CN110610141A - Logistics storage regular shape goods recognition system - Google Patents
Logistics storage regular shape goods recognition system Download PDFInfo
- Publication number
- CN110610141A CN110610141A CN201910787103.XA CN201910787103A CN110610141A CN 110610141 A CN110610141 A CN 110610141A CN 201910787103 A CN201910787103 A CN 201910787103A CN 110610141 A CN110610141 A CN 110610141A
- Authority
- CN
- China
- Prior art keywords
- goods
- image
- module
- cargo
- cargos
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a logistics storage regular-shape cargo identification system which comprises a cargo information statistics module, an image acquisition module, an image preprocessing module, a cargo identification module and a cargo adjustment warehousing module. The invention uses a machine to identify the category and the goods placing mode of the goods, classifies and adjusts the goods for warehousing, solves the problem that the goods are time-consuming and labor-consuming to carry manually, realizes the automatic warehouse goods management, judges the category, the placing mode and the angle of the goods by the shape and the color characteristic of the top view of the goods on the conveyor belt and by the image processing technology, and adjusts the warehousing by the mechanical arm.
Description
Technical Field
The invention relates to the technical field of logistics sorting detection, in particular to a logistics storage regular-shape goods identification system.
Background
The logistics warehouse is an important component of advanced manufacturing field, computer integrated manufacturing system and modern logistics technology, and plays a significant role in the development of manufacturing industry. The existing warehouse still stays in an automation stage, and one main problem of the automatic warehouse is that during picking operation, most of wharfs or ports still need to manually identify goods and carry out warehouse entry and exit operation, which wastes time and labor.
At present, the automatic identification operation of the objects in and out of the warehouse mainly adopts three modes:
firstly, scanning a bar code. The barcode recognition technology is the most mature recognition technology currently used, and a group of fixed format codes containing cargo information are attached to the surface of the cargo to identify relevant information, and recognition is performed in the circulation process of cargo containers through recognition equipment and the recognition technology. In a non-automatic logistics warehousing system, the goods identification system is widely applied and also applied to an automatic stereoscopic warehouse.
However, the bar code is damaged in the using process, and the reliability of the bar code is influenced because the bar code has a high error rate in automatic identification. In addition, due to the limitation of the identification technology, the information contained in the bar code is single, and the identification system cannot meet the application requirements along with the continuous improvement of the automation level and the working efficiency of the stereoscopic warehouse.
And II, RFID technology. Radio Frequency Identification (RFID) technology using a non-contact IC card technology is a technological development direction currently applied to an automated stereoscopic warehouse. The technology is a non-contact automatic Identification technology realized by Radio Frequency Identification (RFID) technology, also called electronic Tag (E-Tag) technology, through Radio Frequency communication. Rfid systems generally consist of two parts, namely an electronic Tag (transponder) and a Reader (Reader). In the practical application of the RFID, the electronic tag is attached to an identified article (surface or inside), and when an identified object with the electronic tag passes through a readable range of the reader, the reader automatically reads out the identification information in the electronic tag in a non-contact manner, so as to realize the function of automatically identifying the article or automatically collecting the identification information of the article. The mode has the greatest advantages that the non-contact working mode is adopted, manual intervention is not needed in the whole identification process, the method is suitable for realizing automation, is not easy to damage, can identify high-speed moving objects and can identify a plurality of radio frequency tags simultaneously, and the operation is rapid and convenient. Has better adaptability to severe environments such as oil stains, dust pollution and the like.
Through the search of the prior art, Chinese patent application numbers: 201220505565.1, patent name: the utility model provides an intelligent warehouse management system, this application scheme provides one the utility model provides an intelligent warehouse management system, including video acquisition equipment, video transmission equipment, server group, the RFID read write line, alarm device, the LED display screen, storage device, server group includes data processing server, image processing server, streaming media transfer server, central control server is server group's core, be used for unified control and send instruction to give image processing server, data processing server, streaming media transfer server, thereby realize different functions, and handle the information that each server feedbacks back. The manipulation of the image is not involved and has the following drawbacks: the RFID tag is added with an RFID emitter, a reader, an encoder, an antenna and other equipment, so that the cost is high; the manual labeling increases the labor capacity; items or environments that contain metal and moisture can affect the RFID. Although barcode technology and RFID technology have become mature, they are not an inherent property of goods and are quite different from the way people know things. Therefore, how to efficiently realize automatic identification of goods by using the characteristics of the goods itself is an urgent problem to be solved in the technical field of logistics.
And thirdly, identifying an article image. Image recognition refers to a technique of processing, analyzing and understanding an image with a computer to recognize various different patterns of objects and objects. In general industrial use, an industrial camera is adopted to shoot pictures, and then software is utilized to further identify and process the pictures according to the gray level difference of the pictures. The patent application name of Chinese patent application No. 201810642072.4 is a supermarket warehouse goods identification and classification method based on target identification and KNN algorithm, and the application scheme provides a supermarket warehouse goods identification and classification method based on target identification and KNN algorithm, which comprises the following steps: acquiring cargo image sample data; preprocessing sample data; extracting a target contour; selecting a minimum external rectangle of the target; calculating the average RGB value and histogram distribution of the whole area; and matching the sample to be detected with the training sample by a KNN algorithm. The method only classifies the article types, cannot judge the placement of the objects, and is not suitable for the logistics storage system. The patent application name of China application No. 201711467294.9 provides an intelligent warehouse goods identification system based on goods image identification technology, which comprises a data input module, a data storage module, an analysis and comparison module, a phase acquisition module, an output module and an abnormity alarm module. And comparing the image of the good product sample with the image of the actual goods by an image identification technology to judge whether the detected goods are correct good products. Similarly, the method only classifies the article types, cannot judge the placement of the objects, and is not suitable for the logistics storage system.
Disclosure of Invention
The invention aims to provide a logistics storage regular-shape goods identification system which can identify the types of goods and judge the positions and the placing modes of the goods so as to sort and store the goods.
The technical scheme for realizing the purpose of the invention is as follows: a logistics storage regular shape cargo identification system comprises a cargo information statistics module, an image acquisition module, an image preprocessing module, a cargo identification module and a cargo adjustment warehousing module;
the cargo information statistical module is used for acquiring the length, width, height, radius and side length of all sample cargos and establishing a cargo information database according to the average color information;
the image acquisition module is used for acquiring video information and transmitting the video information to the image preprocessing module;
the image preprocessing module is used for subtracting each acquired frame of image from the background, and performing image filtering, graying, binarization, corrosion, expansion, edge detection, contour extraction and image filling processing;
the goods identification module is used for judging the shape of goods according to the characteristics, extracting the color in the ROI area and finally determining the type and the placing mode of the goods;
and the cargo adjusting and warehousing module controls the moving distance and the rotating angle of the mechanical arm according to the identification result, and sorts and warehouses the cargos and stacks the cargos orderly.
Compared with the prior art, the invention has the following remarkable advantages: (1) compared with the traditional manual sorting, carrying and warehousing, the method for processing the images by the machine greatly liberates manpower and improves the operation efficiency; (2) compared with bar code identification, the automatic identification of the goods is efficiently realized by utilizing the characteristics of the goods, and the bar code is not needed to be stained; (3) compared with RFID label identification, the method does not need manual labeling, simplifies the process, and reduces the cost by using a single camera.
Drawings
Fig. 1 is a block diagram of a logistics storage regular shape goods identification system according to the invention.
FIG. 2 is a system block diagram of the hardware portion of the system of the present invention.
Fig. 3 is a mechanical structure diagram of the image acquisition module of the present invention.
FIG. 4 is a schematic diagram of the image pre-processing module of the present invention.
Fig. 5 is a schematic diagram of the cargo identification module of the present invention.
Detailed Description
The automatic warehouse goods management can solve the problems that manual sorting and carrying are time-consuming and labor-consuming in wharfs, ports and the like, and warehousing is more efficient. The image identification method makes up the defects of the existing bar code scanning, RFID and image identification methods.
As shown in fig. 1, the invention provides a logistics storage regular shape cargo identification system, which comprises a cargo information statistics module, an image acquisition module, an image preprocessing module, a cargo identification module and a cargo adjustment warehousing module;
the cargo information statistical module is used for acquiring the length, width, height, radius and side length of all sample cargos and establishing a cargo information database according to the average color information; so as to compare with the processed test goods characteristics, thereby obtaining the test goods type and the placing mode.
The image acquisition module is used for acquiring video information and transmitting the video information to the image preprocessing module; image acquisition is the process of acquiring images of a scene from a job site. The CCD camera with the advantages of high sensitivity, strong light resistance, small distortion, small size, long service life, vibration resistance and the like is used for acquiring continuous field images, and analog image signals are digitized and then sent to the image processing module.
The image preprocessing module is used for subtracting each acquired frame of image from the background, and performing image filtering, graying, binarization, corrosion, expansion, edge detection, contour extraction and image filling processing;
the goods identification module is used for judging the shape of goods according to the characteristics, extracting the color in the ROI and finally determining the type and the placing mode of the goods;
and the cargo adjusting and warehousing module controls the moving distance and the rotating angle of the mechanical arm according to the identification result, and sorts and warehouses the cargos and stacks the cargos orderly.
The average color information acquisition method comprises the following steps: and (3) shooting pictures of a plurality of cargos, converting the pictures into an LAB color space, selecting a region where the cargos are located, carrying out three-channel color histogram statistics, and solving the average color of the cargos.
The image acquisition module comprises a front-end camera, a transmission line and a memory, the front-end camera is connected with an industrial personal computer through the transmission line and used for acquiring video signals, and the industrial personal computer is connected with the image preprocessing module and used for converting the acquired analog video signals into digital video sequences and transmitting the digital video sequences to the image preprocessing module; image acquisition module mechanical structure picture as shown in fig. 3, camera fixed mounting uses the light filling lamp to reduce the light influence directly over the conveyer belt.
The image preprocessing comprises graying, image filtering, background subtraction, binaryzation, corrosion, expansion and image filling; wherein: the background image and the current image are obtained from the memory, graying, image filtering, background subtraction, binaryzation, corrosion, expansion and image filling processing are sequentially carried out, the image preprocessing module is connected with the goods identification module, and the processing process is shown in fig. 4.
The goods identification module comprises an edge detection module, a shape detection module, a contour drawing module, an interested region color analysis module and a goods information module of a comparison database. Wherein: the shape detection is to calculate the perimeter and the number of vertexes of the graph by using a Laplace edge detection algorithm. Firstly, judging whether the geometric figure is circular or not, namely judging whether the ratio of the square of the perimeter of the figure to the area is in a specified range or not, otherwise, judging the number of vertexes, namely, a triangle is equal to 3, and a rectangle is equal to 4. If the rectangular shape is adopted, the cargo types can be continuously subdivided according to the ratio of the length to the width, and whether the cargo is placed in the right direction or in the side direction can be judged according to the ratio. The perimeter and the area of the geometric figure are output while the shape of the geometric figure is recognized. And drawing a contour after the shape detection, setting the inside of the contour as an interested area, and analyzing the color. Finally, the type and the placing mode of the goods are judged through shape detection and color detection, and the specific flow is shown in fig. 5.
And the step of adjusting and warehousing the goods is to control the moving distance and the rotating angle of the mechanical arm according to the identification result, and classify and warehouse the goods and stack the goods orderly. Wherein: the hardware part of the whole system for adjusting and warehousing the goods mainly comprises a human-computer interface, a PLC control system, a camera, a driving unit, a servo system, a goods shelf bin and mechanical parts. And data monitoring and data writing-in are carried out on the programmable controller through a human-computer interface, so that the warehouse is monitored, goods are identified and goods are extracted.
The system of the present invention is further described below in conjunction with the appended figures.
Examples
A logistics storage rule goods identification system comprises a goods information statistics module, an image acquisition module, an image preprocessing module, a goods identification module and a goods adjusting and warehousing module;
the cargo information statistical module is used for acquiring the length, width, height, radius, side length and average color information of all sample cargos to establish a cargo information database. So as to compare with the processed test goods characteristics, thereby obtaining the test goods type and the placing mode. And acquiring average color information to acquire photos of a plurality of cargos, converting the photos into an LAB color space, selecting a region where the cargos are located, performing three-channel color histogram statistics, and obtaining the average color of the cargos.
The image acquisition module receives the analog video signal and digitizes the analog video signal through A/D, or directly receives the digital video data digitized by the camera. The image acquisition part stores the digital image in the internal memory of the industrial personal computer. The image acquisition module reads the current frame every 30ms according to a preset program and delay, so that a continuous video signal is obtained. The average background picture is obtained by taking 5 background pictures of the conveyor belt without goods and averaging.
An image preprocessing module: for the acquired digital image, due to the influence of equipment and environmental factors, the accuracy is often influenced by interferences of different degrees, such as noise, geometric deformation, color misregistration and the like. For this purpose, the acquired images have to be preprocessed. The preprocessing process comprises graying, image filtering, background subtraction, binaryzation, corrosion, expansion and image filling.
Graying is a processing process of obtaining a single-channel grayscale image by a weighted average method for an RGB color picture. And performing Gaussian filtering on the average background picture and the current frame after graying, and subtracting the processed average background picture and the current frame by using background subtraction to obtain a difference image. And a proper threshold value is set, the difference image is subjected to corrosion and expansion treatment after binarization, noise is eliminated, the edge is clearer, a closed boundary is obtained, but holes with large and small sizes still exist inside the difference image, and a relatively complete cargo image is obtained by a hole filling method.
The goods identification module is used for detecting edges, judging the shape of goods according to the characteristics, extracting the color in the ROI after the outline is drawn, and finally determining the type and the placing mode of the goods.
And (3) shape detection:
(1) circular: a circle is the most specific of all regular geometric figures, the ratio of the square of the perimeter to the area fluctuates around 4 pi, the radius contrast has no effect, so a circle is considered as long as the identified figure satisfies this condition.
(2) Rectangle: if the number of the vertexes is equal to 4, the vertex is rectangular; otherwise, the other geometry. Similar to the circular recognition, the phenomenon that the number of vertexes is not 4 may occur in the actual detection process of the rectangle, the detected vertexes need to be judged again in the same neighborhood region, whether some vertexes belong to the same neighborhood region or not is judged, the embodiment is 8 neighborhood regions, if so, only one vertex is left to remove other vertexes, and thus the result can be well corrected, and the occurrence of error detection can be avoided. With this method, it is well recognized that the detected pattern is rectangular.
(3) Triangle: the identification of triangles is similar to the identification method of rectangles, and the geometrical shapes to which the figures belong are judged by the number of vertexes.
And the Laplace edge detection algorithm is used for calculating the perimeter and the number of vertexes of the graph. And after the geometric figure is detected by using a Laplace edge detection algorithm, accumulating the number of boundary points to obtain the perimeter of the geometric figure. Then, the boundary points are further distinguished to find out the top points. After the preprocessing and feature extraction of the image are completed, the judgment of the shape of the geometric figure can be started according to the feature information. In the process, it is first determined whether the geometric figure is circular, that is, whether the ratio of the square of the perimeter of the figure to the area is within a predetermined range. If so, it is circular; otherwise, judging the number of the vertexes, wherein the vertexes are triangular when the number is equal to 3, and the vertexes are rectangular when the number is equal to 4. The perimeter and the area of the geometric figure can be output while the shape of the geometric figure is recognized. Because the perimeter, area and vertex coordinates of the regular geometric figure are known, parameters such as side length, centroid and the like can be calculated.
Color detection:
and outputting the contour sequence, corresponding to the current frame to form an ROI (region of interest), solving a three-channel average value (x, y, z) of the RGB (red, green and blue) image in the ROI, comparing the three-channel average value with a sample cargo information base, finding out the most possible cargo type, and performing auxiliary judgment.
The placing mode is as follows:
and for rectangular cargos, judging whether the cargos are placed in the front or in the side direction according to the ratio of the length to the width.
And the cargo adjusting and warehousing step is to control the moving distance and the rotating angle of the mechanical arm according to the identification result, sort and stack the cargos in a warehouse.
As shown in fig. 2, the hardware part of the whole system mainly comprises a human-computer interface, a PLC control system, a camera, a driving unit, a servo system, a shelf space and mechanical components. And data monitoring and data writing-in are carried out on the programmable controller through a human-computer interface, so that the warehouse is monitored, goods are identified and goods are extracted. And the corresponding interface can be displayed by clicking the corresponding picture, and the length, width, height, radius, side length and average color information of the sample goods are conveniently input in the manifest.
The image acquisition part is as shown in figure 3, a camera is fixed above the conveying belt, and a circle of light supplement lamps are arranged around the upper side of the camera. When the goods are transmitted to the lower part of the camera, the goods image appears in the picture shot by the camera, and the identification module can identify the type and the placing mode of the goods.
The image preprocessing part comprises graying, background subtraction, image filtering, binarization, corrosion, expansion and image filling as shown in figure 4. Obtaining a current frame and an average background image, respectively carrying out graying and Gaussian filtering, subtracting to obtain a difference image, carrying out binarization processing, then carrying out corrosion and expansion processing, eliminating noise, making the edge clearer, obtaining a closed boundary, and filling the inside of the current frame and the average background image with a hole filling method.
As shown in fig. 5, the cargo identification part first detects the edge of the preprocessed image, extracts the contour, determines the type of the cargo according to the shape and the color, and determines the cargo placement mode according to the contour information.
According to the logistics storage regular-shape goods identification system, the type and the placing mode of goods on the conveying belt can be well judged. The system greatly liberates manpower and improves efficiency; compared with bar code identification, the automatic identification of the goods is efficiently realized by utilizing the characteristics of the goods, and the bar code is not needed to be stained; compared with RFID label identification, the method does not need manual labeling, simplifies the process, reduces the cost by using a single camera, and has good market prospect.
Claims (6)
1. A logistics storage regular shape cargo identification system is characterized by comprising a cargo information statistics module, an image acquisition module, an image preprocessing module, a cargo identification module and a cargo adjustment warehousing module;
the cargo information statistical module is used for acquiring the length, width, height, radius and side length of all sample cargos and establishing a cargo information database according to the average color information;
the image acquisition module is used for acquiring video information and transmitting the video information to the image preprocessing module;
the image preprocessing module is used for subtracting each acquired frame of image from the background, and performing image filtering, graying, binarization, corrosion, expansion, edge detection, contour extraction and image filling processing;
the goods identification module is used for judging the shape of goods according to the characteristics, extracting the color in the ROI area and finally determining the type and the placing mode of the goods;
and the cargo adjusting and warehousing module controls the moving distance and the rotating angle of the mechanical arm according to the identification result, and sorts and warehouses the cargos and stacks the cargos orderly.
2. The logistics storage regular shape cargo identification system of claim 1, wherein the average color information acquisition method comprises: and (3) shooting pictures of a plurality of cargos, converting the pictures into an LAB color space, selecting a region where the cargos are located, carrying out three-channel color histogram statistics, and solving the average color of the cargos.
3. The system for recognizing regular-shaped goods in logistics storage according to claim 1, wherein the image acquisition module comprises a front-end camera, a transmission line and a memory, the front-end camera is fixedly installed right above the conveyor belt and connected with an industrial personal computer through the transmission line for acquiring video signals, and the industrial personal computer is connected with the image preprocessing module for converting the acquired analog video signals into digital video sequences and transmitting the digital video sequences to the image preprocessing module.
4. The logistics storage regular shape cargo identification system of claim 1, wherein: the image preprocessing module acquires a background image and a current image from a memory, and sequentially performs graying, image filtering, background subtraction, binarization, corrosion, expansion and image filling processing.
5. The logistics storage regular shape cargo identification system of claim 1, wherein: the cargo identification module calculates the perimeter and the number of vertexes of the graph by adopting a Laplace edge detection algorithm, firstly judges whether the geometric graph is circular, namely judges whether the ratio of the square of the perimeter to the area of the graph is in a specified range, and otherwise, judges the number of vertexes, namely, a triangle is equal to 3 and a rectangle is equal to 4; if the goods are rectangular, continuously subdividing the goods according to the ratio of the length to the width; outputting the perimeter and the area of the geometric figure while identifying the shape of the geometric figure; drawing a contour after the shape detection, setting the inside as an interested area, and analyzing the color; and finally, judging the category and the placing mode of the goods through shape detection and color detection.
6. The system according to claim 5, wherein the cargo is placed on the front or side according to the ratio of the length to the width of the rectangle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787103.XA CN110610141A (en) | 2019-08-25 | 2019-08-25 | Logistics storage regular shape goods recognition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787103.XA CN110610141A (en) | 2019-08-25 | 2019-08-25 | Logistics storage regular shape goods recognition system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110610141A true CN110610141A (en) | 2019-12-24 |
Family
ID=68890798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910787103.XA Withdrawn CN110610141A (en) | 2019-08-25 | 2019-08-25 | Logistics storage regular shape goods recognition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610141A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111146728A (en) * | 2020-01-10 | 2020-05-12 | 北京电子工程总体研究所 | Efficient closed-loop focusing system and method for power grid laser foreign matter removing device |
| CN111476524A (en) * | 2020-04-09 | 2020-07-31 | 广州创显科教股份有限公司 | Goods picking method, system and device for finished product delivery based on artificial intelligence and readable storage medium |
| CN111957592A (en) * | 2020-08-06 | 2020-11-20 | 姜斌 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
| CN112124957A (en) * | 2020-08-31 | 2020-12-25 | 苏州吉成智能科技有限公司 | Automatic medicine warehousing method and system |
| CN112464707A (en) * | 2020-10-14 | 2021-03-09 | 浙江科技学院 | Conveying device with image acquisition function and data processing method thereof |
| CN112733985A (en) * | 2021-01-27 | 2021-04-30 | 昆山善思光电科技有限公司 | Method for automatically identifying large and small material trays |
| CN113780935A (en) * | 2021-08-09 | 2021-12-10 | 北京国电光宇机电设备有限公司 | Intelligent logistics receiving and dispatching system and method |
| CN114781982A (en) * | 2022-06-17 | 2022-07-22 | 广州朗通科技有限公司 | Cold chain warehouse management method and system |
| CN114866764A (en) * | 2022-05-10 | 2022-08-05 | 安徽睿极智能科技有限公司 | Universal video terminal large-batch whole machine testing method and system |
| CN114971466A (en) * | 2022-05-23 | 2022-08-30 | 杭州精逸创新跨境电商服务有限公司 | Warehouse management system for overseas warehouse based on data acquisition |
| CN115376242A (en) * | 2022-08-22 | 2022-11-22 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
| CN115410390A (en) * | 2022-08-19 | 2022-11-29 | 河南泽阳实业有限公司 | Intelligent scheduling method for intelligent port |
| CN116187908A (en) * | 2023-03-21 | 2023-05-30 | 江陵县百顺通达物流有限公司 | Warehouse logistics intelligent management method and system based on image recognition |
| CN116611773A (en) * | 2023-05-26 | 2023-08-18 | 网赢如意仓供应链有限公司 | Warehouse inventory checking system and method based on offline checking |
-
2019
- 2019-08-25 CN CN201910787103.XA patent/CN110610141A/en not_active Withdrawn
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111146728A (en) * | 2020-01-10 | 2020-05-12 | 北京电子工程总体研究所 | Efficient closed-loop focusing system and method for power grid laser foreign matter removing device |
| CN111146728B (en) * | 2020-01-10 | 2021-04-02 | 北京电子工程总体研究所 | Efficient closed-loop focusing system and method for power grid laser foreign matter removing device |
| CN111476524A (en) * | 2020-04-09 | 2020-07-31 | 广州创显科教股份有限公司 | Goods picking method, system and device for finished product delivery based on artificial intelligence and readable storage medium |
| CN111476524B (en) * | 2020-04-09 | 2023-11-24 | 广州创显科教股份有限公司 | Goods picking method, system, device and readable storage medium for finished product delivery based on artificial intelligence |
| CN111957592A (en) * | 2020-08-06 | 2020-11-20 | 姜斌 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
| CN112124957A (en) * | 2020-08-31 | 2020-12-25 | 苏州吉成智能科技有限公司 | Automatic medicine warehousing method and system |
| CN112124957B (en) * | 2020-08-31 | 2022-04-15 | 苏州吉成智能科技有限公司 | Automatic medicine warehousing method and system |
| CN112464707A (en) * | 2020-10-14 | 2021-03-09 | 浙江科技学院 | Conveying device with image acquisition function and data processing method thereof |
| CN112733985A (en) * | 2021-01-27 | 2021-04-30 | 昆山善思光电科技有限公司 | Method for automatically identifying large and small material trays |
| CN113780935A (en) * | 2021-08-09 | 2021-12-10 | 北京国电光宇机电设备有限公司 | Intelligent logistics receiving and dispatching system and method |
| CN114866764A (en) * | 2022-05-10 | 2022-08-05 | 安徽睿极智能科技有限公司 | Universal video terminal large-batch whole machine testing method and system |
| CN114866764B (en) * | 2022-05-10 | 2024-08-23 | 安徽睿极智能科技有限公司 | Universal method and system for testing large-scale complete machines of video terminals |
| CN114971466A (en) * | 2022-05-23 | 2022-08-30 | 杭州精逸创新跨境电商服务有限公司 | Warehouse management system for overseas warehouse based on data acquisition |
| CN114781982A (en) * | 2022-06-17 | 2022-07-22 | 广州朗通科技有限公司 | Cold chain warehouse management method and system |
| CN115410390A (en) * | 2022-08-19 | 2022-11-29 | 河南泽阳实业有限公司 | Intelligent scheduling method for intelligent port |
| CN115376242A (en) * | 2022-08-22 | 2022-11-22 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
| CN115376242B (en) * | 2022-08-22 | 2023-08-08 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
| CN116187908A (en) * | 2023-03-21 | 2023-05-30 | 江陵县百顺通达物流有限公司 | Warehouse logistics intelligent management method and system based on image recognition |
| CN116187908B (en) * | 2023-03-21 | 2023-12-22 | 岳阳礼一科技股份有限公司 | Warehouse logistics intelligent management method and system based on image recognition |
| CN116611773A (en) * | 2023-05-26 | 2023-08-18 | 网赢如意仓供应链有限公司 | Warehouse inventory checking system and method based on offline checking |
| CN116611773B (en) * | 2023-05-26 | 2024-02-23 | 网赢如意仓供应链有限公司 | Warehouse inventory checking system and method based on offline checking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610141A (en) | Logistics storage regular shape goods recognition system | |
| KR102579783B1 (en) | Vision inspection system by using remote learning of product defects image | |
| CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN109949331B (en) | Container edge detection method and device | |
| Shen et al. | A positioning lockholes of container corner castings method based on image recognition | |
| CN106203239B (en) | Information processing method, device and system for container tallying | |
| Zhong et al. | Blob analyzation-based template matching algorithm for LED chip localization | |
| Abbas et al. | Automated sorting and grading of agricultural products based on image processing | |
| CN108171098B (en) | Bar code detection method and equipment | |
| CN114332622A (en) | Label detection method based on machine vision | |
| CN113688965B (en) | Automatic storage code scanning detection method and cargo management system | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN112581452A (en) | Industrial accessory surface defect detection method and system, intelligent device and storage medium | |
| CN110807354A (en) | Industrial production line product counting method | |
| CN113724322A (en) | Cargo pallet positioning method and system for unmanned forklift | |
| CN113145473A (en) | Intelligent fruit sorting system and method | |
| CN105448095A (en) | Yellow label car detection method and device | |
| CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
| US20230152781A1 (en) | Manufacturing intelligence service system connected to mes in smart factory | |
| KR100503724B1 (en) | Finding objects in an image | |
| CN115860605A (en) | Warehouse logistics detection system based on visual identification | |
| EP3098758B1 (en) | System and method for reading machine readable codes in transportation and logistic applications | |
| CN115082567A (en) | Automatic target detection sample acquisition and labeling method, system and medium | |
| CN114187583A (en) | Rapid identification method for container and flat car loading combined identification |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191224 |