WO2021174682A1 - 体积检测装置和智能仓 - Google Patents

体积检测装置和智能仓 Download PDF

Info

Publication number
WO2021174682A1
WO2021174682A1 PCT/CN2020/091579 CN2020091579W WO2021174682A1 WO 2021174682 A1 WO2021174682 A1 WO 2021174682A1 CN 2020091579 W CN2020091579 W CN 2020091579W WO 2021174682 A1 WO2021174682 A1 WO 2021174682A1
Authority
WO
WIPO (PCT)
Prior art keywords
board
algorithm
volume
control board
volume measurement
Prior art date
Application number
PCT/CN2020/091579
Other languages
English (en)
French (fr)
Inventor
任林
宋侃
Original Assignee
深圳市丰巢科技有限公司
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 深圳市丰巢科技有限公司 filed Critical 深圳市丰巢科技有限公司
Publication of WO2021174682A1 publication Critical patent/WO2021174682A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/04—Sorting according to size
    • B07C5/10—Sorting according to size measured by light-responsive means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection

Definitions

  • the present disclosure relates to the field of information processing technology, for example, to a volume detection device and a smart warehouse.
  • the traditional express cabinet is displayed in front of people by the middle man-machine interaction panel, and the left and right sides are the lattice cabinets.
  • the person goes to the interactive panel to control the opening of the door to open the door, walks to the opening of the door to access the item, and then closes the door after accessing the item to the opening of the door.
  • the express warehouse is like a three-dimensional warehouse.
  • the human-computer interaction panel is similar to the express cabinet. The difference is that the delivery and receipt can be completed in front of the panel instead of the distribution grid. That is, there is only one access port in front of the panel.
  • the access port When the access port is opened, the courier or items are placed on the port tray, and then the access port is closed, and the internal movement mechanism of the express warehouse will automatically transfer the courier or items to a suitable location. When picking up the parcel, you only need to wait for a few seconds at the access port. The internal movement mechanism of the express warehouse will automatically transfer the courier or item to the access port. After the access port door is opened, the courier or item will be taken away, and the access port will automatically closure.
  • the express warehouse is more convenient and automated than the express cabinet, but the volume of the express or the item is not easy to measure. Some use grating to measure the length, width and height, but it is only a rough value. For irregular objects, such as clothing, the measurement difference is large and the measurement accuracy is not high. .
  • the embodiments of the present disclosure provide a volume detection device and a smart warehouse to improve the volume detection accuracy of an article or express.
  • the embodiment of the present disclosure provides a volume detection device, including an artificial intelligence AI algorithm board, a depth camera, a visual light source module, and a visual control board; the visual control board is connected to the AI algorithm board and the visual light source module , The visual control board is configured to send a light intensity control signal to the visual light source module to control the light intensity inside the visual light source module, send a volume measurement instruction to the AI algorithm board, and be configured to receive the The volume measurement information returned by the AI algorithm board; the depth camera is embedded in the visual light source module and is connected to the AI algorithm board. Measure the depth picture of the object, and transmit the depth picture to the AI algorithm board; the AI algorithm board is set to calculate the measured object according to the received depth picture after receiving the volume measurement instruction The volume measurement information of the object, and the volume measurement information is returned to the vision control board.
  • the embodiment of the present disclosure also provides a smart warehouse, including the above-mentioned volume detection device, a main control board, an industrial computer, and a motor board;
  • the main control board is connected to the motor board, the industrial computer, and the visual control board in the volume detection device; the industrial computer is configured to receive external instructions and send the external instructions to the main Control board; the main control board is configured to send volume detection instructions to the vision control board, receive volume measurement information returned by the vision control board, and instruct the motor board to measure the object according to the received volume measurement information Transport to a suitable location.
  • FIG. 1 is a schematic structural diagram of a volume detection device provided by an embodiment of the present disclosure
  • Figure 2 is a schematic structural diagram of a smart warehouse provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic block diagram of a vision control board in a volume detection device provided by an embodiment of the present disclosure
  • Fig. 4 is a functional principle diagram of a visual control board in a volume detection device provided by an embodiment of the present disclosure.
  • FIG 1 shows a schematic structural diagram of a volume detection device provided by an embodiment of the present disclosure. This embodiment may be suitable for detecting the volume of solid objects or express items. As shown in Figure 1, the volume described in this embodiment
  • the detection device includes: an artificial intelligence (AI) algorithm board 110, a depth camera 130, a visual light source module 120, and a vision control board 140.
  • AI artificial intelligence
  • the visual control board 140 is connected to the AI algorithm board 110 and the visual light source module 120, and the visual control board 140 is configured to send a light intensity control signal to the visual light source module 120 to control the visual light source
  • the brightness inside the module 120 sends a volume measurement instruction to the AI algorithm board 110, and is configured to receive the volume measurement information returned by the AI algorithm board 110.
  • the depth camera 130 is embedded in the visual light source module 120 and is connected to the AI algorithm board 110.
  • the depth camera 130 is configured to capture the depth of the measured object after receiving the shooting instruction of the AI algorithm board 110 Image, and transmit the depth image to the AI algorithm board 110.
  • the AI algorithm board 110 is configured to, after receiving the volume measurement instruction, calculate the volume measurement information of the measured object according to the received depth image, and return the volume measurement information to the vision control ⁇ 140 ⁇ Plate 140.
  • the volume measurement information may include one or more of volume, height, volume over-range information (that is, whether the volume of the measured object exceeds a preset range), and volume measurement unsuccessful information.
  • the vision control board 140 may also be configured to adjust the brightness control signal (for example, to the visual light source model) according to the received volume measurement information (for example, volume measurement unsuccessful information).
  • the group 120 sends a brightness control signal), and sends the adjusted volume measurement instruction to the AI algorithm board 110 again, and receives the volume measurement information returned by the AI algorithm board 110.
  • the visual control board 140 includes a dimming circuit and a Microcontroller Unit (MCU); the dimming circuit is connected to the visual light source module 120 and is configured to The visual light source module 120 sends the light intensity control signal to control the light intensity inside the visual light source module 120; the MCU is connected to the AI algorithm board 110 and is configured to send to the AI algorithm board 110 The volume measurement instruction is set to receive the volume measurement information returned by the AI algorithm board 110.
  • MCU Microcontroller Unit
  • the visual light source module 120 has a built-in uniform light emitting diode (Light Emitting Diode, LED), and the dimming circuit is an LED constant current dimming circuit.
  • the vision control board 140 can be connected to the AI algorithm board 110 through a Universal Asynchronous Receiver/Transmitter (UART) at a close distance, and the AI algorithm board 110 uses transistor-transistor logic (Transistor logic) through the UART. -Transistor Logic, TTL) in the form of a serial port signal to return the volume measurement information to the vision control board 140.
  • the depth camera 130 may be connected to the AI algorithm board 110 through a universal serial bus (Universal Serial Bus, USB).
  • the AI algorithm board 110 may include a reduced instruction set microprocessor (Advanced RISC Machines, ARM) 4-core A53 processor, graphics processing unit (GPU), DDR4 memory, embedded multimedia controller (Embedded MultiMedia Card, eMMC) flash memory, USB3.0 interface and High Definition Multimedia Interface (HDMI) interface.
  • a reduced instruction set microprocessor Advanced RISC Machines, ARM
  • GPU graphics processing unit
  • DDR4 memory DDR4 memory
  • embedded multimedia controller Embedded MultiMedia Card, eMMC
  • HDMI High Definition Multimedia Interface
  • the volume detection device described in the embodiment of the present disclosure adopts a depth camera, a visual light source module 120 and an AI algorithm board 110 to measure the contour and volume of an object, which can improve the volume detection accuracy of an article or express.
  • Fig. 2 shows a schematic structural diagram of a smart bin provided by an embodiment of the present disclosure.
  • this embodiment discloses a smart bin including the volume detection device.
  • the smart warehouse described in this embodiment includes the volume detection device shown in the embodiment shown in FIG. 1, the main control board 150, the industrial computer 160, and the motor board 170.
  • the volume detection device includes the AI algorithm board 110 and the depth camera 130.
  • the visual light source module 120 and the visual control board 140, the connection structure of multiple components is shown in FIG.
  • the connection relationship between 140 and the way of information exchange are shown in the embodiment described in FIG. 1, which is not described in detail in this embodiment.
  • the main control board 150 is connected to the motor board 170, the industrial computer 160, and the visual control board 140 in the volume detection device; Sent to the main control board 150; the main control board 150 is configured to send a volume detection instruction to the vision control board 140, receive the volume measurement information returned by the vision control board 140, and according to the received volume measurement information The motor board 170 is instructed to transfer the measured object to a suitable position.
  • the motor board 170 instructs the motor board 170 to transfer the measured object to a suitable position, and the pre-storage position of the measured object in the bin can be determined, and The motor board 170 is controlled to transfer the measured object to the pre-storage position.
  • the visual light source module 120 and the depth camera 130 in the volume detection device are installed on the top of the access port of the smart warehouse; the size of the visual light source module 120 and the storage of the smart warehouse Match the size of the top of the mouth.
  • the depth camera 130 described in this embodiment can be connected to an AI algorithm board 110 (for example, an AI artificial intelligence board) with a GPU through a USB3.0 to process high-resolution pictures and quickly run the AI algorithm.
  • the visual light source module 120 is used to provide a shooting light source, and the light brightness is adjusted according to an algorithm.
  • This embodiment solves the problem of identifying the contour of the object and prompting how to correctly place the object to be measured when the object to be measured exceeds the area where the tray is placed.
  • volume calculation and height measurement are used, and the measured object is transferred to the shelf after the measurement, and suitable space is allocated.
  • This embodiment can increase the shelf space utilization rate, increase the storage capacity, and realize the efficient storage of the smart warehouse.
  • AI algorithm board 110 can use NVIDIA ETSON NANO embedded AI algorithm board, its CPU is ARM 4-core A53 processor, AI algorithm board 110 can also include NVIDIA GPU, large-capacity DDR4 memory, eMMC flash memory, USB3.0 interface and HDMI interface .
  • the depth camera 130 adopts the Intel real sense 3D depth camera 130, which has a deep field of view, high-speed sensing global shutter, can perform 3D real sense scanning, with a minimum accuracy of 10 mm, and supports a USB3.0 interface.
  • the visual light source module 120 has a built-in uniform LED with adjustable brightness, which can be adjusted in combination with the camera and the AI algorithm board 110.
  • the central part of the visual light source module 120 is hollowed out, and the depth camera 130 is embedded in the visual light source module 120.
  • the size of the visual light source module 120 is customized according to the size of the top of the access port.
  • the visual light source module 120 and the depth camera 130 are installed in the storage Take the top of the mouth.
  • the power line of the visual light source module 120 is connected to the visual control board 140.
  • the camera is connected to the AI algorithm board 110 through a USB3.0 cable, and the serial UART signal of the AI algorithm board 110 is connected to the vision control board 140.
  • the vision control board 140 communicates with the AI algorithm board 110, controls the work of the AI algorithm board, and receives information processed by the AI algorithm board, that is, information such as the volume, length, width, and height of the object, and whether it is over-edge.
  • the constant current dimming circuit on the visual control board 140 adjusts the switch and brightness of the visual light source module 120.
  • the vision control board 140 communicates with the main control board 150 through RS485, reports the visual inspection information to the main control board 150 and the industrial computer 160, and controls the motor board 170 to drive the motor to move the object to a suitable position.
  • the visual control board 140 performs the function of intermediate signal control and processing, and connects the volume detection device and the main control board 150.
  • the output of the AI algorithm board 110 is a TTL serial port signal, which is weak and cannot be transmitted over a long distance.
  • the vision control board 140 needs to be installed close to the AI algorithm board.
  • the information processed by the MCU on the visual control board 140 is transmitted to the main control board 150 through the RS485 bus, and the main control board 150 also controls the visual control board 140.
  • the working principle block diagram of the vision control board 140 is shown in FIG. 3.
  • the vision control board 140 is designed with the LED driving circuit of the vision light source module 120, and the LED driving chip is controlled by the PWM signal to realize functions such as constant current and dimming.
  • the smart warehouse also includes an RS485 circuit and a power supply circuit that communicate with the main control board 150.
  • the functional circuit of the visual control board 140 is shown in FIG. 4.
  • the smart warehouse described in the embodiments of the present disclosure adopts a depth camera, a visual light source module 120 and an AI algorithm board 110 to measure the contour and volume of an object, which can accurately calculate the volume of express items and increase the utilization rate of shelves.
  • volume detection device and the smart bin shown in FIGS. 1-4 are only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions In some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutively represented blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the function involved.
  • Each block in the block diagram and/or flowchart, and The combination of blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

一种体积检测装置，包括AI算法板（110）、深度相机（130）、视觉光源模组（120）和视觉控制板（140）；视觉控制板与AI算法板和视觉光源模组连接，该视觉控制板设置为向视觉光源模组发送光亮度控制信号，向AI算法板发送体积测量指令，以及设置为接收AI算法板返回的体积测量信息；深度相机内嵌于该视觉光源模组中，与AI算法板连接，深度相机设置为接收AI算法板的拍摄指令后拍摄被测物体的深度图片，并将深度图片传输给该AI算法板；该AI算法板设置为在接收到该体积测量指令之后，根据接收到的该深度图片计算该被测物体的体积测量信息，以及将该体积测量信息返回给该视觉控制板。还涉及一种具有该体积检测装置的智能仓。

Description

体积检测装置和智能仓
本申请要求在2020年03月02日提交中国专利局、申请号为202010135137.3的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及信息处理技术领域，例如涉及一种体积检测装置和智能仓。
背景技术
近年来，随着电子商务的迅猛发展，和电子商务息息相关的快递业务呈高速增长趋势，但快递末端的“最后一公里”投递问题却成为快递发展的瓶颈，智能快递柜和快递仓在此环境下应运而生。
传统快递柜展现在人们面前的是中间人机交互面板、左右两边是格口柜子。人到交互面板前操作控制格口开门，走到已开门的格口位置存取件，往格口存取件后关门。快递仓就如同立体仓库，人机交互面板和快递柜类似，不同的是存取件不是分配格口，而是在面板前就可以完成投递和接收，即面板前只有一个存取口，存件时存取口打开，把快递或物品放在存取口托盘上，之后存取口关闭，快递仓内部运动机构会自动把快递或物品传送到适合的位置。取件时，也只需要在存取口等待数秒，快递仓内部运动机构会自动把要取的快递或物品传送到存取口，存取口门打开后取走快递或物品，存取口自动关闭。
快递仓相对快递柜要便利和自动化，但是快递或物品的体积不容易测量，有采用光栅测量长宽高的，但只是粗略值，对不规则物体，比如衣物，测量差异大，测量精确不高。
发明内容
本公开实施例提供一种体积检测装置和智能仓，以提高物品或快递的体积检测精度。
本公开实施例提供了一种体积检测装置，包括人工智能AI算法板、深度相机、视觉光源模组和视觉控制板；所述视觉控制板与所述AI算法板和所述视觉光源模组连接，所述视觉控制板设置为向所述视觉光源模组发送光亮度控制信号以控制所述视觉光源模组内部的光亮度，向所述AI算法板发送体积测量指令，以及设置为接收所述AI算法板返回的体积测量信息；所述深度相机内嵌于所述视觉光源模组中，与所述AI算法板连接，所述深度相机设置为接收所述AI算 法板的拍摄指令后拍摄被测物体的深度图片，并将所述深度图片传输给所述AI算法板；所述AI算法板设置为在接收到所述体积测量指令之后，根据接收到的所述深度图片计算所述被测物体的体积测量信息，以及将所述体积测量信息返回给所述视觉控制板。
本公开实施例还提供了一种智能仓，包括上述的体积检测装置、主控板、工控机和电机板；
所述主控板与所述电机板、所述工控机、以及所述体积检测装置中的视觉控制板连接；所述工控机设置为接收外部指令，并将所述外部指令发送给所述主控板；所述主控板设置为向所述视觉控制板发出体积检测指令，接收所述视觉控制板返回的体积测量信息，根据接收的所述体积测量信息指示所述电机板将被测物体传送到适合位置。
附图说明
图1是本公开实施例提供的一种体积检测装置的结构示意图；
图2是本公开实施例提供的一种智能仓的结构示意图；
图3是本公开实施例提供的一种体积检测装置中视觉控制板的原理框图；
图4是本公开实施例提供的一种体积检测装置中视觉控制板的功能原理图。
具体实施方式
下面将结合附图对本公开实施例的技术方案进行描述，所描述的实施例仅仅是本公开实施例中的一部分实施例，而不是全部的实施例。
本公开实施例中下述多个实施例可以单独执行，多个实施例之间也可以相互结合执行，本公开实施例对此不作限制。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图并通过具体实施方式来说明本公开实施例的技术方案。
图1示出了本公开实施例提供的一种体积检测装置的结构示意图，本实施例可适用于检测固体物品或快递件的体积的情况，如图1所示，本实施例所述的体积检测装置包括：人工智能(Artificial Intelligence，AI)算法板110、深度相机130、视觉光源模组120和视觉控制板140。
所述视觉控制板140与所述AI算法板110和所述视觉光源模组120连接，所述视觉控制板140设置为向所述视觉光源模组120发送光亮度控制信号以控制所述视觉光源模组120内部的光亮度，向所述AI算法板110发送体积测量指令，以及设置为接收所述AI算法板110返回的体积测量信息。
所述深度相机130内嵌于所述视觉光源模组120中，与所述AI算法板110连接，所述深度相机130设置为接收所述AI算法板110的拍摄指令后拍摄被测物体的深度图片，并将所述深度图片传输给所述AI算法板110。
所述AI算法板110设置为在接收到所述体积测量指令之后，根据接收到的所述深度图片计算所述被测物体的体积测量信息，以及将所述体积测量信息返回给所述视觉控制板140。
所述体积测量信息可包括体积、高度、体积超范围信息(即被测物体积是否超出预设范围)和体积测量不成功信息等内容中的一个或多个。根据本公开的一个或多个实施例，所述视觉控制板140还可设置为根据接收的所述体积测量信息(例如体积测量不成功信息)调整所述光亮度控制信号(例如向视觉光源模组120发送调亮控制信号)，并再次向所述AI算法板110发送调整后的体积测量指令，以及接收所述AI算法板110返回的体积测量信息。
根据本公开的一个或多个实施例，所述视觉控制板140包括调光电路和微控制单元(Microcontroller Unit，MCU)；所述调光电路与所述视觉光源模组120连接，设置为向所述视觉光源模组120发送所述光亮度控制信号以控制所述视觉光源模组120内部的光亮度；所述MCU与所述AI算法板110连接，设置为向所述AI算法板110发送所述体积测量指令，并设置为接收所述AI算法板110返回的体积测量信息。
根据本公开的一个或多个实施例，所述视觉光源模组120内置均匀发光二极管(Light Emitting Diode，LED)，所述调光电路为LED恒流调光电路。所述视觉控制板140可以与所述AI算法板110通过通用异步收发传输器(Universal Asynchronous Receiver/Transmitter，UART)近距离连接，所述AI算法板110通过所述UART以晶体管-晶体管逻辑(Transistor-Transistor Logic，TTL)串口信号的形式将所述体积测量信息返回给所述视觉控制板140。所述深度相机130可以与所述AI算法板110通过通用串行总线(Universal Serial Bus，USB)接带连接。所述AI算法板110可包括精简指令集微处理器(Advanced RISC Machines，ARM)4核A53处理器、图形处理器(Graphics Processing Unit，GPU)、DDR4内存、嵌入式多媒体控制器(Embedded Multi Media Card，eMMC)闪存、USB3.0接口和高清多媒体接口(High Definition Multimedia Interface，HDMI)接口。
本公开实施例所述的体积检测装置采用深度相机、视觉光源模组120和AI 算法板110实现物体轮廓和体积的测量，能够提高物品或快递的体积检测精度。
图2示出了本公开实施例提供的一种智能仓的结构示意图，本实施例以前述体积检测装置实施例为基础，公开了一种包含该体积检测装置的智能仓。本实施例所述的智能仓包括图1所述实施例所示的体积检测装置、主控板150、工控机160和电机板170，其中所述体积检测装置包括AI算法板110、深度相机130、视觉光源模组120和视觉控制板140，多个部件连接结构如图2所示，其中所述体积检测装置所包括的AI算法板110、深度相机130、视觉光源模组120和视觉控制板140之间的连接关系及信息交互方式见图1所述实施例所示，本实施例对此不作赘述。
所述主控板150与所述电机板170、所述工控机160、以及所述体积检测装置中的视觉控制板140连接；所述工控机160设置为接收外部指令，并将所述外部指令发送给所述主控板150；所述主控板150设置为向所述视觉控制板140发出体积检测指令，接收所述视觉控制板140返回的体积测量信息，根据接收的所述体积测量信息指示所述电机板170将被测物体传送到适合位置。
在一实施例中，根据接收的所述体积测量信息指示所述电机板170将所述被测物传送到适合位置，可确定所述被测物在所述仓体中的预存放位置，以及控制所述电机板170将所述被测物传送到所述预存放位置。
于一实施例中，所述体积检测装置中的视觉光源模组120和深度相机130安装于所述智能仓的存取口顶部；所述视觉光源模组120的尺寸与所述智能仓的存取口顶部的尺寸相配合。
本实施例所述的深度相机130可通过USB3.0接带GPU的AI算法板110(例如AI人工智能板卡)，处理高分辨率图片，快速运行AI算法。采用视觉光源模组120提供拍摄光源，光亮度按算法调节。本实施例解决了物品轮廓识别、当被测物体超出放置托盘的区域，提示如何正确放置被测物体的问题。本实施例通过体积计算、高度测量，测量后将被测物体传送到货架，分配适合的空间。本实施例能够提升货架空间使用率，提高存储量，实现智能仓的高效存储。
本实施例所述的体积检测装置采用的器件包括AI算法板110、深度相机130、视觉光源模组120和视觉控制板140。AI算法板110可采用英伟达ETSON NANO嵌入式AI算法板，其CPU为ARM 4核A53处理器，AI算法板110还可以包括英伟达GPU、大容量DDR4内存、eMMC闪存、USB3.0接口和HDMI接口。深度相机130采用因特尔实感3D深度相机130，具有深度视野、高速感应全局快门，能够进行3D实感扫描，最小精度为10mm，支持USB3.0接口。 视觉光源模组120内置均匀LED，亮度可调，结合相机和AI算法板110进行调节。视觉光源模组120中部镂空，深度相机130嵌入视觉光源模组120内，视觉光源模组120的尺寸按存取口顶部尺寸定制视觉光源模组，视觉光源模组120和深度相机130安装于存取口顶部。
视觉光源模组120的电源线接视觉控制板140。相机通过USB3.0线接AI算法板110，AI算法板110的串口UART信号接视觉控制板140。视觉控制板140和AI算法板110通信，控制AI算法板工作，接收AI算法板处理后的信息，即物体体积、长宽高和是否超边等信息。视觉控制板140上的恒流调光电路调节视觉光源模组120的开关和亮度。视觉控制板140通过RS485和主控板150通信，将视觉检测信息上报主控板150和工控机160，控制电机板170驱动电机动作，把物体传送到适合的位置。
如图2所示，视觉控制板140起到了中间信号控制和处理的功能，连接了体积检测装置和主控板150。AI算法板110输出是TTL串口信号，信号弱，不能长距离传输。视觉控制板140需要近距离安装在AI算法板旁。视觉控制板140上的MCU处理后的信息通过RS485总线传送到主控板150，主控板150也对视觉控制板140进行控制。视觉控制板140的工作原理框图如图3。
视觉控制板140设计了视觉光源模组120的LED驱动电路，通过PWM信号控制LED驱动芯片，实现恒流和调光等功能。另外智能仓还包括和主控板150通信的RS485电路、电源电路等。视觉控制板140功能电路如图4所示。
本公开实施例所述的智能仓采用深度相机、视觉光源模组120和AI算法板110实现物体轮廓和体积的测量，解够精确计算快递件的体积，能够使货架使用率增大。
图1-4示出的体积检测装置和智能仓仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
附图中的框图，图示了按照本公开实施例多种实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专 用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。

Claims (10)

  1. 一种体积检测装置，包括：人工智能AI算法板、深度相机、视觉光源模组和视觉控制板；
    所述视觉控制板与所述AI算法板和所述视觉光源模组连接，所述视觉控制板设置为向所述视觉光源模组发送光亮度控制信号以控制所述视觉光源模组内部的光亮度，向所述AI算法板发送体积测量指令，以及设置为接收所述AI算法板返回的体积测量信息；
    所述深度相机内嵌于所述视觉光源模组中，与所述AI算法板连接，所述深度相机设置为接收所述AI算法板的拍摄指令后拍摄被测物体的深度图片，并将所述深度图片传输给所述AI算法板；
    所述AI算法板设置为在接收到所述体积测量指令之后，根据接收到的所述深度图片计算所述被测物体的体积测量信息，以及将所述体积测量信息返回给所述视觉控制板。
  2. 根据权利要求1所述的体积检测装置，其中，所述视觉控制板还设置为：
    根据接收的所述体积测量信息调整所述光亮度控制信号，并再次向所述AI算法板发送调整后的体积测量指令，以及接收所述AI算法板返回的体积测量信息。
  3. 根据权利要求1所述的体积检测装置，其中，所述体积测量信息包括体积、高度、体积超范围信息和体积测量不成功信息。
  4. 根据权利要求1所述的体积检测装置，其中，所述视觉控制板包括调光电路和微控制单元MCU；
    所述调光电路与所述视觉光源模组连接，设置为向所述视觉光源模组发送所述光亮度控制信号以控制所述视觉光源模组内部的光亮度；
    所述MCU与所述AI算法板连接，设置为向所述AI算法板发送所述体积测量指令，并设置为接收所述AI算法板返回的体积测量信息。
  5. 根据权利要求4所述的体积检测装置，其中，所述视觉光源模组内置均匀发光二极管LED，所述调光电路为LED恒流调光电路。
  6. 根据权利要求1所述的体积检测装置，其中，所述视觉控制板与所述AI算法板通过通用异步收发传输器UART近距离连接，所述AI算法板通过所述UART以晶体管-晶体管逻辑TTL串口信号的形式将所述体积测量信息返回给所述视觉控制板。
  7. 根据权利要求1所述的体积检测装置，其中，所述深度相机与所述AI算法板通过通用串行总线USB接带连接。
  8. 根据权利要求1所述的体积检测装置，其中，所述AI算法板包括精简指令集微处理器ARM4核A53处理器、图形处理器GPU、DDR4内存、嵌入式多媒体控制器eMMC闪存、USB3.0接口和高清多媒体接口HDMI接口。
  9. 一种智能仓，包括如权利要求1-8中任一项所述的体积检测装置、主控板、工控机和电机板；
    所述主控板与所述电机板、所述工控机、以及所述体积检测装置中的视觉控制板连接；
    所述工控机设置为接收外部指令，并将所述外部指令发送给所述主控板；
    所述主控板设置为向所述视觉控制板发出体积检测指令，接收所述视觉控制板返回的体积测量信息，根据接收的所述体积测量信息指示所述电机板将被测物体传送到适合位置。
  10. 根据权利要求9所述的智能仓，其中，所述体积检测装置中的视觉光源模组和深度相机安装于所述智能仓的存取口顶部；
    所述视觉光源模组的尺寸与所述智能仓的存取口顶部的尺寸相配合。
PCT/CN2020/091579 2020-03-02 2020-05-21 体积检测装置和智能仓 WO2021174682A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010135137.3 2020-03-02
CN202010135137.3A CN111229635B (zh) 2020-03-02 2020-03-02 体积检测装置和智能仓

Publications (1)

Publication Number Publication Date
WO2021174682A1 true WO2021174682A1 (zh) 2021-09-10

Family

ID=70861939

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/091579 WO2021174682A1 (zh) 2020-03-02 2020-05-21 体积检测装置和智能仓

Country Status (2)

Country Link
CN (1) CN111229635B (zh)
WO (1) WO2021174682A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114345714A (zh) * 2021-12-29 2022-04-15 北京京东振世信息技术有限公司 一种物品分拣方法和装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112082478A (zh) * 2020-09-05 2020-12-15 深圳市华星视讯科技有限公司 一种高精度光学背光式尺寸测量仪

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005022079A1 (de) * 2003-08-27 2005-03-10 Siemens Aktiengesellschaft Vorrichtung zur bestimmung des volumens von fördergut
CN107855287A (zh) * 2017-12-15 2018-03-30 广东工业大学 一种快递货物体积自动检测系统
CN108447088A (zh) * 2018-03-21 2018-08-24 轻客智能科技（江苏）有限公司 一种用于快递寄件的体积测量方法及装置
CN109068051A (zh) * 2018-06-19 2018-12-21 江苏高远智能科技有限公司 一种工业相机自适应智能调节装置
CN110610341A (zh) * 2019-09-20 2019-12-24 深圳市丰巢科技有限公司 一种智能仓、智能仓的派件方法和智能仓的取件方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6974373B2 (en) * 2002-08-02 2005-12-13 Geissler Technologies, Llc Apparatus and methods for the volumetric and dimensional measurement of livestock
CN105403155A (zh) * 2015-12-22 2016-03-16 中国计量学院 一种基于机器视觉的小微型轴类部件尺寸在线检测装置
CN107449501A (zh) * 2017-08-17 2017-12-08 深圳市异方科技有限公司 一种产品自动称重读码及尺寸体积测量系统
CN110084849B (zh) * 2019-05-09 2021-03-19 福建（泉州）哈工大工程技术研究院 具有自动测量体积和重量功能的物流系统
CN110017773B (zh) * 2019-05-09 2021-12-17 福建（泉州）哈工大工程技术研究院 一种基于机器视觉的包裹体积测量方法
CN212069566U (zh) * 2020-03-02 2020-12-04 深圳市丰巢科技有限公司 体积检测装置和智能仓

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005022079A1 (de) * 2003-08-27 2005-03-10 Siemens Aktiengesellschaft Vorrichtung zur bestimmung des volumens von fördergut
CN107855287A (zh) * 2017-12-15 2018-03-30 广东工业大学 一种快递货物体积自动检测系统
CN108447088A (zh) * 2018-03-21 2018-08-24 轻客智能科技（江苏）有限公司 一种用于快递寄件的体积测量方法及装置
CN109068051A (zh) * 2018-06-19 2018-12-21 江苏高远智能科技有限公司 一种工业相机自适应智能调节装置
CN110610341A (zh) * 2019-09-20 2019-12-24 深圳市丰巢科技有限公司 一种智能仓、智能仓的派件方法和智能仓的取件方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114345714A (zh) * 2021-12-29 2022-04-15 北京京东振世信息技术有限公司 一种物品分拣方法和装置
CN114345714B (zh) * 2021-12-29 2023-11-03 北京京东振世信息技术有限公司 一种物品分拣方法和装置

Also Published As

Publication number Publication date
CN111229635A (zh) 2020-06-05
CN111229635B (zh) 2023-11-28

Similar Documents

Publication Publication Date Title
WO2021174682A1 (zh) 体积检测装置和智能仓
US10518414B1 (en) Navigation method, navigation system, movement control system and mobile robot
US10467806B2 (en) Volume dimensioning systems and methods
CN110460782A (zh) 信息采集装置、方法、巡检机器人和存储介质
US10671843B2 (en) Technologies for detecting interactions with surfaces from a spherical view of a room
TW452723B (en) Method and apparatus for three-dimensional input entry
CN103019385B (zh) 一种基于红外的3d手势识别控制器及实现方法
CN205537542U (zh) 一种用于三维图像建模的人体和衣物的照片自动采集系统
US20140267866A1 (en) Non-uniform correction illumination pattern
CN108372130B (zh) 一种基于fpga图像处理的目标定位分拣系统及其实现方法
CN104317391A (zh) 一种基于立体视觉的三维手掌姿态识别交互方法和系统
CN103135753A (zh) 手势输入的方法及系统
CN102216890A (zh) 带有图像传感器和信号处理器的触摸输入
CN204303078U (zh) 基于机器视觉辅助的贩卖机货物存储及取拿系统
TW201227538A (en) Method and apparatus for tracking target object
US20130127705A1 (en) Apparatus for touching projection of 3d images on infrared screen using single-infrared camera
TWI671692B (zh) 智慧監控系統及監控方法
CN105425937A (zh) 可与3d影像互动的手势控制系统
US20190164281A1 (en) Robotic pill filling, counting, and validation
CN105329641A (zh) 输送控制装置及输送控制方法
CN102741881A (zh) 布料制品识别装置和布料制品抓持系统
CN212069566U (zh) 体积检测装置和智能仓
CN110046566A (zh) 一种基于图形识别及物联网技术的实验室智能物料柜
Shah et al. Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementation using Serial Communication
CN102135795B (zh) 移动侦测装置

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: 20923010

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: 20923010

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20923010

Country of ref document: EP

Kind code of ref document: A1