CN112591356A - Stacking visual detection system in closed or semi-closed limited space - Google Patents

Stacking visual detection system in closed or semi-closed limited space Download PDF

Info

Publication number
CN112591356A
CN112591356A CN202011403279.XA CN202011403279A CN112591356A CN 112591356 A CN112591356 A CN 112591356A CN 202011403279 A CN202011403279 A CN 202011403279A CN 112591356 A CN112591356 A CN 112591356A
Authority
CN
China
Prior art keywords
module
image
control
detection
semi
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202011403279.XA
Other languages
Chinese (zh)
Inventor
陈新
王辉
汪良红
毛桂豪
朱婷
欧栋生
林学森
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan Longshen Robot Co Ltd
Original Assignee
Foshan Longshen Robot Co Ltd
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 Foshan Longshen Robot Co Ltd filed Critical Foshan Longshen Robot Co Ltd
Priority to CN202011403279.XA priority Critical patent/CN112591356A/en
Publication of CN112591356A publication Critical patent/CN112591356A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
    • B65G1/02—Storage devices
    • B65G1/04—Storage devices mechanical
    • B65G1/0407—Storage devices mechanical using stacker cranes
    • B65G1/0421—Storage devices mechanical using stacker cranes with control for stacker crane operations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/71—Circuitry for evaluating the brightness variation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
    • B65G2203/04—Detection means
    • B65G2203/041—Camera

Abstract

The invention provides a stacking visual detection system in a closed or semi-closed limited space, and relates to the technical field of material handling. The visual palletizing detection system under the closed or semi-closed confined space comprises: the control and processing system comprises an image filtering module, an image transformation module, an edge detection module, a feature extraction module and a target processing module, and the camera module is used for collecting images, converting the images into corresponding image data and inputting the image data into the control and processing system. According to the visual palletizing detection system in the closed or semi-closed confined space, the regions of all the target objects detected by the feature extraction module can be mapped onto the image with the original resolution according to the corresponding proportion through the target processing module, and in use, a reasonable serial-parallel processing framework is adopted, so that higher detection speed is obtained under the condition of ensuring enough detection precision, and meanwhile, the hardware configuration cost is reasonable.

Description

Stacking visual detection system in closed or semi-closed limited space
Technical Field
The invention relates to the technical field of material handling, in particular to a palletizing visual detection system in a closed or semi-closed limited space.
Background
In order to facilitate the packing and transportation of goods in logistics labor, the goods are usually stacked together and then redistributed, and the stacking belongs to an essential step of factory production and logistics transportation. The visual detection of the palletizing system is a basic research content in pattern recognition and artificial intelligence, and aims to detect whether a target object with a specific characteristic exists in an image or not and give the area position and the area size of the target object if the target object exists. Typically, the palletizing system visual inspection is divided into three steps: constructing a classifier for the target object based on specific features and an algorithm; acquiring an image to be detected possibly containing a target object by adopting an image acquisition system; and extracting specific characteristics corresponding to the target object from the image to be detected, and detecting the target object by using a classifier.
However, in the prior art, when the existing palletizing vision detecting system is used, the detection result of illumination on a target object is greatly influenced, the exposure time of the existing image collecting system is fixed or is artificially set before shooting, and the existing palletizing vision detecting system cannot be well adapted to the light intensity change of the external environment, so that the image quality is reduced due to the light intensity change of the environment, and the detection interference is serious.
Disclosure of Invention
The present invention provides an object of providing a palletizing vision detection system under a closed or semi-closed confined space, which solves the problems of the background art described above.
In order to achieve the purpose, the invention is realized by the following technical scheme: a palletising vision detection system under confined or semi-confined spaces comprising:
the control and processing system comprises an image filtering module, an image transformation module, an edge detection module, a feature extraction module and a target processing module.
And the camera module is used for collecting images and converting the images into corresponding image data to be input into the control and processing system.
And the image acquisition module is used for processing the image information acquired by the camera module and transmitting the image information to the control and processing system.
And the light intensity detection module is used for detecting the illumination intensity.
And the camera configuration module is used for configuring parameters of the camera module and configuring the exposure time of the camera module according to the light intensity signal fed back by the light intensity detection module.
And the stacking system is internally provided with a computer system and is used for processing each received signal and transmitting the signal so as to control each module to work.
The picture storage module is used for storing the images received by the stacking system.
And the detection output module outputs the detection result.
And the detection execution module is used for receiving the control signal and executing the control command.
And the control module is used for controlling the detection execution module to work after receiving the signal output by the stacking system.
And the communication interface control module is used for transmitting signals of the control and processing system.
And the communication interface module is used for carrying out level conversion on signals transmitted between the control and processing system and the stacking system.
As a further scheme of the invention: the image filtering module is a state filtering module and a median filtering module, and is used for enhancing and denoising the acquired image information.
As a further scheme of the invention: the image transformation module changes the representation domain and representation data of the image through orthogonal transformation and unitary edge transformation.
As a further scheme of the invention: the edge detection module is used for identifying points with obvious brightness change in the image.
As a further scheme of the invention: the characteristic extraction module is used for extracting characteristic information in the collected image.
As a further scheme of the invention: and the target processing module is used for mapping the areas of all the targets detected by the feature extraction module onto the image with the original resolution according to the corresponding proportion.
As a further scheme of the invention: the output end of the camera module is electrically connected with the input end of the image acquisition module through a conducting wire, the output end of the light intensity detection module is electrically connected with the input end of the camera configuration module through a conducting wire, and the output end of the camera configuration module is electrically connected with the input end of the camera module through a conducting wire.
As a further scheme of the invention: the output of image acquisition module passes through wire and control and processing system's input electric connection, the output of image filtering module passes through wire and image transform module's input electric connection, image transform module's output passes through wire and edge detection module's input electric connection, edge detection module's output passes through wire and characteristic extraction module's input electric connection, characteristic extraction module's output passes through wire and target processing module's input electric connection.
As a further scheme of the invention: the output end of the control and processing system is electrically connected with the input end of the communication interface control module through a wire, the communication interface control module is electrically connected with the communication interface module in a bidirectional mode through a wire, the output end of the communication interface module is electrically connected with the input end of the stacking system through a wire, the stacking system is electrically connected with the picture storage module in a bidirectional mode through a wire, the output end of the stacking system is electrically connected with the input ends of the detection output module and the control module through wires, and the output end of the control module is electrically connected with the input end of the detection execution module through a wire.
The invention provides a palletizing visual detection system in a closed or semi-closed confined space. The method has the following beneficial effects:
(1) this pile up neatly vision detection system under closed or semi-closed confined space, carry out real-time detection through the light intensity of light intensity detection module to the shooting environment of camera module, according to the exposure time of the light intensity value dynamic adjustment camera module that detects, in the settable range of the exposure time of camera module, suitably shorten the exposure time when the light intensity value increases, suitably increase the exposure time when the light intensity value reduces, the image quality that makes the camera module shoot is higher, improve the precision that the target object detected, thereby the exposure time of having solved current image acquisition system is fixed unchangeable or the people sets for before shooting, the light intensity change of external environment makes image quality descend, detect the defect that produces serious interference to the target object.
(2) The visual palletizing detection system under the closed or semi-closed confined space can enhance and denoise collected image information through the image filtering module, can change the representation domain and representation data of an image through orthogonal transformation and unitary edge transformation through the image transformation module, can realize points with obvious brightness change in an identification image through the edge detection module, can extract characteristic information in the collected image through the characteristic extraction module, can map all target object regions detected by the characteristic extraction module to the image with original resolution according to corresponding proportion through the target processing module, adopts a reasonable serial-parallel processing framework in use, obtains higher detection speed under the condition of ensuring enough detection precision, and simultaneously has reasonable hardware configuration cost.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
In the figure: 1. a camera module; 2. an image acquisition module; 3. a camera configuration module; 4. a light intensity detection module; 5. a control and processing system; 6. a palletizing system; 7. a picture storage module; 8. a detection execution module; 9. a control module; 10. a detection output module; 11. a communication interface control module; 12. a communication interface module; 13. a target processing module; 14. a feature extraction module; 15. an edge detection module; 16. an image transformation module; 17. and an image filtering module.
Detailed Description
The invention will be further illustrated with reference to the following examples and drawings:
referring to fig. 1: a palletising vision detection system under confined or semi-confined spaces comprising: the control and processing system 5, the control and processing system 5 includes an image filtering module 17, an image transformation module 16, an edge detection module 15, a feature extraction module 14 and a target processing module 13, the camera module 1 is used for collecting images and converting the images into corresponding image data to be input into the control and processing system 5, according to the size of the detection area, the camera module 1 adopts a single camera mode or a multi-camera mode, under the multi-camera mode, all cameras are arranged according to a specific mode, ensuring that the images of adjacent areas are collected at the same time, so that the images of larger area range are collected than under the single camera mode, the image collection module 2 processes the image information collected by the camera module 1 and transmits the image information to the control and processing system 5, the light intensity detection module 4 is used for detecting the intensity of illumination, the camera configuration module 3, the camera configuration module 3 is used for configuring parameters of the camera module 1 and configuring the exposure time of the camera module 1 according to the light intensity signal fed back by the light intensity detection module 4, the palletizing system 6 contains a computer system for processing each received signal and transmitting the signal to control each module to work, the picture storage module 7 is used for storing the image received by the palletizing system 6, the detection output module 10 outputs the detection result, the detection execution module 8 is used for receiving the control signal and executing the control command, the control module 9 controls the detection execution module 8 to work through the control module 9 after receiving the signal output by the palletizing system 6, the control system comprises a communication interface control module 11, the communication interface control module 11 is used for transmitting signals of the control and processing system 5, and the communication interface module 12 is used for performing level conversion on the signals transmitted between the control and processing system 5 and the palletizing system 6.
Specifically, the image filtering module 17 is a dynamic filtering module and a median filtering module, and the image filtering module 17 is configured to enhance and denoise the acquired image information.
Specifically, the image transform module 16 changes the representation domain and the representation data of the image through orthogonal transform and unitary edge transform.
In particular, the edge detection module 15 is used to implement the identification of points in the image where the brightness variation is significant.
Specifically, the feature extraction module 14 is configured to extract feature information in the acquired image.
Specifically, the target processing module 13 is configured to map, in a corresponding ratio, regions where all the targets detected by the feature extraction module 14 are located onto the image with the original resolution.
Specifically, the output end of the camera module 1 is electrically connected to the input end of the image acquisition module 2 through a conducting wire, the output end of the light intensity detection module 4 is electrically connected to the input end of the camera configuration module 3 through a conducting wire, and the output end of the camera configuration module 3 is electrically connected to the input end of the camera module 1 through a conducting wire, so that signal transmission can be performed in use.
Specifically, the output end of the image acquisition module 2 is electrically connected to the input end of the control and processing system 5 through a wire, the output end of the image filtering module 17 is electrically connected to the input end of the image transformation module 16 through a wire, the output end of the image transformation module 16 is electrically connected to the input end of the edge detection module 15 through a wire, the output end of the edge detection module 15 is electrically connected to the input end of the feature extraction module 14 through a wire, the output end of the feature extraction module 14 is electrically connected to the input end of the target processing module 13 through a wire, and signal transmission can be performed in use.
Specifically, the output end of the control and processing system 5 is electrically connected to the input end of the communication interface control module 11 through a wire, the communication interface control module 11 is electrically connected to the communication interface module 12 through a wire in a bidirectional manner, the output end of the communication interface module 12 is electrically connected to the input end of the stacking system 6 through a wire, the stacking system 6 is electrically connected to the picture storage module 7 in a bidirectional manner, the output end of the stacking system 6 is electrically connected to the input ends of the detection output module 10 and the control module 9 through wires, the output end of the control module 9 is electrically connected to the input end of the detection execution module 8 through a wire, and signal transmission can be performed in use.
The above is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, many variations and modifications can be made without departing from the inventive concept of the present invention, which falls into the protection scope of the present invention.

Claims (9)

1. A visual palletization detection system in a confined space, closed or semi-closed, comprising:
the system comprises a control and processing system (5), wherein the control and processing system (5) comprises an image filtering module (17), an image transformation module (16), an edge detection module (15), a feature extraction module (14) and a target processing module (13);
the camera module (1), the camera module (1) is used for collecting images and converting the images into corresponding image data to be input into the control and processing system (5);
the image acquisition module (2) is used for processing the image information acquired by the camera module (1) and transmitting the image information to the control and processing system (5);
the light intensity detection module (4), the said light intensity detection module (4) is used for detecting the intensity of illumination;
the camera configuration module (3), the camera configuration module (3) is used for configuring parameters of the camera module (1) and configuring the exposure time of the camera module (1) according to the light intensity signal fed back by the light intensity detection module (4);
the stacking system (6) is internally provided with a computer system and is used for processing each received signal and transmitting the signal so as to control each module to work;
the picture storage module (7) is used for storing the images received by the stacking system (6);
the detection output module (10), the detection output module (10) outputs the detection result;
the detection execution module (8), the detection execution module (8) is used for receiving the control signal and executing the control command;
the control module (9) receives the signal output by the stacking system (6), and the control module (9) controls the detection execution module (8) to work;
a communication interface control module (11), wherein the communication interface control module (11) is used for transmitting signals of the control and processing system (5);
a communication interface module (12), the communication interface module (12) being configured to level-shift signals transmitted between the control and processing system (5) and the palletizing system (6).
2. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the image filtering module (17) is a state filtering module and a median filtering module, and the image filtering module (17) is used for enhancing and denoising the acquired image information.
3. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the image transformation module (16) changes the representation domain and representation data of the image by orthogonal transformation and unitary edge transformation.
4. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the edge detection module (15) is used for identifying points with obvious brightness change in the image.
5. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the characteristic extraction module (14) is used for extracting characteristic information in the acquired image.
6. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the target processing module (13) is used for mapping the regions of all the targets detected by the feature extraction module (14) onto the image with the original resolution according to the corresponding proportion.
7. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the output end of the camera module (1) is electrically connected with the input end of the image acquisition module (2) through a conducting wire, the output end of the light intensity detection module (4) is electrically connected with the input end of the camera configuration module (3) through a conducting wire, and the output end of the camera configuration module (3) is electrically connected with the input end of the camera module (1) through a conducting wire.
8. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the output of image acquisition module (2) passes through the input electric connection of wire and control and processing system (5), the output of image filtering module (17) passes through the input electric connection of wire and image transformation module (16), the input electric connection of wire and edge detection module (15) is passed through to the output of edge detection module (15) and characteristic extraction module (14), the input electric connection of wire and target processing module (13) is passed through to the output of characteristic extraction module (14).
9. A palletising vision inspection system under confined or semi-confined space as claimed in claim 1 wherein: the output of control and processing system (5) passes through the input electric connection of wire with communication interface control module (11), communication interface control module (11) passes through the two-way electric connection of wire with communication interface module (12), the output of communication interface module (12) passes through the input electric connection of wire with pile up neatly system (6), pile up neatly system (6) passes through the two-way electric connection of wire with picture storage module (7), the output of pile up neatly system (6) pass through the wire respectively with the input electric connection who detects output module (10) and control module (9), the output of control module (9) has the input electric connection who detects execute module (8) through the wire.
CN202011403279.XA 2020-12-04 2020-12-04 Stacking visual detection system in closed or semi-closed limited space Pending CN112591356A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011403279.XA CN112591356A (en) 2020-12-04 2020-12-04 Stacking visual detection system in closed or semi-closed limited space

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011403279.XA CN112591356A (en) 2020-12-04 2020-12-04 Stacking visual detection system in closed or semi-closed limited space

Publications (1)

Publication Number Publication Date
CN112591356A true CN112591356A (en) 2021-04-02

Family

ID=75188131

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011403279.XA Pending CN112591356A (en) 2020-12-04 2020-12-04 Stacking visual detection system in closed or semi-closed limited space

Country Status (1)

Country Link
CN (1) CN112591356A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1043689A2 (en) * 1999-04-08 2000-10-11 Fanuc Ltd Image processing apparatus
CN105825219A (en) * 2016-05-10 2016-08-03 梁伟棠 Machine vision detection system
CN108286938A (en) * 2018-02-06 2018-07-17 陕西理工大学 A kind of Machine Vision Inspecting System
CN111251296A (en) * 2020-01-17 2020-06-09 温州职业技术学院 Visual detection system suitable for pile up neatly electric motor rotor
CN111470327A (en) * 2020-05-25 2020-07-31 常州墨狄机器人科技有限公司 Visual stacking equipment and visual information processing method thereof
CN111776761A (en) * 2019-06-06 2020-10-16 广西现代职业技术学院 Stacking recognition module and system for zinc ingot stack automatic off-line transferring and reinforcing method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1043689A2 (en) * 1999-04-08 2000-10-11 Fanuc Ltd Image processing apparatus
CN105825219A (en) * 2016-05-10 2016-08-03 梁伟棠 Machine vision detection system
CN108286938A (en) * 2018-02-06 2018-07-17 陕西理工大学 A kind of Machine Vision Inspecting System
CN111776761A (en) * 2019-06-06 2020-10-16 广西现代职业技术学院 Stacking recognition module and system for zinc ingot stack automatic off-line transferring and reinforcing method
CN111251296A (en) * 2020-01-17 2020-06-09 温州职业技术学院 Visual detection system suitable for pile up neatly electric motor rotor
CN111470327A (en) * 2020-05-25 2020-07-31 常州墨狄机器人科技有限公司 Visual stacking equipment and visual information processing method thereof

Similar Documents

Publication Publication Date Title
CN106886216B (en) Robot automatic tracking method and system based on RGBD face detection
CN111008961B (en) Transmission line equipment defect detection method and system, equipment and medium thereof
CN101915910B (en) Method and system for identifying marine oil spill object by marine radar
CN102496157A (en) Image detection method based on Gaussian multi-scale transform and color complexity
CN110705847A (en) Intelligent substation inspection method and system based on image recognition technology
US10824885B2 (en) Method and apparatus for detecting braking behavior of front vehicle of autonomous vehicle
CN105405138B (en) Waterborne target tracking based on conspicuousness detection
CN104056790A (en) Intelligent potato sorting method and apparatus
CN112528979B (en) Transformer substation inspection robot obstacle distinguishing method and system
JP5701181B2 (en) Image processing apparatus, image processing method, and computer program
Bhujade et al. Detection of power-lines in complex natural surroundings
CN104573713A (en) Mutual inductor infrared image recognition method based on image textual features
CN113673584A (en) Image detection method and related device
CN105825219A (en) Machine vision detection system
CN102930279A (en) Image identification method for detecting product quantity
CN113034526B (en) Grabbing method, grabbing device and robot
CN115423982B (en) Three-dimensional detection method for desktop curling based on images and depth
CN112591356A (en) Stacking visual detection system in closed or semi-closed limited space
CN111830051A (en) Transformer substation equipment oil leakage detection method and detection system based on deep learning
Bo et al. Research on weed recognition method based on invariant moments
Wang et al. An efficient method of shadow elimination based on image region information in HSV color space
CN111652055B (en) Intelligent switch instrument identification method based on two-stage positioning
CN111488889B (en) Intelligent image processor for extracting image edges
US20230009925A1 (en) Object detection method and object detection device
CN213365525U (en) License plate recognition system based on linear array CCD camera device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210402

RJ01 Rejection of invention patent application after publication