CN110852240A - Retail commodity detection system and detection method - Google Patents
Retail commodity detection system and detection method Download PDFInfo
- Publication number
- CN110852240A CN110852240A CN201911076394.8A CN201911076394A CN110852240A CN 110852240 A CN110852240 A CN 110852240A CN 201911076394 A CN201911076394 A CN 201911076394A CN 110852240 A CN110852240 A CN 110852240A
- Authority
- CN
- China
- Prior art keywords
- image
- foreground
- detected
- detection
- module
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 121
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 230000010339 dilation Effects 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a retail commodity detection system, which comprises: the image acquisition module is used for acquiring an image to be detected shot aiming at the retail commodity; the foreground extraction module is connected with the image acquisition module and used for extracting and storing a foreground mask of the image to be detected; the image fusion module is respectively connected with the image acquisition module and the foreground extraction module and is used for carrying out image fusion on the originally input image to be detected and the foreground mask so as to extract the image to be detected which only contains the foreground from the original image to be detected; the image detection module is connected with the image fusion module and used for carrying out image detection on the image to be detected only containing the foreground, and finally obtaining and storing a detection result of the retail commodity in the selling state.
Description
Technical Field
The invention relates to the technical field of retail commodity detection, in particular to a retail commodity detection system and a detection method.
Background
In the field of commodity retail, channel display area scenes are more and more complicated due to factors such as channel sinking and the like. In such a complex scene, the problems of disordered goods placement, discontinuous display area, large illumination change, too large display background area of the goods and the like often exist, and the problems directly influence the shooting of the retail goods image by the retail goods detection system.
Currently, a method for detecting the on-sale state of a retail product generally determines the on-sale state of the retail product by identifying the position of the retail product in a display area image and identifying whether the retail product is present in the identified area position. However, the display area image acquired by the conventional retail commodity detection system is a complete image containing a foreground and a background, and for the display area image shot in a complex scene, the system may identify an irrelevant object in the background as a retail commodity, which directly affects the identification accuracy of the system on the selling state of the retail commodity.
Disclosure of Invention
The invention aims to provide a retail commodity detection system to solve the technical problem.
In order to achieve the purpose, the invention adopts the following technical scheme:
there is provided a retail goods detection system for detecting a selling state of retail goods, comprising:
the image acquisition module is used for acquiring an image to be detected shot aiming at the retail commodity;
the foreground extraction module is connected with the image acquisition module and used for extracting and storing a foreground mask of the image to be detected;
the image fusion module is respectively connected with the image acquisition module and the foreground extraction module and is used for carrying out image fusion on the originally input image to be detected and the foreground mask so as to extract the image to be detected which only contains the foreground from the original image to be detected;
and the image detection module is connected with the image fusion module and used for carrying out image detection on the image to be detected only containing the foreground, and finally obtaining and storing the detection result of the retail commodity in the selling state.
As a preferred scheme of the invention, the foreground extraction module extracts the foreground mask of the image to be detected by applying one of an image feature extraction network among a significant target detection network, an example segmentation network and a semantic segmentation network in a convolutional neural network.
As a preferable aspect of the present invention, the retail product detection system further includes:
and the image processing module is respectively connected with the foreground extraction module and the image feature extraction module and is used for carrying out image morphological processing on the original foreground mask extracted by the foreground extraction module to finally obtain the foreground mask after image processing.
As a preferred embodiment of the present invention, the image morphology processing performed on the original foreground mask includes image erosion processing, and/or image dilation processing, and/or image filtering processing on the original foreground mask.
As a preferred embodiment of the present invention, the image detection module implements image detection on the image to be detected by applying any one of a network architecture of YOLO, SSD, fast RCNN, Mask RCNN, and FPN in a convolutional neural network.
As a preferable aspect of the present invention, the retail product detection system further includes:
the first recognition model training module is respectively connected with the foreground extraction module and the image processing module and is used for training to form a foreground mask extraction model by taking the foreground mask which is processed by the image processing module and is related to the image to be detected as a training sample;
and the foreground extraction module extracts the foreground mask from the input image to be detected through the foreground mask extraction model.
As a preferable aspect of the present invention, the retail product detection system further includes:
the second recognition model training module is connected with the image detection module and used for training to form an image detection model by taking the detection result of the image detection module as a training sample;
and the image detection module carries out image detection on the image to be detected only containing the foreground through the image detection model, and finally obtains the detection result of the retail commodity in the selling state.
The invention also provides a retail commodity detection method, which is realized by applying the retail commodity detection system and specifically comprises the following steps:
step S1, the retail commodity detection system collects the images to be detected shot aiming at the retail commodity;
step S2, the retail merchandise detection system extracting the foreground mask associated with the image to be detected;
step S3, the retail goods detection system carries out image fusion on the image to be detected and the foreground mask which are input originally, so as to extract the image to be detected which only contains foreground from the original image to be detected;
and step S4, the retail commodity detection system carries out image detection on the image to be detected, which only contains the foreground, and finally obtains a detection result.
As a preferred embodiment of the present invention, the step S2 further includes a foreground mask image processing process, where the foreground mask image processing process specifically includes:
and the retail commodity detection system performs image morphological processing on the extracted original foreground mask to finally obtain the foreground mask after image processing.
As a preferred aspect of the present invention, the image morphology processing includes image erosion processing, and/or image dilation processing, and/or image filtering processing on the original foreground mask.
The retail commodity detection system provided by the invention firstly extracts the foreground mask from the originally input image to be detected, then extracts the image to be detected only containing the foreground from the originally input image to be detected according to the extracted foreground mask, and finally, carries out the subsequent retail commodity detection flow on the image to be detected only containing the foreground, so that the accuracy and the detection efficiency of detecting the selling state of the retail commodity can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram of a retail product detection system according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a retail product detection system provided in the second embodiment of the present invention;
fig. 3 is a method step diagram for implementing detection of the selling status of the retail goods by applying the retail goods detection system provided in the first embodiment or the second embodiment.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
Wherein the showings are for the purpose of illustration only and are shown by way of illustration only and not in actual form, and are not to be construed as limiting the present patent; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "inner", "outer", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not indicated or implied that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and the specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the description of the present invention, unless otherwise explicitly specified or limited, the term "connected" or the like, if appearing to indicate a connection relationship between the components, is to be understood broadly, for example, as being fixed or detachable or integral; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or may be connected through one or more other components or may be in an interactive relationship with one another. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example one
In an embodiment, a retail product detection system is provided for detecting a selling status of a retail product, referring to fig. 1, the retail product detection system includes:
the image acquisition module 1 is used for acquiring an image to be detected shot aiming at retail commodities;
the foreground extraction module 2 is connected with the image acquisition module 1 and is used for extracting a foreground mask (mask) of the image to be detected;
the image fusion module 3 is respectively connected with the image acquisition module 1 and the foreground extraction module 2 and is used for carrying out image fusion on the original input image to be detected and the foreground mask so as to extract the image to be detected which only contains the foreground from the original image to be detected;
and the image detection module 4 is connected with the image fusion module 3 and is used for carrying out image detection on the image to be detected only containing the foreground to finally obtain a detection result.
In the above technical solution, the foreground extraction module 2 extracts the foreground mask of the image to be detected by applying one of an image feature extraction network in a significant target detection network, an instance segmentation network or a semantic segmentation network in a convolutional neural network.
The salient object detection network, the example segmentation network and the semantic segmentation network are all image feature extraction networks in the prior art, and the three image feature extraction networks are used for extracting the foreground mask of the image to be detected, which is an existing technical means, so that the specific extraction process of the foreground mask is not explained here.
In order to obtain a foreground mask with higher image quality, preferably, before the retail commodity detection system performs image detection on an image to be detected, the retail commodity detection system needs to perform image morphological processing on the original foreground mask extracted by the foreground extraction module 2, and finally obtains the foreground mask after the image processing.
With continued reference to fig. 1, preferably, the retail merchandise detection system further comprises:
and the image processing module 5 is respectively connected with the foreground extraction module 2 and the image fusion module 3, and is used for performing image morphological processing on the original foreground mask extracted by the foreground extraction module 2 and finally obtaining the foreground mask after the image processing.
It should be noted here that the image morphology processing performed on the original foreground mask includes, but is not limited to, image erosion processing, image dilation processing, and image filtering processing on the original foreground mask.
In addition, the image detection module 4 in the retail product detection system implements image detection of an image to be detected by applying any one of network architectures of YOLO, SSD, fast RCNN, Mask RCNN, and FPN in the convolutional neural network.
The method for detecting the on-sale state of the retail commodity by the retail commodity detection system based on the image to be detected only containing the foreground and based on the convolutional neural network is an existing detection method, and the detection method is not the scope of the claimed invention, so the method is not explained herein.
Example two
The difference between the second embodiment and the first embodiment is that, referring to fig. 2, the retail product detection system provided in the second embodiment further includes:
the first recognition model training module 6 is respectively connected with the foreground extraction module 2 and the image processing module 5, and is used for training to form a foreground mask extraction model by taking a foreground mask which is processed by the image processing module 5 and is related to the image to be detected as a training sample;
the foreground extraction module 2 extracts a foreground mask from the input image to be detected through a foreground mask extraction model.
In addition, the retail product detection system provided by the second embodiment further includes:
the second recognition model training module 7 is connected with the image detection module 4 and is used for training to form an image detection model by taking the detection result of the image detection module 4 as a training sample;
the image detection module 4 performs image detection on the image to be detected, which only contains the foreground, through the image detection model, and finally obtains the detection result of the retail commodity in the selling state.
The invention further provides a retail commodity detection method, which is realized by applying the retail commodity detection system provided by the first embodiment or the second embodiment, and referring to fig. 3, the retail commodity detection method specifically comprises the following steps:
step S1, the retail commodity detection system collects the images to be detected shot aiming at the retail commodity;
step S2, the retail goods detection system extracts the foreground mask associated with the image to be detected;
step S3, the retail goods detection system carries out image fusion on the original input image to be detected and the foreground mask corresponding to the image to be detected so as to extract the image to be detected which only contains foreground from the original image to be detected;
and step S4, the retail commodity detection system carries out image detection on the image to be detected, which only contains the foreground, and finally obtains the detection result of the selling state of the retail commodity.
In order to improve the image quality of the foreground mask, step S2 preferably further includes a foreground mask image processing process, where the foreground mask image processing process specifically includes:
and the retail commodity detection system performs image morphological processing on the extracted original foreground mask to finally obtain the foreground mask after image processing.
Image morphological processing includes, but is not limited to, image erosion processing, image dilation processing, and image filtering processing of the original foreground mask.
In addition, in step S2, the retail product detection system performs an and operation on the original image to be detected and the foreground mask to obtain the image to be detected that only includes the foreground.
The method of and-operating the original image to be detected and the foreground mask is the existing method, and the specific calculation process is not described here.
In summary, the retail commodity detection system provided by the invention firstly extracts the foreground mask from the originally input image to be detected, then extracts the image to be detected only containing the foreground from the originally input image to be detected according to the extracted foreground mask, and finally, by performing the subsequent retail commodity detection process on the image to be detected only containing the foreground, the accuracy and the detection efficiency of detecting the selling state of the retail commodity can be greatly improved.
It should be understood that the above-described embodiments are merely preferred embodiments of the invention and the technical principles applied thereto. It will be understood by those skilled in the art that various modifications, equivalents, changes, and the like can be made to the present invention. However, such variations are within the scope of the invention as long as they do not depart from the spirit of the invention. In addition, certain terms used in the specification and claims of the present application are not limiting, but are used merely for convenience of description.
Claims (10)
1. A retail merchandise detection system for detecting a status of retail merchandise, comprising:
the image acquisition module is used for acquiring an image to be detected shot aiming at the retail commodity;
the foreground extraction module is connected with the image acquisition module and used for extracting and storing a foreground mask of the image to be detected;
the image fusion module is respectively connected with the image acquisition module and the foreground extraction module and is used for carrying out image fusion on the originally input image to be detected and the foreground mask so as to extract the image to be detected which only contains the foreground from the original image to be detected;
and the image detection module is connected with the image fusion module and used for carrying out image detection on the image to be detected only containing the foreground, and finally obtaining and storing the detection result of the retail commodity in the selling state.
2. A retail merchandise detection system according to claim 1, wherein the foreground extraction module extracts foreground masks of the image to be detected by applying an image feature extraction network of one of a salient object detection network, an instance segmentation network and a semantic segmentation network in a convolutional neural network.
3. A retail merchandise detection system according to claim 1, further comprising:
and the image processing module is respectively connected with the foreground extraction module and the image fusion module and is used for carrying out image morphological processing on the original foreground mask extracted by the foreground extraction module to finally obtain the foreground mask after image processing.
4. A retail merchandise detection system according to claim 3, characterised in that the image morphological processing of the original foreground mask comprises an image erosion processing, and/or an image dilation processing, and/or an image filtering processing of the original foreground mask.
5. The retail product detection system of claim 1, wherein the image detection module implements image detection of the image to be detected by applying any one of a network architecture of YOLO, SSD, fast RCNN, Mask RCNN, and FPN in a convolutional neural network.
6. A retail merchandise detection system according to claim 3, further comprising:
the first recognition model training module is respectively connected with the foreground extraction module and the image processing module and is used for training to form a foreground mask extraction model by taking the foreground mask which is processed by the image processing module and is related to the image to be detected as a training sample;
and the foreground extraction module extracts the foreground mask from the input image to be detected through the foreground mask extraction model.
7. A retail merchandise detection system according to claim 1, further comprising:
the second recognition model training module is connected with the image detection module and used for training to form an image detection model by taking the detection result of the image detection module as a training sample;
and the image detection module carries out image detection on the image to be detected only containing the foreground through the image detection model, and finally obtains the detection result of the retail commodity in the selling state.
8. A retail commodity detection method implemented by applying the retail commodity detection system according to any one of claims 1 to 7, comprising the steps of:
step S1, the retail commodity detection system collects the images to be detected shot aiming at the retail commodity;
step S2, the retail merchandise detection system extracting the foreground mask associated with the image to be detected;
step S3, the retail goods detection system carries out image fusion on the image to be detected and the foreground mask which are input originally, so as to extract the image to be detected which only contains foreground from the original image to be detected;
step S4, the retail commodity detection system carries out image detection on the image to be detected, which only contains foreground, and finally obtains the detection result of the retail commodity in the selling state.
9. The retail product detection method according to claim 8, wherein the step S2 further includes a foreground mask image processing process, and the foreground mask image processing process specifically includes:
and the retail commodity detection system performs image morphological processing on the extracted original foreground mask to finally obtain the foreground mask after image processing.
10. A retail merchandise detection method according to claim 9, characterised in that the image morphological processing comprises image erosion processing, and/or image dilation processing, and/or image filtering processing of the original foreground mask.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911076394.8A CN110852240A (en) | 2019-11-06 | 2019-11-06 | Retail commodity detection system and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911076394.8A CN110852240A (en) | 2019-11-06 | 2019-11-06 | Retail commodity detection system and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110852240A true CN110852240A (en) | 2020-02-28 |
Family
ID=69599950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911076394.8A Pending CN110852240A (en) | 2019-11-06 | 2019-11-06 | Retail commodity detection system and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852240A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570510A (en) * | 2016-11-07 | 2017-04-19 | 南京航空航天大学 | Supermarket commodity identification method |
| CN108197623A (en) * | 2018-01-19 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For detecting the method and apparatus of target |
| CN108509879A (en) * | 2018-03-19 | 2018-09-07 | 北京学之途网络科技有限公司 | A kind of method and device for realizing information processing |
| CN108846401A (en) * | 2018-05-30 | 2018-11-20 | 京东方科技集团股份有限公司 | Commodity detect terminal, method, system and computer equipment, readable medium |
| CN109446883A (en) * | 2018-09-05 | 2019-03-08 | 北京三快在线科技有限公司 | Condition of merchandise recognition methods, device, electronic equipment and readable storage medium storing program for executing |
| US10304193B1 (en) * | 2018-08-17 | 2019-05-28 | 12 Sigma Technologies | Image segmentation and object detection using fully convolutional neural network |
| CN109902549A (en) * | 2017-12-08 | 2019-06-18 | 富士电机株式会社 | Commodity detection device |
-
2019
- 2019-11-06 CN CN201911076394.8A patent/CN110852240A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570510A (en) * | 2016-11-07 | 2017-04-19 | 南京航空航天大学 | Supermarket commodity identification method |
| CN109902549A (en) * | 2017-12-08 | 2019-06-18 | 富士电机株式会社 | Commodity detection device |
| CN108197623A (en) * | 2018-01-19 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For detecting the method and apparatus of target |
| CN108509879A (en) * | 2018-03-19 | 2018-09-07 | 北京学之途网络科技有限公司 | A kind of method and device for realizing information processing |
| CN108846401A (en) * | 2018-05-30 | 2018-11-20 | 京东方科技集团股份有限公司 | Commodity detect terminal, method, system and computer equipment, readable medium |
| US10304193B1 (en) * | 2018-08-17 | 2019-05-28 | 12 Sigma Technologies | Image segmentation and object detection using fully convolutional neural network |
| CN109446883A (en) * | 2018-09-05 | 2019-03-08 | 北京三快在线科技有限公司 | Condition of merchandise recognition methods, device, electronic equipment and readable storage medium storing program for executing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3910608B1 (en) | Article identification method and system, and electronic device | |
| US10726562B2 (en) | Video tracking method and device, and object recognition method and device | |
| US20210065381A1 (en) | Target tracking method, device, system and non-transitory computer readable medium | |
| US10592726B2 (en) | Manufacturing part identification using computer vision and machine learning | |
| US10452707B2 (en) | Product auditing in point-of-sale images | |
| CN111260666B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| US10824832B2 (en) | Barcode tag detection in side view sample tube images for laboratory automation | |
| WO2016034059A1 (en) | Target object tracking method based on color-structure features | |
| CN111797653A (en) | Image annotation method and device based on high-dimensional image | |
| WO2014151035A1 (en) | Computer-based method and system of dynamic category object recognition | |
| CN109344864B (en) | Image processing method and device for dense object | |
| CN108229344A (en) | Image processing method and device, electronic equipment, computer program and storage medium | |
| CN107016344A (en) | Brand identity system and its implementation in video | |
| WO2014193220A2 (en) | System and method for multiple license plates identification | |
| CN111666792B (en) | Image recognition method, image acquisition and recognition method, and commodity recognition method | |
| CN113449639B (en) | Non-contact data acquisition method of gateway of Internet of things for instrument | |
| CN109977875A (en) | Gesture identification method and equipment based on deep learning | |
| CN109086725B (en) | Hand tracking method and machine-readable storage medium | |
| Specker et al. | Improving multi-target multi-camera tracking by track refinement and completion | |
| CN113723157A (en) | Crop disease identification method and device, electronic equipment and storage medium | |
| CN104794446A (en) | Human body action recognition method and system based on synthetic descriptors | |
| CN112949451A (en) | Cross-modal target tracking method and system through modal perception feature learning | |
| CN114419493A (en) | Image annotation method and device, electronic equipment and storage medium | |
| CN107203638A (en) | Monitor video processing method, apparatus and system | |
| KR20160000533A (en) | The method of multi detection and tracking with local feature point for providing information of an object in augmented reality |
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: 20200228 |
|
| RJ01 | Rejection of invention patent application after publication |