composed of a plurality of infrared light receiving units;
  • the number of the infrared light receiving units is the same as the number of the infrared light emitting units, and the positions correspond to each other.
  • the infrared light emitted by the infrared emitting array constitutes an infrared region, and the infrared region covers the target object.
  • the frequency of infrared light emitted by the infrared light emitting device is consistent with the rotation frequency of the turntable.
  • the system further includes a processing module connected to the photoelectric converter, and the processing module is configured to acquire point cloud data of the target object according to the multiple images.
  • the processing module acquires point cloud data of the target object according to the multiple images, including:
  • the point cloud data of the target object is obtained according to the edge information.
  • the processing module acquires edge information of the target object according to the multiple images, including:
  • the processing module obtains the point cloud data of the target object according to the edge information, including:
  • the polygons are stacked according to the hierarchical spatial positions to obtain the point cloud data of the target object.
  • the target object is set between the infrared light emitting device and the infrared light receiving device, and the turntable is set to rotate the target object, and the infrared image obtained when the turntable rotates the target object Light, photoelectric conversion, to obtain the image of the target object, no need to install a camera device, save space, eliminate the perspective projection effect, the edge information of the target object obtained through the image of the target object is more accurate, and is not affected by ambient light and object surface texture influences.
  • the embodiment of the second aspect of the present disclosure proposes a method for obtaining object point cloud data, which is applied to the system for obtaining object point cloud data described in the first aspect, and the method includes:
  • controlling the photoelectric conversion device to photoelectrically convert the infrared light to obtain multiple images
  • the acquiring point cloud data of the target object according to the multiple images includes:
  • the point cloud data of the target object is obtained according to the edge information.
  • the acquiring edge information of the target object according to the multiple images includes:
  • the obtaining the point cloud data of the target object according to the edge information includes:
  • the polygons are stacked according to the hierarchical spatial positions to obtain the point cloud data of the target object.
  • the embodiment of the third aspect of the present disclosure provides a computing processing device, including the system described in the first aspect.
  • the embodiment of the fourth aspect of the present disclosure proposes a computer program, including computer readable codes, when the computer readable codes are run on a computing processing device, causing the computing processing device to execute the first aspect of the present disclosure.
  • the embodiment of the fifth aspect of the present disclosure provides a computer-readable storage medium, in which the computer program provided by the embodiment of the fourth aspect of the present disclosure is stored.
  • FIG. 1 provides a schematic diagram of a system for acquiring object point cloud data according to an embodiment of the present disclosure
  • FIG. 2 provides a flow chart of a processing module acquiring point cloud data of a target object for an embodiment of the present disclosure
  • FIG. 3 provides a flowchart of step S101 in obtaining point cloud data of a target object according to an embodiment of the present disclosure
  • FIG. 4 provides a flowchart of step S102 in obtaining point cloud data of a target object according to an embodiment of the present disclosure
  • FIG. 5 provides a schematic diagram of a processing module acquiring point cloud data of a target object for an embodiment of the present disclosure
  • FIG. 6 provides a block diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 7 provides a schematic structural diagram of a computing processing device according to an embodiment of the present disclosure.
  • Fig. 8 is a schematic diagram of a program code storage unit for portable or fixed implementation of the method according to the present disclosure provided by an embodiment of the present disclosure.
  • 3D detection and positioning is mainly based on deep learning algorithms using point clouds or other 3D data formats or Traditional ICP (Iterative Closest Point, nearest point iteration) registration method.
  • the deep learning algorithm is a data-driven algorithm that requires a large number of 3D models as support, and the ICP registration algorithm requires a complete point cloud model to build a database, that is, both algorithms require the 3D model of the object as support, and the 3D model consists of The point cloud data composition of the object.
  • the 3D model of the object in the related art can be obtained through 3D scanner, MVS (Multi-View Stereo, multi-view stereo geometry), through CAD (Computer Aided Design, computer-aided design) artificially designed object-specific 3D reconstruction model and object projection reconstruction algorithm .
  • the present disclosure provides a system for acquiring point cloud data of an object, which can obtain the point cloud data of the object without being affected by the shape, surface texture, material and ambient light of the object.
  • Fig. 1 provides a schematic diagram of a system for obtaining object point cloud data according to an embodiment of the present disclosure.
  • the system for obtaining object point cloud data includes: an infrared light emitting device, an infrared light receiving device, a photoelectric converter, and a storage device tower;
  • the infrared light emitting device, the storage table and the infrared light receiving device are sequentially arranged in the same straight line direction;
  • the storage table includes a storage table body and a turntable that is rotatable relative to the storage table body, and the turntable is used to place target objects;
  • the infrared light receiving device is used to receive the infrared light emitted by the infrared light emitting device to the target object on the rotating turntable;
  • the photoelectric converter is connected with the infrared light receiving device, and the photoelectric conversion device is used to photoelectrically convert the infrared light to obtain multiple images, and the multiple images are used to obtain point cloud data of the target object.
  • the system for obtaining object point cloud data sets the target object between the infrared light emitting device and the infrared light receiving device, sets the turntable to rotate the target object, and obtains the infrared light when the turntable rotates the target object on it, and performs Photoelectric conversion can obtain the image of the target object without setting up a camera device, which saves space and eliminates the perspective projection effect.
  • the edge information of the target object obtained through the image of the target object is more accurate and is not affected by ambient light and surface texture of the object.
  • the processing module connected to the photoelectric converter acquires the point cloud data of the target object according to multiple images.
  • the system for acquiring object point cloud data further includes a synchronous translation device, the synchronous translation device includes a base and two mutually parallel slide plates that can slide relative to the base;
  • the infrared light emitting device and the infrared light receiving device are respectively arranged on two mutually parallel sliding plates, so that the infrared light emitting device and the infrared light receiving device can slide synchronously along the horizontal direction and/or vertical direction of the target object.
  • the resolution of the obtained image is h*w.
  • the infrared light emitting device and the infrared light receiving device need to be translated h'/h times in the horizontal direction and w'/w times in the vertical direction through the synchronous translation device;
  • the horizontal translation step size is Ww/[(w-1 )w']
  • the translation step in the vertical direction is Hh/[(h-1)h']
  • the infrared light receiving device will h'w'/hw images with a resolution of h*w merged into a high-resolution image with a resolution of h'*w', where H is the height of the infrared light emitting device, and W is the width of the infrared light emitting device.
  • the infrared light emitting direction of the infrared light emitting device is parallel to the object placement surface of the turntable.
  • the infrared light emitted by the infrared light emitting device is infrared parallel light
  • the infrared receiving device receives the infrared parallel light emitted by the infrared emitting device, and passes the infrared parallel light to the target. Objects are scanned.
  • Adjusting the infrared light of the infrared light emitting device to be parallel to the object surface of the turntable can avoid deformation and distortion of the image obtained by the infrared light, and does not need to perform deformation correction processing on the image.
  • the infrared light emitting device includes an infrared light emitting array, and the infrared light emitting array is composed of a plurality of infrared light emitting units.
  • a plurality of infrared light emitting units form an infrared light emitting array according to a preset size, and the preset size can be preset according to the needs of the user or the size of the target object.
  • the infrared light emitting array has a high position H and a width of W, and is composed of h rows and w columns of infrared light emitting units, and the distance between each infrared light emitting unit in the horizontal direction is H/(h-1). The spacing in the vertical direction is W/(w-1).
  • Scanning the target object through the column of infrared light emission can shorten the time for acquiring the image of the target object and improve the efficiency of acquiring the image of the target object.
  • the infrared light emitting unit h'*w' times to obtain the image of the target object by emitting infrared light to the target object through a single infrared light emitting unit, while using an infrared light emitting array to emit infrared light to the target object can reduce the number of movements , which shortens the time to acquire the image of the target object to 1/h*w.
  • the infrared light receiving device includes an infrared receiving array, and the infrared receiving array is composed of a plurality of infrared light receiving units;
  • the number of infrared light receiving units is the same as the number of infrared light emitting units, and the positions correspond to each other.
  • the infrared light receiving array receives the infrared light emitted by the infrared light emitting array to the target object on the rotating turntable, records the position of the light signal, and obtains a sparse projection image of the target object.
  • the position is recorded as 0, and when the optical signal is not received, the position is recorded as 1, so as to obtain the optical signal corresponding to the target object, through
  • the photoelectric converter performs photoelectric conversion on all the obtained light signals to obtain the projected image of the target object.
  • the infrared light emitted by the infrared emitting array constitutes an infrared region, and the infrared region covers the target object.
  • the image of the target object is obtained through infrared light, which is not affected by ambient light and surface texture of the object.
  • the frequency of infrared light emitted by the infrared light emitting device is consistent with the rotation frequency of the turntable.
  • the frequency of the infrared light emitted by the infrared light emitting device By setting the frequency of the infrared light emitted by the infrared light emitting device to be consistent with the rotation frequency of the turntable, it is avoided that the obtained image is blurred and the point cloud data of the target object cannot be obtained.
  • the plane of the infrared light emitted by the lowest row of infrared light emitting units in the infrared light emitting array on the skateboard is lower than the plane of the turntable, and the infrared light emits the highest row of infrared light in the entire row.
  • the plane of the infrared light emitted by the emitting unit is higher than the plane where the highest position of the target object is located, that is, the infrared area formed by the infrared light emitted by the infrared light emitting array covers the target object, and there is no need to install a camera device, which saves space;
  • each infrared light receiving unit of the infrared light receiving array can receive the infrared light emitted by the infrared light emitting unit in the corresponding infrared light emitting array (the placed object Except for the occlusion of the platform), the perspective projection effect is eliminated, and it is not affected by the ambient light and the surface texture of the target object;
  • the turntable rotates, and the infrared light emission frequency is consistent with the rotation frequency;
  • the target object is scanned through the infrared light emission array and the infrared light reception array, and the scanning method can be line by line or column by line.
  • the infrared light receiving array sends the optical signal obtained by each scan to the photoelectric converter, and the photoelectric converter converts the optical signal into a digital signal and presents it in the form of an image;
  • the image of the point cloud data of the target object is obtained, and the point cloud data obtained through the image can more accurately reflect the edge state of the target object.
  • the system for acquiring point cloud data of an object further includes a processing module connected to the photoelectric converter, and the processing module is used to acquire point cloud data of the target object according to multiple images.
  • the point cloud data of the target object is obtained from multiple images through the processing module connected to the photoelectric converter, and the result of building a 3D model of the target object based on the point cloud data is not affected by the shape, surface texture, material and ambient light of the object , and obtain the point cloud data of the target object with fast speed, high precision and low cost.
  • the 3D model of the target object is a closed surface in three-dimensional space, and each layer is a three-dimensional A closed curve in space, by obtaining all the closed curves layer by layer, the surface of the target object can be reconstructed, that is, the surface of the target object can be reconstructed through the point cloud information on the surface of the target object.
  • point cloud data there is no connection between points, that is, it is necessary to realize the splicing of point clouds, only by adding the corresponding three-dimensional coordinates.
  • the point cloud is reconstructed layer by layer along the height direction of the target object, and the point cloud information of the target object can be obtained by merging all point cloud coordinates together.
  • the processing module acquires the point cloud data of the target object according to multiple images, including:
  • step S101 edge information of a target object is acquired according to multiple images.
  • step S102 the point cloud information of the target object is obtained according to the edge information.
  • the image segmentation algorithm based on deep learning is mainly implemented.
  • the image segmentation algorithm based on deep learning is fast and can recognize semantic information, but its stability is poor, and the accuracy of the extracted edge information cannot meet the projection reconstruction. requirements.
  • acquiring the edge information of the target object according to the director image in step S101 includes the following steps:
  • step S1011 the target object is stratified according to the preset unit.
  • each layer of the target object in Figure 5(a) is a plane, and the edge curve of the target object in each plane needs to be extracted when reconstructing the 3D model of the target object.
  • step S1012 multiple sets of contour parallel lines of the target object at each layer are determined according to each image.
  • the image captured by the camera device at any angle during the rotation of the target object can obtain the left and right edge points of the target object, corresponding to
  • multiple groups of parallel lines constituting the outline of the target object can be determined according to multiple images of the target object acquired by the camera device, that is, it is determined that the target object is in each layer. Multiple sets of contour parallel lines.
  • step S1013 multiple sets of parallel contour lines of the target object in each layer are used as edge information of the target object.
  • the preset unit may be the unit that can achieve the best effect determined according to the reconstruction process of a large number of 3D models, and may also be the unit under the highest precision state that the 3D model reconstruction software can achieve.
  • the preset The unit is in pixel units.
  • step S102 obtaining the point cloud information of the target object according to the edge information includes the following steps:
  • step S1021 polygon fitting is performed on multiple groups of contour parallel lines of each layer to obtain polygons of the target object in each layer.
  • each rotation angle of the target object is ⁇ /N, and the rotation center corresponds to the zero point.
  • the coordinate values of the left and right edges are l i and r i .
  • the corresponding set of parallel lines is:
  • the target object rotates once to get N sets of parallel lines, and 2N (N-1) intersection points can be obtained. These intersection points are traversed. If an intersection point is outside a certain set of parallel lines, it is discarded, and the points that meet the line are kept. , calculate its convex hull as the approximate polygon of the target object in the current layer.
  • step S1022 each polygon is stacked according to the hierarchical spatial position to obtain point cloud information of the target object.
  • the parameter ⁇ can be set according to the construction of the three-dimensional model of the target object, which is not specifically limited in the present disclosure.
  • the curves are stacked in the hierarchical space according to the order from top to bottom or bottom to top to obtain the point cloud information of the target object.
  • the processing module may be set on an electronic device.
  • FIG. 6 provides a block diagram of an electronic device 700 according to an embodiment of the present disclosure. As shown in FIG. 6 , the electronic device 700 may include: a processor 701 and a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input/output (I/O) interface 704 , and a communication component 705 .
  • a multimedia component 703 an input/output (I/O) interface 704
  • I/O input/output
  • the processor 701 is used to control the overall operation of the electronic device 700, so as to complete all or part of the above-mentioned steps of acquiring point cloud data of an object.
  • the memory 702 is used to store various types of data to support the operation of the electronic device 700, for example, these data may include instructions for any application or method operating on the electronic device 700, and application-related data, Such as contact data, sent and received messages, pictures, audio, video, etc.
  • the memory 702 can be realized by any type of volatile or non-volatile memory device or their combination, such as Static Random Access Memory (Static Random Access Memory, referred to as SRAM), Electrically Erasable Programmable Read-Only Memory (EPROM) Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, referred to as EPROM), Programmable Read-Only Memory (Programmable Read-Only Memory, referred to as PROM), read-only Memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM Static Random Access Memory
  • EPROM Electrically Erasable Programmable Read-Only Memory
  • EEPROM Electrically Erasable Programmable Read-Only Memory
  • PROM Programmable Read-Only Memory
  • PROM Read-Only Memory
  • magnetic memory flash memory
  • flash memory magnetic disk or optical disk.
  • Multimedia components 703 may include screen and audio components.
  • the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals.
  • an audio component may include a microphone for receiving external audio signals.
  • the received audio signal may be further stored in memory 702 or sent via communication component 705 .
  • the audio component also includes at least one speaker for outputting audio signals.
  • the I/O interface 704 provides an interface between the processor 701 and other interface modules, which may be a keyboard, a mouse, buttons, and the like. These buttons can be virtual buttons or physical buttons.
  • the communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices.
  • Wireless communication such as Wi-Fi, Bluetooth, Near Field Communication (NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them Combinations are not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module and the like.
  • the electronic device 700 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing equipment (Digital Signal Processing Device, referred to as DSPD), programmable logic device (Programmable Logic Device, referred to as PLD), field programmable gate array (Field Programmable Gate Array, referred to as FPGA), controller, microcontroller, microprocessor or other electronic components Implementation, for performing all or part of the above-mentioned steps of acquiring the point cloud data of the object.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD Digital Signal Processing Device
  • PLD programmable logic device
  • FPGA Field Programmable Gate Array
  • controller microcontroller
  • microprocessor or other electronic components Implementation for performing all or part of the above-mentioned steps of acquiring the point cloud data of the object.
  • the present disclosure also proposes a method for obtaining object point cloud data, which is applied to the above-mentioned system for obtaining object point cloud data, and the method includes:
  • the infrared light receiving device to receive the infrared light emitted by the infrared light emitting device to the target object on the turntable in a rotating state
  • controlling the photoelectric conversion device to photoelectrically convert the infrared light to obtain multiple images
  • the point cloud data of the target object is obtained according to multiple images, including:
  • the point cloud data of the target object is obtained according to the edge information.
  • the edge information of the target object is acquired according to multiple images, including:
  • the point cloud data of the target object is obtained according to the edge information, including:
  • the polygons are stacked according to the layered spatial positions to obtain the point cloud data of the target object.
  • the present disclosure also proposes a computing processing device, including the above-mentioned system for acquiring object point cloud data.
  • the present disclosure also proposes a computer program, including computer readable codes, which, when the computer readable codes are run on a computing processing device, cause the computing processing device to execute the aforementioned acquiring object point cloud data method.
  • FIG. 7 is a schematic structural diagram of a computing processing device provided by an embodiment of the present disclosure.
  • the computing processing device typically includes a processor 1110 and a computer program product or computer readable medium in the form of memory 1130 .
  • Memory 1130 may be electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the memory 1130 has a storage space 1150 for program code 1151 for performing any method steps in the methods described above.
  • the storage space 1150 for program codes may include respective program codes 1151 for respectively implementing various steps in the above methods.
  • program codes can be read from or written into one or more computer program products.
  • These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such a computer program product is typically a portable or fixed storage unit as shown in FIG. 8 .
  • the storage unit may have storage segments, storage spaces, etc. arranged similarly to the storage 1130 in the server in FIG. 7 .
  • the program code can eg be compressed in a suitable form.
  • the memory unit includes computer readable code 1151', i.e. code readable by, for example, a processor such as 1110, which when executed by the server causes the server to perform the various steps in the methods described above.
  • a "computer-readable medium” may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device.
  • computer-readable media include the following: electrical connection with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM).
  • the computer-readable medium may even be paper or other suitable medium on which the program can be printed, since the program can be read, for example, by optically scanning the paper or other medium, followed by editing, interpretation or other suitable processing if necessary. processing to obtain the program electronically and store it in computer memory.
  • various parts of the present disclosure may be implemented in hardware, software, firmware or a combination thereof.
  • various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware as in another embodiment, it can be implemented by any one or combination of the following techniques known in the art: a discrete Logic circuits, ASICs with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are realized in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.
  • the storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Analysis (AREA)

Abstract

一种获取物体点云数据的系统，包括：红外光发射装置、红外光接收装置、光电转换器以及置物台；红外光发射装置、置物台以及红外光接收装置依次布置在同一直线方向上；置物台包括置物台本体以及相对置物台本体可转动的转台，转台用于放置目标物体；红外光接收装置用于接收红外光发射装置向处于转动状态的转台上的目标物体发射的红外光；光电转换器与红外光接收装置连接，光电转换器用于对红外光进行光电转换，从而得到多张图像，多张图像用于获取目标物体的点云数据。

Description

获取物体点云数据的系统及方法
相关申请的交叉引用
本公开要求在2021年06月23日提交中国专利局、申请号为202110698198.5、名称为“获取物体点云数据的系统”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及计算机视觉领域，具体地，涉及一种获取物体点云数据的系统及方法。
背景技术
获取体型较小的物体时，在算法层面需要对物体进行3D检测定位，目前3D检测定位效果较好的方法是利用物体的点云数据或其他3D数据格式的深度学习算法或传统的ICP(Iterative Closest Point，迭代最近点算法)配准方法。深度学习算法需要大量的3D模型作为支持，ICP配准也要求有完整的点云模型来构建数据库，无论哪种算法都需要物体3D模型作为支持。
目前获取3D模型可以通过3D扫描得到，但该方法成本高，且无法处理透明反光的表面；还可以通过MVS(Multi-View Stereo，多视角立体几何)实现，但MVS依赖于图像特征，无法处理表面纹理不丰富的物体，且处理速度很慢。
发明内容
本公开旨在至少在一定程度上解决相关技术中的技术问题之一。
为达上述目的，本公开第一方面实施例提出了一种获取物体点云数据的系统，所述系统包括：红外光发射装置、红外光接收装置、光电转换器以及置物台；
其中，所述红外光发射装置、所述置物台以及所述红外光接收装置依次布置在同一直线方向上；
所述置物台包括置物台本体以及相对所述置物台本体可转动的转台，所述转台用于放置目标物体；
所述红外光接收装置用于接收所述红外光发射装置向处于转动状态的所述转台上的所述目标物体发射的红外光；
所述光电转换器与所述红外光接收装置连接，所述光电转换装置用于对所述红外光进行光电转换，从而得到多张图像，所述多张图像用于获取所述目标物体的点云数据。
根据本公开的一个实施例，所述系统还包括同步平移装置，所述同步平移装置包括底座以及相对所述底座可滑动的两个相互平行的滑板；
所述红外光发射装置和所述红外光接收装置分别设置在所述两个相互平行的滑板上，从而使得所述红外光发射装置与所述红外光接收装置可沿所述目标物体的水平方向和/或竖直方向同步滑动。
根据本公开的一个实施例，所述红外光发射装置的红外光发射方向与所述转台的置物面平行。
根据本公开的一个实施例，所述红外光发射装置包括红外发射阵列，所述红外发射阵列由多个红外光发射单元组成。
根据本公开的一个实施例，所述红外光接收装置包括红外接收阵列，所述红外接收阵列由多个红外光接收单元组成；
其中，所述红外光接收单元的数量与所述红外光发射单元的数量相同，且位置一一对应。
根据本公开的一个实施例，所述红外发射阵列发射的红外光构成红外区域，所述红外区域覆盖所述目标物体。
根据本公开的一个实施例，所述红外光发射装置发射红外光的频率与所述转台的转动频率一致。
根据本公开的一个实施例，所述系统还包括与所述光电转换器连接的处理模块，所述处理模块用于根据所述多张图像获取所述目标物体的点云数据。
根据本公开的一个实施例，所述处理模块根据所述多张图像获取所述目标物体的点云数据，包括：
根据所述多张图像获取所述目标物体的边缘信息；
根据所述边缘信息得到所述目标物体的点云数据。
根据本公开的一个实施例，所述处理模块根据所述多张图像获取所述目标物体的边缘信息，包括：
根据预设单位对所述目标物体进行分层处理；
根据各所述图像确定所述目标物体在各层的多组轮廓平行线；
将所述目标物体在各层的多组轮廓平行线作为所述目标物体的边缘信息。
根据本公开的一个实施例，所述处理模块根据所述边缘信息得到所述目标物体的点云数据，包括：
分别对各层的多组轮廓平行线进行多边形拟合，得到所述目标物体在各层的多边形；
将各所述多边形根据分层的空间位置进行堆叠，得到所述目标物体的点云数据。
本公开第一方面提供的获取物体点云数据的系统，将目标物体设置在红外光发射装置和红外光接收装置之间，设置转台使目标物体转动，获取转台旋转其上的目标物体时的红外光，进行光电转换，得到目标物体的图像，无需设置摄像装置，节省了空间，消除透视投影效果，通过目标物体的图像得到的目标物体的边缘信息更加准确，且不受环境光以及物体表面纹理影响。
为达上述目的，本公开第二方面实施例提出了获取物体点云数据的方法，应用于第一方面所述的获取物体点云数据的系统，所述方法包括：
控制所述红外光接收装置接收所述红外光发射装置向处于转动状态的所述转台上的目标物体发射的红外光；
控制所述光电转换装置对所述红外光进行光电转换，从而得到多张图像；
根据所述多张图像获取所述目标物体的点云数据。
根据本公开的一个实施例，所述根据所述多张图像获取所述目标物体的点云数据，包括：
根据所述多张图像获取所述目标物体的边缘信息；
根据所述边缘信息得到所述目标物体的点云数据。
根据本公开的一个实施例，所述根据所述多张图像获取所述目标物体的边缘信息，包括：
根据预设单位对所述目标物体进行分层处理；
根据各所述图像确定所述目标物体在各层的多组轮廓平行线；
将所述目标物体在各层的多组轮廓平行线作为所述目标物体的边缘信息。
根据本公开的一个实施例，所述根据所述边缘信息得到所述目标物体的点云数据，包括：
分别对各层的多组轮廓平行线进行多边形拟合，得到所述目标物体在各层的多边形；
将各所述多边形根据分层的空间位置进行堆叠，得到所述目标物体的点云数据。
为达上述目的，本公开第三方面实施例提出了一种计算处理设备，包括第一方面所述的系统。
为达上述目的，本公开第四方面实施例提出了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，导致所述计算处理设备执行本公开第二方面实施例所提出的获取物体点云数据的方法。
为达上述目的，本公开第五方面实施例提出了一种计算机可读存储介质，其中存储了本公开第四方面实施例所提出的计算机程序。
本公开附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本公开的实践了解到。
附图说明
本公开上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1为本公开实施例提供了一种获取物体点云数据的系统的示意图；
图2为本公开实施例提供了处理模块获取目标物体点云数据的流程图；
图3为本公开实施例提供了获取目标物体点云数据中步骤S101的流程图；
图4为本公开实施例提供了获取目标物体点云数据中步骤S102的流程图；
图5为本公开实施例提供了处理模块获取目标物体点云数据的示意图；
图6为本公开实施例提供了一种电子设备的框图；
图7为本公开实施例提供了一种计算处理设备的结构示意图；
图8为本公开实施例提供了一种用于便携式或者固定实现根据本公开的方法的程序代码的存储单元的示意图。
具体实施方式
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本公开，而不能理解为对本公开的限制。
服务型机器人在抓取体型较小的物体，如饮料瓶、杯子、水果等，在算法层面需要对物体进行3D检测定位，3D检测定位主要为利用点云或者其他3D数据格式的深度学习算法或者传统的ICP(Iterative Closest Point，最近点迭代)配准方法。其中，深度学习 算法是一种数据驱动算法，需要大量的3D模型作为支持，ICP配准算法需要完整的点云模型来构建数据库，即两种算法均需要物体的3D模型作为支持，3D模型由物体的点云数据构成。
相关技术中物体的3D模型可以通过3D扫描仪、MVS(Multi-View Stereo，多视角立体几何)、通过CAD(Computer Aided Design，计算机辅助设计)人工设计物体专用三维重建模型以及物体投影重建算法获得。
但发明人发现，3D扫描仪虽然可对任意形状的物体进行表面重建，不受物体形状的限制，且重建速度快，但设备昂贵，且无法获取表面透明、反光的物体的三维重建模型；MVS虽然可以根据物体的已知位姿的图片，对观察到的物体进行几何重建，但对图像的特征依赖较强，且无法获取表面纹理不丰富的物体的三维重建模型且处理速度很慢；通过CAD人工设计的物体专用三维重建模型虽然可得到最为精确的物体的模型，但受物体形状的限制，适用性底，且成本太高；对于物体投影重建算法，采用相机获取物体的边缘图像，从边缘图像中来获取物体的点云数据，但在相机拍摄过程中，物体边缘会收到环境光影响、且拍摄距离过近会产生透视投影，导致获取的点云数据不准确。
有鉴于此，本公开提供一种获取物体点云数据的系统，不受物体的形状、表面纹理、材质以及环境光等影响，得到物体的点云数据。
图1为本公开实施例提供了一种获取物体点云数据的系统的示意图，参照图1，该获取物体点云数据的系统包括：红外光发射装置、红外光接收装置、光电转换器以及置物台；
其中，红外光发射装置、置物台以及红外光接收装置依次布置在同一直线方向上；
置物台包括置物台本体以及相对置物台本体可转动的转台，转台用于放置目标物体；
红外光接收装置用于接收红外光发射装置向处于转动状态的转台上的目标物体发射的红外光；
光电转换器与红外光接收装置连接，光电转换装置用于对红外光进行光电转换，从而得到多张图像，多张图像用于获取目标物体的点云数据。
本公开提供的获取物体点云数据的系统，将目标物体设置在红外光发射装置和红外光接收装置之间，设置转台使目标物体转动，获取转台旋转其上的目标物体时的红外光，进行光电转换，得到目标物体的图像，无需设置摄像装置，节省了空间，消除透视投影效果，通过目标物体的图像得到的目标物体的边缘信息更加准确，且不受环境光以及物 体表面纹理影响，与光电转换器连接的处理模块根据多张图像获取目标物体的点云数据。
在一可实施例中，如图1所示，获取物体点云数据的系统还包括同步平移装置，同步平移装置包括底座以及相对底座可滑动的两个相互平行的滑板；
红外光发射装置和红外光接收装置分别设置在两个相互平行的滑板上，从而使得红外光发射装置与红外光接收装置可沿目标物体的水平方向和/或竖直方向同步滑动。
通过同步平移装置将红外光发射装置和红外光接收装置沿水平方向和/或竖直方向同步平移，可得到不同分辨率的图像，还可提高得到的图像的分辨率。
举例说明，在未通过同步平移装置对红外光发射装置和红外光接收装置进行移动式，得到的图像的分辨率为h*w，在需要得到分辨率为h’*w’的图像的情况下，需要通过同步平移装置将红外光发射装置和红外光接收装置沿水平方向平移h’/h次，沿竖直方向平移w’/w次；水平方向平移步长为Ww/[(w-1)w’]，竖直方向平移步长为Hh/[(h-1)h’]，在全部平移结束后，红外光接收装置将h’w’/hw个分辨率为h*w的图像合并为一个分辨率为h’*w’的高分辨率图像，其中，H为红外光发射装置的高度，W为红外光发射装置的宽度。
在一可实施例中，如图1所示，红外光发射装置的红外光发射方向与转台的置物面平行。
举例说明，如图1所示，在转台的置物面为水平面时，红外光发射装置发射的红外光为红外平行光，红外接收装置接收红外发射装置发射的红外平行光，通过红外平行光对目标物体进行扫面。
将红外光发射装置的红外光与转台的置物面调整为平行状态，可避免通过红外光得到的图像变形扭曲，无需对图像进行变形校正处理。
在一可实施例中，如图1所示，红外光发射装置包括红外光发射阵列，红外光发射阵列由多个红外光发射单元组成。
其中，多个红外光发射单元根据预设尺寸组成红外光发射阵列，预设尺寸可根据用户需要或者目标物体的大小尺寸进行预设。
在本实施例中，红外光发射阵列高位H，宽为W，由h行w列个红外光发射单元组成，各红外光发射单元在水平方向上的间距为H/(h-1)，在竖直方向上的间距为W/(w-1)。
通过红外光发射这列对目标物体进行扫描，可缩短获取目标物体图像的时间，提高获取目标物体图像的效率。
举例说明，通过单个红外光发射单元向目标物体发射红外光从而获取目标物体图像需要移动h’*w’次红外光发射单元，而使用红外光发射阵列向目标物体发射红外光可减小移动次数，将获取目标物体图像的时间缩短为1/h*w。
在一可实施例中，如图1所示，红外光接收装置包括红外接收阵列，红外接收阵列由多个红外光接收单元组成；
其中，红外光接收单元的数量与红外光发射单元的数量相同，且位置一一对应。
红外光接收阵列接收红外光发射阵列向处于转动状态的转台上的目标物体发射的红外光，对光信号的位置进行记录，得到一张稀疏的目标物体的投影图像。
举例说明，红外光接收阵列中各红外光在接收单元在接收到光信号时，该位置记为0，未收到光信号时，该位置记为1，从而得到对应目标物体的光信号，通过光电转换器将得到的所有光信号进行光电转换，得到目标物体的投影图像。
在一可实施例中，红外发射阵列发射的红外光构成红外区域，红外区域覆盖目标物体。
通过红外光获取目标物体的图像，不受环境光以及物体表面纹理影响。
在一可实施例中，红外光发射装置发射红外光的频率与转台的转动频率一致。
通过将红外光发射装置发射红外光的频率与转台的转动频率设置为一致，避免得到的图像模糊，无法获取目标物体的点云数据。
对本实施例中获取物体点云数据的系统获取目标物体图像的过程进行说明。
如图1所示，通过移动滑板与底座的位置，使得滑板上的红外光发射阵列中最低一列红外光发射单元发射的红外光所处平面低于转台平面，红外光发射整列中最高一列红外光发射单元发射的红外光所处平面高于目标物体最高位置所处的平面，即红外光发射阵列发射的红外光构成的红外区域覆盖目标物体，无需设置摄像装置，节省了空间；
校正红外光接收阵列与红外光发射阵列之间的对应关系，使得红外光接收阵列的每一个红外光接收单元都能接收到对应的红外光发射阵列中红外光发射单元发射的红外光(被置物台遮挡的除外)，消除了透视投影效果，且不受环境光以及目标物体表面纹理影响；
启动红外光发射阵列发射红外光，转台转动，且红外光发射频率与转动频率一致；通过红外光发射阵列和红外光接收阵列对目标物体进行扫描，扫描方式可以为逐行扫描或者逐列扫描，红外光接收阵列将每次扫描得到的光信号发送给光电转换器，光电转换 器将光信号转换成数字信号，并以图像形式呈现；在转台旋转一周，全部扫描结束后，得到多张用于获取目标物体的点云数据的图像，通过该图像得到的点云数据可更加准确的体现出目标物体边缘状态。
在一可实施例中，获取物体点云数据的系统还包括与光电转换器连接的处理模块，处理模块用于根据多张图像获取目标物体的点云数据。
通过与光电转换器连接的处理模块根据多张图像获取目标物体的点云数据，根据该点云数据对目标物体进行三维模型构建的结果不受物体的形状、表面纹理、材质以及环境光的影响，且获取目标物体的点云数据的速度快、精度高且成本底。
目标物体的3D模型，绝大多数都只包含表面信息，无需目标物体的内部信息，因此从几何角度分析，目标物体的3D模型，是三维空间中的一个闭合曲面，其每一层都是三维空间中的一条闭合曲线，通过逐层地获取所有的闭合曲线，就能重建目标物体的表面，即可通过目标物体表面的点云信息重建目标物体的表面。
在点云数据中，点与点之间是没有建立关联的，即需实现点云的拼接，仅通过添加相应的三维坐标即可。沿目标物体的高度方向逐层重建点云，将所有点云坐标合并到一起即可得到目标物体的点云信息。
在一可实施例中，如图2所示，处理模块根据多张图像获取目标物体的点云数据，包括：
在步骤S101中，根据多张图像获取目标物体的边缘信息。
在步骤S102中，根据边缘信息得到目标物体的点云信息。
在通过多张图像获取目标物体的点云数据时，需提取图像中物体的边缘信息。而相关技术中主要基于深度学习的图像分割算法实现，基于深度学习的图像分割算法速度快且能识别语义信息，但其稳定性较差，且提取的边缘信息的精度达不到投影重建所需的要求。
在一可实施例中，如图3所示，步骤S101中根据所长图像获取目标物体的边缘信息包括以下步骤：
在步骤S1011中，根据预设单位对目标物体进行分层处理。
所示对目标物体分层后，如图5(a)目标物体的每层都是一个平面，在重建目标物体的三维模型时需提取每个平面中目标物体的边缘曲线。
在步骤S1012中，根据各图像确定目标物体在各层的多组轮廓平行线。
如图5(b)～5(e)所示，对于目标物体分层的各层，摄像装置在目标物体转动过程中的任一角度获取的图像可以得到目标物体的左右两个边缘点，对应图5(b)～5(e)所示的一组平行线，则可根据摄像装置获取的目标物体的多个图像确定构成目标物体的轮廓的多组平行线，即确定目标物体在各层的多组轮廓平行线。
在步骤S1013中，将目标物体在各层的多组轮廓平行线作为目标物体的边缘信息。
其中，预设单位可以是根据大量三维模型重建过程中，确定的能达到最好效果的单位，还可以是三维模型重建软件所能达到的最高精度状态下的单位，在本实施例中预设单位采用像素单位。
在一可实施例中，如图4所示，在步骤S102中，根据边缘信息得到目标物体的点云信息，包括以下步骤：
在步骤S1021中，分别对各层的多组轮廓平行线进行多边形拟合，得到目标物体在各层的多边形。
如图5(f)所示，计算出各层中所有直线的交点；如图5(g)利用点到直线的距离公式求出所有直线的交点的内点；如图5(h)～5(j)所示，利用Graham(凸包)算法，计算出内点形成的凸包，即目标物体在各层的多边形。
举例说明，设目标物体旋转一周相机拍摄了N次，目标物体的每次旋转角为π/N，旋转中心对应零点，对于第i次旋转，左右边缘的坐标值为l i和r i，此时对应的一组平行线为：
l i cos(2πi/N)x+sin(2πi/N)y+l i＝0，
l i cos(2πi/N)x+sin(2πi/N)y+r i＝0，
设点p＝[x 0，y 0] T，直线Ax+By+C＝0，则点到直线的距离为：
d＝|(Ax 0+By 0+C)/√(A^2+B^2)|
设直线l 0：Ax+By+C＝0，直线l 1：Ax+By+C1＝0，则直线l 0到l 1的距离为：
d＝|C 0-C 1|/√(A^2+B^2)
目标物体旋转一周得到N组平行线，可得到2N(N-1)个交点，遍历这些交点，若某个交点处于某组平行线之外则舍弃，保留符合处于线上的点，对保留下来的点，计算其凸包，作为目标物体在当前层的近似多边形。
在步骤S1022中，将各多边形根据分层空间位置进行堆叠，得到目标物体的点云信息。
在各多边形(即凸包)的顶点间做离散插值，得到由密度均匀的点云构成的一条闭合曲线，各点间距离为参数ρ，使得相机拍摄到的点云数据是密度均匀的，并且密度是可知的，尽量减少与实际采集数据间的差异。其中，参数ρ可根据目标物体的三维模型的构建进行设置，本公开不作具体限定。将各曲线在分层空间中根据从上至下或者从下至上的顺序进行堆叠，得到目标物体的点云信息。
在一实施例中，处理模块可以设置在电子设备上，图6为本公开实施例提供了一种电子设备700的框图。如图6所示，该电子设备700可以包括：处理器701，存储器702。该电子设备700还可以包括多媒体组件703，输入/输出(I/O)接口704，以及通信组件705中的一者或多者。
其中，处理器701用于控制该电子设备700的整体操作，以完成上述的获取物体的点云数据的全部或部分步骤。
存储器702用于存储各种类型的数据以支持在该电子设备700的操作，这些数据例如可以包括用于在该电子设备700上操作的任何应用程序或方法的指令，以及应用程序相关的数据，例如联系人数据、收发的消息、图片、音频、视频等等。该存储器702可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，例如静态随机存取存储器(Static Random Access Memory，简称SRAM)，电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，简称EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，简称EPROM)，可编程只读存储器(Programmable Read-Only Memory，简称PROM)，只读存储器(Read-Only Memory，简称ROM)，磁存储器，快闪存储器，磁盘或光盘。
多媒体组件703可以包括屏幕和音频组件。其中屏幕例如可以是触摸屏，音频组件用于输出和/或输入音频信号。例如，音频组件可以包括一个麦克风，麦克风用于接收外部音频信号。所接收的音频信号可以被进一步存储在存储器702或通过通信组件705发送。音频组件还包括至少一个扬声器，用于输出音频信号。
I/O接口704为处理器701和其他接口模块之间提供接口，上述其他接口模块可以是键盘，鼠标，按钮等。这些按钮可以是虚拟按钮或者实体按钮。
通信组件705用于该电子设备700与其他设备之间进行有线或无线通信。无线通信，例如Wi-Fi，蓝牙，近场通信(Near Field Communication，简称NFC)，2G、3G、4G、NB-IOT、eMTC、或其他5G等等，或它们中的一种或几种的组合，在此不做限定。因此 相应的该通信组件705可以包括：Wi-Fi模块，蓝牙模块，NFC模块等等。
在一示例性实施例中，电子设备700可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit，简称ASIC)、数字信号处理器(Digital Signal Processor，简称DSP)、数字信号处理设备(Digital Signal Processing Device，简称DSPD)、可编程逻辑器件(Programmable Logic Device，简称PLD)、现场可编程门阵列(Field Programmable Gate Array，简称FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述的获取物体的点云数据的全部或部分步骤。
为了实现上述实施例，本公开还提出了获取物体点云数据的方法，应用于上述的获取物体点云数据的系统，该方法包括：
控制该红外光接收装置接收该红外光发射装置向处于转动状态的该转台上的目标物体发射的红外光；
控制该光电转换装置对该红外光进行光电转换，从而得到多张图像；
根据多张图像获取该目标物体的点云数据。
在一可实施例中，根据多张图像获取该目标物体的点云数据，包括：
根据多张图像获取该目标物体的边缘信息；
根据该边缘信息得到该目标物体的点云数据。
在一可实施例中，根据多张图像获取该目标物体的边缘信息，包括：
根据预设单位对该目标物体进行分层处理；
根据各图像确定该目标物体在各层的多组轮廓平行线；
将该目标物体在各层的多组轮廓平行线作为该目标物体的边缘信息。
在一可实施例中，根据该边缘信息得到该目标物体的点云数据，包括：
分别对各层的多组轮廓平行线进行多边形拟合，得到该目标物体在各层的多边形；
将各多边形根据分层的空间位置进行堆叠，得到该目标物体的点云数据。
为了实现上述实施例，本公开还提出了一种计算处理设备，包括上述获取物体点云数据的系统。
为了实现上述实施例，本公开还提出了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，导致所述计算处理设备执行前述的获取物体点云数据的方法。
为了实现上述实施例，本公开还提出了一种计算机可读存储介质，其中存储了前述 的计算机程序。图7为本公开实施例提供了一种计算处理设备的结构示意图。该计算处理设备通常包括处理器1110和以存储器1130形式的计算机程序产品或者计算机可读介质。存储器1130可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器1130具有用于执行上述方法中的任何方法步骤的程序代码1151的存储空间1150。例如，用于程序代码的存储空间1150可以包括分别用于实现上面的方法中的各种步骤的各个程序代码1151。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘，紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如图8示的便携式或者固定存储单元。该存储单元可以具有与图7服务器中的存储器1130类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常，存储单元包括计算机可读代码1151’，即可以由例如诸如1110之类的处理器读取的代码，这些代码当由服务器运行时，导致该服务器执行上面所描述的方法中的各个步骤。
以上结合附图详细描述了本公开的优选实施方式，但是，本公开并不限于上述实施方式中的具体细节，在本公开的技术构思范围内，可以对本公开的技术方案进行多种简单变型，这些简单变型均属于本公开的保护范围。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本公开对各种可能的组合方式不再另行说明。
此外，本公开的各种不同的实施方式之间也可以进行任意组合，只要其不违背本公开的思想，其同样应当视为本公开所公开的内容。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本公开的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本公开的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指 令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本公开各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。尽管上面已经示出和描述了本公开的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本公开的限制，本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (18)

  1. 一种获取物体点云数据的系统，其特征在于，所述系统包括：红外光发射装置、红外光接收装置、光电转换器以及置物台；
    其中，所述红外光发射装置、所述置物台以及所述红外光接收装置依次布置在同一直线方向上；
    所述置物台包括置物台本体以及相对所述置物台本体可转动的转台，所述转台用于放置目标物体；
    所述红外光接收装置用于接收所述红外光发射装置向处于转动状态的所述转台上的所述目标物体发射的红外光；
    所述光电转换器与所述红外光接收装置连接，所述光电转换装置用于对所述红外光进行光电转换，从而得到多张图像，所述多张图像用于获取所述目标物体的点云数据。
  2. 根据权利要求1所述的系统，其特征在于，所述系统还包括同步平移装置，所述同步平移装置包括底座以及相对所述底座可滑动的两个相互平行的滑板；
    所述红外光发射装置和所述红外光接收装置分别设置在所述两个相互平行的滑板上，从而使得所述红外光发射装置与所述红外光接收装置可沿所述目标物体的水平方向和/或竖直方向同步滑动。
  3. 根据权利要求1所述的系统，其特征在于，所述红外光发射装置的红外光发射方向与所述转台的置物面平行。
  4. 根据权利要求1或3所述的系统，其特征在于，所述红外光发射装置包括红外发射阵列，所述红外发射阵列由多个红外光发射单元组成。
  5. 根据权利要求4所述的系统，其特征在于，所述红外光接收装置包括红外接收阵列，所述红外接收阵列由多个红外光接收单元组成；
    其中，所述红外光接收单元的数量与所述红外光发射单元的数量相同，且位置一一对应。
  6. 根据权利要求5所述的系统，其特征在于，所述红外发射阵列发射的红外光构成红外区域，所述红外区域覆盖所述目标物体。
  7. 根据权利要求1所述的系统，其特征在于，所述红外光发射装置发射红外光的频率与所述转台的转动频率一致。
  8. 根据权利要求1所述的系统，其特征在于，所述系统还包括与所述光电转换器连 接的处理模块，所述处理模块用于根据所述多张图像获取所述目标物体的点云数据。
  9. 根据权利要求8所述的系统，其特征在于，所述处理模块根据所述多张图像获取所述目标物体的点云数据，包括：
    根据所述多张图像获取所述目标物体的边缘信息；
    根据所述边缘信息得到所述目标物体的点云数据。
  10. 根据权利要求9所述的系统，其特征在于，所述处理模块根据所述多张图像获取所述目标物体的边缘信息，包括：
    根据预设单位对所述目标物体进行分层处理；
    根据各所述图像确定所述目标物体在各层的多组轮廓平行线；
    将所述目标物体在各层的多组轮廓平行线作为所述目标物体的边缘信息。
  11. 根据权利要求10所述的系统，其特征在于，所述处理模块根据所述边缘信息得到所述目标物体的点云数据，包括：
    分别对各层的多组轮廓平行线进行多边形拟合，得到所述目标物体在各层的多边形；
    将各所述多边形根据分层的空间位置进行堆叠，得到所述目标物体的点云数据。
  12. 一种获取物体点云数据的方法，其特征在于，应用于权利要求1所述的获取物体点云数据的系统，所述方法包括：
    控制所述红外光接收装置接收所述红外光发射装置向处于转动状态的所述转台上的目标物体发射的红外光；
    控制所述光电转换装置对所述红外光进行光电转换，从而得到多张图像；
    根据所述多张图像获取所述目标物体的点云数据。
  13. 根据权利要求12所述的方法，其特征在于，所述根据所述多张图像获取所述目标物体的点云数据，包括：
    根据所述多张图像获取所述目标物体的边缘信息；
    根据所述边缘信息得到所述目标物体的点云数据。
  14. 根据权利要求13所述的方法，其特征在于，所述根据所述多张图像获取所述目标物体的边缘信息，包括：
    根据预设单位对所述目标物体进行分层处理；
    根据各所述图像确定所述目标物体在各层的多组轮廓平行线；
    将所述目标物体在各层的多组轮廓平行线作为所述目标物体的边缘信息。
  15. 根据权利要求14所述的方法，其特征在于，所述根据所述边缘信息得到所述目标物体的点云数据，包括：
    分别对各层的多组轮廓平行线进行多边形拟合，得到所述目标物体在各层的多边形；
    将各所述多边形根据分层的空间位置进行堆叠，得到所述目标物体的点云数据。
  16. 一种计算处理设备，其特征在于，包括权利要求1-11所述的系统。
  17. 一种计算机程序，包括计算机可读代码，当所述计算机可读代码在计算处理设备上运行时，导致所述计算处理设备执行根据权利要求12-15中任一项所述的获取物体点云数据的方法。
  18. 一种计算机可读存储介质，其中存储了如权利要求17所述的计算机程序。
PCT/CN2021/143974 2021-06-23 2021-12-31 获取物体点云数据的系统及方法 WO2022267434A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110698198.5 2021-06-23
CN202110698198.5A CN113536957B (zh) 2021-06-23 2021-06-23 获取物体点云数据的系统

Publications (1)

Publication Number Publication Date
WO2022267434A1 true WO2022267434A1 (zh) 2022-12-29

Family

ID=78125664

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/143974 WO2022267434A1 (zh) 2021-06-23 2021-12-31 获取物体点云数据的系统及方法

Country Status (2)

Country Link
CN (1) CN113536957B (zh)
WO (1) WO2022267434A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113536957B (zh) * 2021-06-23 2023-04-07 达闼机器人股份有限公司 获取物体点云数据的系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150362718A1 (en) * 2013-01-31 2015-12-17 Danmarks Tekniske Universitet Infrared up-conversion telescope
CN106780725A (zh) * 2016-12-23 2017-05-31 西安交通大学 一种双目三维重构方法及系统
CN108665535A (zh) * 2018-05-10 2018-10-16 青岛小优智能科技有限公司 一种基于编码光栅结构光的三维结构重建方法与系统
CN109215108A (zh) * 2017-06-30 2019-01-15 深圳先进技术研究院 基于激光扫描的全景三维重建系统及方法
CN113536957A (zh) * 2021-06-23 2021-10-22 达闼机器人有限公司 获取物体点云数据的系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102509286B (zh) * 2011-09-28 2014-04-09 清华大学深圳研究生院 一种医学图像目标区域勾画方法
CN105184852B (zh) * 2015-08-04 2018-01-30 百度在线网络技术（北京）有限公司 一种基于激光点云的城市道路识别方法及装置
CN206410678U (zh) * 2016-12-30 2017-08-15 武汉海达数云技术有限公司 三维激光扫描装置
CN108010134A (zh) * 2017-11-29 2018-05-08 湘潭大学 一种基于移动终端的实时三维虚拟试衣方法
CN209789240U (zh) * 2018-12-04 2019-12-17 广州市腾翔包装制品有限公司 一种具有防护结构的珠宝盒展台
CN209397968U (zh) * 2018-12-05 2019-09-17 一汽物流有限公司 一种仓储车辆的停放系统及停车场
CN109490909A (zh) * 2018-12-26 2019-03-19 中国科学院微电子研究所 激光雷达扫描探测装置及其探测方法
CN212721315U (zh) * 2020-09-07 2021-03-16 四川锐坤电子技术有限公司 一种测试台
CN112269181A (zh) * 2020-09-11 2021-01-26 中国科学院微电子研究所 激光主动探测装置及激光主动探测处置系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150362718A1 (en) * 2013-01-31 2015-12-17 Danmarks Tekniske Universitet Infrared up-conversion telescope
CN106780725A (zh) * 2016-12-23 2017-05-31 西安交通大学 一种双目三维重构方法及系统
CN109215108A (zh) * 2017-06-30 2019-01-15 深圳先进技术研究院 基于激光扫描的全景三维重建系统及方法
CN108665535A (zh) * 2018-05-10 2018-10-16 青岛小优智能科技有限公司 一种基于编码光栅结构光的三维结构重建方法与系统
CN113536957A (zh) * 2021-06-23 2021-10-22 达闼机器人有限公司 获取物体点云数据的系统

Also Published As

Publication number Publication date
CN113536957B (zh) 2023-04-07
CN113536957A (zh) 2021-10-22

Similar Documents

Publication Publication Date Title
KR102431117B1 (ko) 포인트 클라우드 맵핑
JP7161150B2 (ja) ジオメトリ情報の動き補償
Davis et al. Unstructured light fields
Seitz Image-based transformation of viewpoint and scene appearance
US20120176380A1 (en) Forming 3d models using periodic illumination patterns
US20120176478A1 (en) Forming range maps using periodic illumination patterns
US8754887B2 (en) Determining three-dimensional (3D) object data models based on object movement
US20190147624A1 (en) Method for Processing a Raw Image of a Time-of-Flight Camera, Image Processing Apparatus and Computer Program
JP2023549821A (ja) 変形可能なニューラル放射輝度場
US9224238B2 (en) Seamless texturing of 3D meshes of objects from multiple views
CN111189415B (zh) 一种基于线结构光的多功能三维测量重建系统及方法
CN108805979A (zh) 一种动态模型三维重建方法、装置、设备和存储介质
US8363930B1 (en) Use of materials and appearances to merge scanned images
GB2562037A (en) Three-dimensional scene reconstruction
WO2022267434A1 (zh) 获取物体点云数据的系统及方法
Taubin et al. 3d scanning for personal 3d printing: build your own desktop 3d scanner
JP2019534511A (ja) 自由動作ｆｖｖアプリケーションのためのマルチレイヤｕｖマップに基づくテクスチャレンダリング
US20210374986A1 (en) Image processing to determine object thickness
WO2018080533A1 (en) Real-time generation of synthetic data from structured light sensors for 3d object pose estimation
JP2022548608A (ja) ３ｄモデルのテクスチャを取得するための方法および関連する装置
Germann et al. Novel‐View Synthesis of Outdoor Sport Events Using an Adaptive View‐Dependent Geometry
CN108655571A (zh) 一种数控激光雕刻机、控制系统及控制方法、计算机
WO2022242192A1 (zh) 物体投影重建系统及方法
Evers‐Senne et al. Image based interactive rendering with view dependent geometry
Kumara et al. Real-time 3D human objects rendering based on multiple camera details

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: 21946907

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21946907

Country of ref document: EP

Kind code of ref document: A1