CN116596953B - A method and apparatus for segmenting shelf images - Google Patents
A method and apparatus for segmenting shelf imagesInfo
- Publication number
- CN116596953B CN116596953B CN202310622179.3A CN202310622179A CN116596953B CN 116596953 B CN116596953 B CN 116596953B CN 202310622179 A CN202310622179 A CN 202310622179A CN 116596953 B CN116596953 B CN 116596953B
- Authority
- CN
- China
- Prior art keywords
- plug
- shelf
- coordinates
- regions
- areas
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a device for dividing shelf images, which are applied to a shelf with a plurality of guide rails, wherein the edge of each guide rail is provided with a plug, and the plugs are used for preventing price tags on the guide rails from sliding out of the guide rails; detecting plug areas based on each goods shelf guide rail area respectively to obtain coordinates of a plurality of plug areas on the goods shelf image; and fitting a dividing line according to the coordinates of the plug areas, and dividing the shelf image based on the dividing line. The embodiment of the application can avoid small target detection, thereby accurately realizing the division of the shelf image.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly relates to a method and a device for dividing shelf images.
Background
With the rapid development of artificial intelligence, smart retailing has also been rapidly developed under its impetus. The intelligent digital shelf is an important foothold of intelligent retail, however, how to finely manage the intelligent digital shelf is important, and small shelf division is a sharp tool for finely managing the intelligent digital shelf.
The small goods shelf division management can carry out fine intelligent classification and management on goods, can help the super-manufacturer to realize quick, accurate and efficient management of goods display, can also help the super-manufacturer to realize quick search and positioning of goods, and improves shopping convenience and experience of users. In general, small shelf division is an important field of artificial intelligence technology application in the super business industry, and can help super business to realize fine management and optimization, improve operation efficiency and user satisfaction, and further promote the digital, automatic and intelligent development of the super business.
However, when the small shelf is divided by computer vision, the small shelf is divided by detecting the mark due to the complex actual scene environment, and when the mark is too small, it is difficult to ensure the accuracy of small target detection, thereby affecting the accuracy of target detection.
Disclosure of Invention
The embodiment of the application aims to provide a method and a device for dividing a shelf image, which are used for solving the defect of insufficient accuracy of target detection in the prior art.
In order to solve the technical problems, the application is realized as follows:
In a first aspect, a method for segmenting a shelf image is provided, for use with a shelf having a plurality of rails, each rail having an edge provided with a plug for preventing a price tag on the rail from sliding off the rail, the method comprising the steps of:
Acquiring a shelf image, and detecting a plurality of shelf guide rail areas from the shelf image;
Detecting plug areas based on each goods shelf guide rail area respectively to obtain coordinates of a plurality of plug areas on the goods shelf image;
and fitting a dividing line according to the coordinates of the plug areas, and dividing the shelf image based on the dividing line.
In a second aspect, there is provided an apparatus for segmenting a shelf image for use with a shelf having a plurality of rails, each rail having an edge provided with a plug for preventing a price tag on the rail from sliding off the rail, the apparatus comprising:
The acquisition module is used for acquiring a shelf image and detecting a plurality of shelf guide rail areas from the shelf image;
The detection module is used for respectively detecting plug areas based on each shelf guide rail area to obtain coordinates of a plurality of plug areas on the shelf image;
and the segmentation module is used for fitting out a segmentation line according to the coordinates of the plug areas and segmenting the shelf image based on the segmentation line.
In a third aspect, a computer readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, implements the steps of the above-described method of segmenting shelf images.
Compared with the prior art, the application has the following beneficial effects:
According to the embodiment of the application, the plurality of shelf guide rail areas are detected from the shelf image, the plug areas are detected based on each shelf guide rail area, the coordinates of the plurality of plug areas on the shelf image are obtained, the dividing line is fitted according to the detected coordinates of the plurality of plug areas, and the shelf image is divided based on the dividing line, so that small target detection can be avoided, and the division of the shelf image is accurately realized.
Drawings
FIG. 1 is a flow chart of a method for segmenting shelf images provided by an embodiment of the present application;
fig. 2 is a schematic structural diagram of an apparatus for dividing a shelf image according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In order to solve the problems faced by small goods shelf segmentation, the embodiment of the application provides a small goods shelf segmentation method based on goods shelf guide rails and plug detection. In an actual scenario, a plug for preventing the price tag from sliding out of the guide rail exists at the edge of the commercial super shelf guide rail. The small goods shelf segmentation method provided by the embodiment of the application comprises the steps of firstly, attaching a reflective strip on a plug. Secondly, a target detection algorithm in the fields of computer vision and artificial intelligence is used for the shelf guide rail, a detection model is trained and obtained by using a machine learning method based on the image of the target and the label information of the target, target detection is carried out, and the method is adopted for subsequent target detection. And expanding the acquired goods shelf guide rail area, and detecting a reflection strip (plug) in the expanded goods shelf guide rail target area so as to acquire the dividing points of the small goods shelf (the plugs exist at the head and the tail of the goods shelf guide rail, and the area of each small goods shelf can be determined by detecting the plugs). Finally, small shelf division is performed through the division points. The method provided by the embodiment of the application not only does not use the excessively obvious small shelf segmentation mark, but also avoids the precision problem caused by small target detection, and can also meet the requirement of small shelf segmentation of lighting in a dim night scene.
The method for dividing the shelf image provided by the embodiment of the application is described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.
As shown in fig. 1, a flowchart of a method for dividing a shelf image according to an embodiment of the present application is applied to a shelf having a plurality of rails, wherein an edge of each rail is provided with a plug, and the plug is used for preventing a price tag on the rail from sliding out of the rail, and the method includes the following steps:
step 101, acquiring a shelf image, and detecting a plurality of shelf guide rail areas from the shelf image.
And 102, detecting plug areas based on each shelf guide rail area respectively, and obtaining coordinates of a plurality of plug areas on the shelf image.
Specifically, after a plurality of shelf guide rail areas are detected from the shelf image, each shelf guide rail area can be expanded, and accordingly, plug areas can be detected in each expanded shelf guide rail area.
In this embodiment, after detecting plug regions based on each shelf rail region, respectively, coordinates of a plurality of plug regions on the shelf image are obtained, whether two plug regions with intersecting regions exist may be further determined according to the coordinates of the plurality of plug regions on the shelf image, and if so, de-duplication is performed on one plug region of the two plug regions.
In addition, a plurality of price tags can be arranged on the guide rail, correspondingly, after the coordinates of a plurality of plug areas on the shelf image are obtained based on the detection of each shelf guide rail area, whether each plug area has an intersection area with at least one price tag area in the plurality of price tag areas or not can be judged according to the coordinates of the plurality of plug areas on the shelf image and the coordinates of the plurality of price tag areas on the shelf image, and if at least one plug area in the plurality of plug areas has an intersection area with at least one price tag area in the plurality of price tag areas, the at least one plug area is determined to be a false detection area.
In this embodiment, each blocking head may be provided with a reflective element, and correspondingly, the reflective elements may be detected based on each shelf rail region, and the coordinates of the detected reflective elements on the shelf image may be used as the coordinates of the blocking regions on the shelf image.
And 103, fitting a dividing line according to the coordinates of the plug areas, and dividing the shelf image based on the dividing line.
The method comprises the steps of dividing the shelf image into a plurality of end cap areas, and fitting a dividing line according to the coordinates of the end cap areas in each group.
In this embodiment, the grouping of the plurality of plug regions according to the coordinates of the plurality of plug regions specifically includes obtaining a difference value between x-axis coordinates of each plug region, if the difference value between the x-axis coordinates of two plug regions is less than or equal to a preset multiple of a width of one plug region, determining the two plug regions as plug regions in the same group, and correspondingly, calculating an average value of the x-axis coordinates of the plug regions in the same group, and determining a position of a dividing line according to the average value.
According to the embodiment of the application, the plug areas are detected in the shelf guide rail areas, the dividing lines are fitted according to the detected coordinates of the plug areas, and the shelf image is divided based on the dividing lines, so that small target detection can be avoided, and the division of the shelf image is accurately realized.
According to the embodiment of the application, by the small shelf segmentation method based on the shelf guide rail and the plug detection, the small shelf segmentation can be realized by means of the shelf guide rail and the plug of the shelf and on the basis of matching the reflective strips (the color of the reflective strips is similar to that of the shelf guide rail) attached to the plug. The light reflecting strips are materials which can be reflected back to the light source according to the original light ray with certain intensity, and the reason for using the light reflecting strips with similar colors to the guide rails is that 1, the light reflecting strips can realize the division of the small goods shelves on the basis of almost no change to the goods shelves, and 2, the light reflecting strips can realize the division of the small goods shelves under the lighting at night. After the positions of the reflecting strips (plugs) are determined, small shelf dividing lines can be fitted, and the small shelf can be divided.
Specifically, in order to prevent the influence of precision caused by the existence of interference points (interference targets similar to plugs) of the super-commercial images and the direct detection of ultra-small targets such as reflective strips (plugs), the acquired super-commercial images are firstly subjected to shelf guide rail detection, and target detection algorithms in the fields of computer vision and artificial intelligence are used, wherein the algorithms comprise single-stage or two-stage detection and the like. And then, carrying out area expansion on the acquired detection area of the shelf guide rail to avoid missing of a reflection strip (plug), wherein the width of the guide rail detection frame with the size of 1/10 is expanded on two sides. And detecting the reflection strip (plug) of the extended guide rail detection area, wherein the detection method is consistent with the shelf guide rail detection method. Because the reflective strip (plug) detected by the guide rail detection area is the coordinate of the opposite guide rail area, the absolute coordinate of the reflective strip (plug) in the original business super image is determined by dividing the small goods shelf, and the coordinate of the reflective strip (plug) can be returned to the original image by recording the coordinate of the reflective strip (plug) opposite the guide rail area and the coordinate of the guide rail opposite the original image. In order to avoid that the extended guide rail region repeatedly contains plugs in other guide rails, the coordinates of the reflective strips (plugs) returned to the quotient super image are subjected to de-duplication processing, and whether the coordinates returned to the original image have an intersection region or not is judged to be subjected to de-duplication.
Further, the obtained weight-removed reflecting strips (plugs) are grouped in the x-axis, if the difference value of the x-axis coordinates in the reflecting strips (plugs) is within the width of three reflecting strips (plugs), the reflecting strips (plugs) in the same group of dividing lines are judged, so that the dividing lines are fitted, and finally the division of the small goods shelf is completed, wherein the fitting mode is the average value of the x-axis coordinates of the same group of inner coordinates.
In addition, when the price tag frame is detected as the reflective strip by mistake, price tag detection is carried out while shelf guide rail detection is carried out, and coordinates subjected to duplication removal by the reflective strip (plug) and price tag coordinates are filtered, wherein the filtering method is to judge whether an intersection area exists through the coordinates, and if so, the price tag edge false detection is judged.
In this embodiment, the super commodity shelf map is obtained through the AI camera or the AI inspection robot, the commodity shelf guide rail area in the commodity shelf picture is detected through the commodity shelf guide rail algorithm, the detected commodity shelf guide rail area is expanded, then the expanded commodity shelf guide rail area is detected by the reflective strip (plug), and the coordinates are returned to the AI camera or the AI inspection robot to obtain the super commodity shelf map. And finally, fitting a small goods shelf dividing line after de-duplication and grouping of the coordinates of the reflective strips (plugs), and finally completing the division of the small goods shelf.
According to the embodiment of the invention, the detection is carried out on the shelf guide rail first, then the detection is carried out on the reflective strip (plug) in the shelf guide rail, the precision problem caused by ultra-small target detection is avoided, the division line is divided by detecting the coordinate of the reflective strip attached to the plug, and the small shelf division can be accurately carried out even under the weak lighting condition at night depending on the reflective attribute of the reflective strip. Compared with the scheme of placing the segmentation marks which are obviously easy to detect, the embodiment of the invention only pastes the reflective strips with the colors similar to those of the guide rails on the plugs of the guide rails of the goods shelf, hardly influences the super-attractive degree of the goods shelf, and simultaneously avoids the management of the additional segmentation marks by staff.
As shown in fig. 2, a device for dividing shelf images according to an embodiment of the present application is applied to a shelf having a plurality of rails, and an edge of each rail is provided with a plug for preventing a price tag on the rail from sliding out of the rail, the device includes:
The acquiring module 210 is configured to acquire a shelf image, and detect a plurality of shelf rail areas from the shelf image.
And the detection module 220 is configured to detect plug areas based on each of the shelf rail areas, respectively, to obtain coordinates of a plurality of plug areas on the shelf image.
Wherein, each plug is provided with a reflecting element;
Correspondingly, the detection module 220 is specifically configured to detect the reflective elements based on each of the shelf rail areas, and respectively use the coordinates of the detected reflective elements on the shelf image as the coordinates of the plug areas on the shelf image.
The segmentation module 230 is configured to fit a segmentation line according to coordinates of the plurality of plug regions, and segment the shelf image based on the segmentation line.
The segmentation module 230 specifically includes:
and the grouping sub-module is used for grouping the plurality of plug areas according to the coordinates of the plurality of plug areas.
The grouping submodule is specifically configured to obtain a difference value between x-axis coordinates of each plug region, and if the difference value between the x-axis coordinates of two plug regions is less than or equal to a preset multiple of a width of one plug region, determine the two plug regions as plug regions in the same grouping.
And the fitting sub-module is used for respectively fitting out the dividing lines based on the coordinates of the plug areas in each group.
The fitting sub-module is specifically used for calculating the average value of the x-axis coordinates of the plug areas in the same group, and determining the position of the dividing line according to the average value.
And the segmentation submodule is used for segmenting the shelf image based on the segmentation line.
In this embodiment, the apparatus further includes:
And the expansion module is used for expanding each shelf guide rail area respectively.
Correspondingly, the detection module 220 is specifically configured to detect plug regions in each extended shelf rail region respectively, so as to obtain coordinates of a plurality of plug regions on the shelf image.
In this embodiment, the apparatus further includes:
And the de-duplication module is used for judging whether two plug areas with an intersecting area exist or not according to the coordinates of the plug areas on the shelf image, and de-duplication is carried out on one plug area in the two plug areas if the two plug areas exist.
In this embodiment, the guide rail may be provided with a plurality of price tags, and correspondingly, the device further includes:
the judging module is used for judging whether each plug region has an intersecting region with at least one price tag region in the price tag regions according to the coordinates of the plug regions on the shelf image and the coordinates of the price tag regions on the shelf image, and if the intersecting region exists between the at least one plug region in the plug regions and the at least one price tag region in the price tag regions, determining that the at least one plug region is a false detection region.
According to the embodiment of the application, the plug areas are detected in the shelf guide rail areas, the dividing lines are fitted according to the detected coordinates of the plug areas, and the shelf image is divided based on the dividing lines, so that small target detection can be avoided, and the division of the shelf image is accurately realized.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements each process of the above-mentioned method embodiment for dividing a shelf image, and can achieve the same technical effect, so that repetition is avoided, and no further description is provided herein. Wherein, the computer readable storage medium is Read-only memory (ROM), random Access Memory (RAM), magnetic disk or optical disk, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
Claims (13)
1. A method of segmenting a shelf image for use with a shelf having a plurality of rails, each rail having an edge provided with a plug for preventing a price tag on the rail from sliding off the rail, the method comprising the steps of:
Acquiring a shelf image, and detecting a plurality of shelf guide rail areas from the shelf image;
Detecting plug areas based on each goods shelf guide rail area respectively to obtain coordinates of a plurality of plug areas on the goods shelf image;
fitting a dividing line according to the coordinates of the plug areas, and dividing the shelf image based on the dividing line;
The method comprises the steps of detecting plug areas based on each shelf guide rail area respectively, obtaining coordinates of the plug areas on a shelf image, and further comprises the following steps:
judging whether each plug region has an intersecting region with at least one price tag region in the plurality of price tag regions according to the coordinates of the plurality of plug regions on the shelf image and the coordinates of the plurality of price tag regions on the shelf image;
And if at least one plug region in the plurality of plug regions and at least one price tag region in the plurality of price tag regions have an intersection region, determining the at least one plug region as a false detection region.
2. The method of claim 1, wherein after detecting a plurality of shelf rail regions from the shelf image, further comprising:
expanding each shelf guide rail area respectively;
the detection of the plug areas based on each shelf guide rail area comprises the following steps:
and detecting plug areas in each extended shelf guide rail area respectively.
3. The method according to claim 1, wherein the fitting a dividing line according to the coordinates of the plurality of plug regions, and dividing the shelf image based on the dividing line, specifically comprises:
grouping the plurality of plug regions according to the coordinates of the plurality of plug regions;
And fitting a dividing line based on the coordinates of the plug areas in each group, and dividing the shelf image based on the dividing line.
4. The method of claim 3, wherein the grouping the plurality of plug regions according to the coordinates of the plurality of plug regions specifically comprises:
Acquiring a difference value between x-axis coordinates of each plug region, and determining the two plug regions as plug regions in the same group if the difference value between the x-axis coordinates of the two plug regions is smaller than or equal to a preset multiple of the width of one plug region;
The method for fitting the parting line based on the coordinates of the plug areas in each group comprises the following steps:
And calculating the average value of the x-axis coordinates of the plug areas in the same group, and determining the position of the dividing line according to the average value.
5. The method of claim 2, wherein after detecting plug regions based on each of the shelf rail regions, respectively, and obtaining coordinates of a plurality of plug regions on the shelf image, further comprises:
Judging whether two plug areas with intersecting areas exist or not according to the coordinates of the plug areas on the shelf image;
and if the two plug regions exist, carrying out de-duplication on one plug region of the two plug regions.
6. The method of claim 1, wherein the step of determining the position of the substrate comprises,
Detecting plug areas based on each goods shelf guide rail area respectively to obtain coordinates of a plurality of plug areas on the goods shelf image, wherein the method specifically comprises the following steps:
And detecting reflecting elements based on each shelf guide rail area respectively, and taking the coordinates of the detected reflecting elements on the shelf image as the coordinates of the plug areas on the shelf image respectively.
7. An apparatus for dividing a shelf image, for use with a shelf having a plurality of rails, each rail having an edge provided with a plug for preventing a price tag on the rail from sliding off the rail, the apparatus comprising:
The acquisition module is used for acquiring a shelf image and detecting a plurality of shelf guide rail areas from the shelf image;
the detection module is used for respectively detecting plug areas based on each shelf guide rail area to obtain coordinates of a plurality of plug areas on the shelf image;
The dividing module is used for fitting dividing lines according to the coordinates of the plug areas and dividing the shelf image based on the dividing lines;
each plug is provided with a reflecting element, and the guide rail is provided with a plurality of price tags;
The apparatus further comprises:
the judging module is used for judging whether each plug region has an intersecting region with at least one price tag region in the price tag regions according to the coordinates of the plug regions on the shelf image and the coordinates of the price tag regions on the shelf image, and if the intersecting region exists between the at least one plug region in the plug regions and the at least one price tag region in the price tag regions, determining that the at least one plug region is a false detection region.
8. The apparatus as recited in claim 7, further comprising:
The expansion module is used for expanding each shelf guide rail area respectively;
The detection module is specifically configured to detect plug regions in each extended shelf guide rail region respectively, so as to obtain coordinates of a plurality of plug regions on the shelf image.
9. The apparatus of claim 7, wherein the device comprises a plurality of sensors,
The segmentation module specifically comprises:
the grouping sub-module is used for grouping the plurality of plug areas according to the coordinates of the plurality of plug areas;
The fitting sub-module is used for respectively fitting out a parting line based on the coordinates of a plurality of plug areas in each group;
and the segmentation submodule is used for segmenting the shelf image based on the segmentation line.
10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
The grouping submodule is specifically configured to obtain a difference value between x-axis coordinates of each plug region, and if the difference value between the x-axis coordinates of two plug regions is less than or equal to a preset multiple of the width of one plug region, determine the two plug regions as plug regions in the same grouping;
The fitting sub-module is specifically configured to calculate an average value of x-axis coordinates of plug regions in the same group, and determine a position of a dividing line according to the average value.
11. The apparatus as recited in claim 8, further comprising:
And the de-duplication module is used for judging whether two plug areas with an intersecting area exist or not according to the coordinates of the plug areas on the shelf image, and de-duplication is carried out on one plug area in the two plug areas if the two plug areas exist.
12. The apparatus of claim 7, wherein the device comprises a plurality of sensors,
The detection module is specifically configured to detect the reflective elements based on each shelf guide rail region, and respectively use coordinates of the detected reflective elements on the shelf image as coordinates of the plug regions on the shelf image.
13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the steps of the method of segmenting shelf images according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310622179.3A CN116596953B (en) | 2023-05-30 | 2023-05-30 | A method and apparatus for segmenting shelf images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310622179.3A CN116596953B (en) | 2023-05-30 | 2023-05-30 | A method and apparatus for segmenting shelf images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596953A CN116596953A (en) | 2023-08-15 |
| CN116596953B true CN116596953B (en) | 2025-12-30 |
Family
ID=87606064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310622179.3A Active CN116596953B (en) | 2023-05-30 | 2023-05-30 | A method and apparatus for segmenting shelf images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596953B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107328479A (en) * | 2017-07-10 | 2017-11-07 | 国网黑龙江省电力有限公司电力科学研究院 | One kind is used for power equipment infrared photography photo array method and witness marker thing |
| CN113705416A (en) * | 2021-08-23 | 2021-11-26 | 上海汉时信息科技有限公司 | Shelf identification method and device, storage medium and robot |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101446063B1 (en) * | 2014-04-24 | 2014-10-01 | 한국건설기술연구원 | Variable information Sign |
| WO2018204308A1 (en) * | 2017-05-01 | 2018-11-08 | Symbol Technologies, Llc | Method and apparatus for object status detection |
| CN108549870B (en) * | 2018-04-16 | 2022-06-10 | 图麟信息科技（深圳）有限公司 | A kind of method and device for identifying the display of articles |
| CN209515155U (en) * | 2019-01-07 | 2019-10-18 | 北京无线体育俱乐部有限公司 | Merchandise news display structure |
| DE112019007564T5 (en) * | 2019-07-25 | 2022-04-28 | Hanshow Technology Co., Ltd | SHELF EDGE POSITIONING METHOD AND APPARATUS |
| CN212208337U (en) * | 2020-02-13 | 2020-12-22 | 阿里巴巴集团控股有限公司 | Positioning circuit board, guide rail for installing electronic price tag and electronic price tag |
| JP7543035B2 (en) * | 2020-08-31 | 2024-09-02 | 株式会社Retail AI | Information processing device, information processing system, information processing program, and information processing method |
| CN112883955B (en) * | 2021-03-10 | 2024-02-02 | 洛伦兹（北京）科技有限公司 | Shelf layout detection method, device and computer readable storage medium |
| CN114821447A (en) * | 2022-05-18 | 2022-07-29 | 烟台创迹软件有限公司 | Theft monitoring and tracking method and system for physical retail scene |
| CN115392272A (en) * | 2022-07-21 | 2022-11-25 | 盒马(中国)有限公司 | Position identification method and system |
-
2023
- 2023-05-30 CN CN202310622179.3A patent/CN116596953B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107328479A (en) * | 2017-07-10 | 2017-11-07 | 国网黑龙江省电力有限公司电力科学研究院 | One kind is used for power equipment infrared photography photo array method and witness marker thing |
| CN113705416A (en) * | 2021-08-23 | 2021-11-26 | 上海汉时信息科技有限公司 | Shelf identification method and device, storage medium and robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596953A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12536769B2 (en) | System and method for matching products and determining spreads and plugs | |
| CN113191329B (en) | Vehicle berth matching method and system based on monocular vision picture | |
| CN112861656B (en) | Trademark similarity detection method and device, electronic equipment and storage medium | |
| CN111695486A (en) | High-precision direction signboard target extraction method based on point cloud | |
| US10262432B1 (en) | System and method for measuring and comparing items using computer vision | |
| CN109977782A (en) | Across shop operation detection method based on target position information reasoning | |
| CN111553302B (en) | Key frame selection method, apparatus, device, and computer-readable storage medium | |
| CN108345912A (en) | Commodity rapid settlement system based on RGBD information and deep learning | |
| CN107218927A (en) | A kind of cargo pallet detecting system and method based on TOF camera | |
| CN111126393A (en) | Vehicle appearance refitting judgment method and device, computer equipment and storage medium | |
| CN110288612A (en) | Nameplate positioning and bearing calibration and equipment | |
| CN113505763B (en) | Key point detection method and device, electronic equipment and storage medium | |
| Zhai et al. | Crosswalk detection based on MSER and ERANSAC | |
| CN113643420A (en) | Three-dimensional reconstruction method and device | |
| CN110543839B (en) | Commodity shop goods rate acquisition method based on computer vision | |
| US9846949B2 (en) | Determine the shape of a representation of an object | |
| CN116596953B (en) | A method and apparatus for segmenting shelf images | |
| CN115601672A (en) | VR intelligent shop patrol method and device based on deep learning | |
| CN119741309A (en) | Point cloud annotation method, device, equipment, storage medium and vehicle | |
| Zhang et al. | Urban vehicle extraction from aerial laser scanning point cloud data | |
| CN119478843B (en) | Commodity shortage detection method, device and system | |
| CN115953635B (en) | Sorting method, AR (augmented reality) glasses and system for multi-class targets | |
| CN119850537B (en) | MSSA-YOLOv light-weight model-based film defect detection method and apparatus | |
| CN112712538A (en) | Display screen positioning method, electronic equipment and storage medium | |
| CN113506329A (en) | A real-time displacement measurement method based on monocular camera |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |