WO2021229754A1 - 商品特定装置、商品特定方法、及びプログラム - Google Patents

商品特定装置、商品特定方法、及びプログラム Download PDF

Info

Publication number
WO2021229754A1
WO2021229754A1 PCT/JP2020/019259 JP2020019259W WO2021229754A1 WO 2021229754 A1 WO2021229754 A1 WO 2021229754A1 JP 2020019259 W JP2020019259 W JP 2020019259W WO 2021229754 A1 WO2021229754 A1 WO 2021229754A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
images
image
display area
sample
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.)
Ceased
Application number
PCT/JP2020/019259
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
八栄子 米澤
克 菊池
壮馬 白石
悠 鍋藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to PCT/JP2020/019259 priority Critical patent/WO2021229754A1/ja
Priority to JP2022522438A priority patent/JP7400962B2/ja
Publication of WO2021229754A1 publication Critical patent/WO2021229754A1/ja
Priority to US17/923,288 priority patent/US20230368535A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • 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
    • G06T2207/10141—Special mode during image acquisition
    • G06T2207/10144—Varying exposure

Definitions

  • the present invention relates to a product identification device, a product identification method, and a program.
  • Patent Document 1 describes that by processing an image obtained by capturing an image of a product shelf, a product area image included in the image is specified, and a product is specified for each product area image.
  • Patent Document 1 describes that a plurality of images are generated by imaging a product shelf at different angles a plurality of times, and the product identification information is specified by using the plurality of images.
  • a light source is placed near the product display area where products and product samples are displayed, such as product shelves and vending machines.
  • a cover member made of translucent light is arranged in front of the product display area, and the cover member may reflect external light. Therefore, depending on the conditions at the time of imaging, a part of the image may be overexposed, or conversely, the exposure may be insufficient and the image may be unclear. If the image looks like this, the accuracy of the image analysis will decrease.
  • An example of the object of the present invention is to ensure that the accuracy of image analysis does not decrease when the product and / or the product sample is specified by analyzing the image obtained by capturing the image of the product display area where the product and / or the product sample is displayed. To be.
  • the present invention there are a plurality of images obtained by capturing a product display area in which a product and / or a product sample are arranged, and a plurality of images in which the parameters of the imaging means at the time of imaging are different from each other.
  • a product identification device comprising the above is provided.
  • the present invention it is a result of processing a plurality of images obtained by capturing an image of a product and / or a product display area in which a product sample is lined up, and the feature points of the product or the product sample and the positions of the feature points are determined by the plurality of images.
  • An acquisition method for acquiring analysis data shown for each image A data processing means for identifying the product or the product sample located in the product display area by processing the analysis data and outputting the specific result. Equipped with For the plurality of images, a product specifying device having different parameters of the imaging means at the time of imaging is provided.
  • the computer A plurality of images obtained by capturing a product display area in which a product and / or a product sample are lined up and having different parameters of the imaging means at the time of imaging are acquired.
  • a product identification method for identifying the product or the product sample located in the product display area and outputting the specific result is provided.
  • the computer Analysis data showing the feature points of the product or the product sample and the positions of the feature points for each of the plurality of images, which is the result of processing a plurality of images of the product display area in which the product and / or the product sample are lined up.
  • the analysis data By processing the analysis data, the product or the product sample located in the product display area is specified, and the specific result is output.
  • the plurality of images are provided with a product identification method in which the parameters of the imaging means at the time of imaging are different from each other.
  • the computer An acquisition function for acquiring a plurality of images in which a product and / or a product display area in which product samples are lined up, and the parameters of the imaging means at the time of imaging are different from each other.
  • An image processing function that identifies the product or the product sample located in the product display area by processing the plurality of images and outputs the specific result. Is provided.
  • the computer Analysis data showing the feature points of the product or the product sample and the positions of the feature points for each of the plurality of images, which is the result of processing a plurality of images of the product display area in which the product and / or the product sample are lined up.
  • the acquisition function to acquire and A data processing function that identifies the product or the product sample located in the product display area by processing the analysis data and outputs the specific result.
  • the plurality of images are provided with programs in which the parameters of the imaging means at the time of imaging are different from each other.
  • the present invention it is possible to suppress a decrease in the accuracy of image analysis when the product and / or the product sample is specified by analyzing the image obtained by capturing the image of the product display area in which the product and / or the product sample is displayed.
  • FIG. 1 is a diagram for explaining a usage environment of the product specifying device 20 according to the present embodiment.
  • the product identification device 20 is used together with the image pickup device 10.
  • the image pickup device 10 takes an image of the product mounting area.
  • the product placement area may be a product shelf 40 installed in a store, or may be an area where products and / or product samples are displayed in a vending machine.
  • the image generated by the image pickup device 10 is transmitted to the product identification device 20.
  • the product identification device 20 identifies the positions of the product 50 and / or the product sample in the product display area by processing the image generated by the image pickup device 10.
  • the person who uses the product specifying device 20 confirms whether or not the positions of the product 50 and / or the product sample are in the desired positions by using the processing result of the product specifying device 20.
  • the image pickup device 10 is a portable device.
  • the image pickup device 10 may be a communication device having an image pickup function, such as a so-called smartphone.
  • the user of the image pickup device 10 captures the product shelf 40 to generate an image, and transmits this image to an external device, for example, the product identification device 20.
  • the product specifying device 20 identifies the positions of the product 50 and / or the product sample by processing the image generated by the image pickup device 10.
  • a light source is placed near the product shelf 40.
  • a translucent cover member is arranged in front of the product display area where the product and / or the product sample is arranged, and the cover member may reflect external light. be. Therefore, depending on the conditions at the time of imaging, a part of the image may be overexposed, or conversely, the exposure may be insufficient and the image may be unclear. Therefore, in the present embodiment, the image pickup apparatus 10 generates a plurality of images by taking images of the product display area a plurality of times by changing the parameters at the time of image pickup. Then, the product specifying device 20 identifies the product and / or the product sample located in the product display area by processing these a plurality of images, and outputs the specific result.
  • the product placement area will be referred to as the product shelf 40, and the product and / or the product sample will be described as the product 50 placed on the product shelf 40.
  • An example of a parameter at the time of imaging is exposure.
  • Examples of parameters for setting the exposure are at least one of the exposure time and the aperture.
  • FIG. 2 is a diagram showing an example of the functional configuration of the product specifying device 20.
  • the product specifying device 20 has an acquisition unit 210 and an image processing unit 220.
  • the acquisition unit 210 acquires a plurality of images captured by the image pickup apparatus 10. These plurality of images are generated by imaging the same product shelf 40 while changing the parameters.
  • the image processing unit 220 identifies the product 50 located on the product shelf 40 by processing these a plurality of images, and outputs the specific result.
  • the specific result is, for example, a correspondence between the product identification information (for example, JAN code) of the product 50 and the position of the product 50 on the product shelf 40.
  • the details of the processing performed by the image processing unit 220 will be described later using a flowchart.
  • the product identification device 20 includes a storage processing unit 230.
  • the storage processing unit 230 is an output destination of the specific result of the image processing unit 220, and stores the specific result in the storage unit 240.
  • the storage unit 240 may be a part of the product identification device 20 or may be an external storage device of the product identification device 20.
  • FIG. 3 is a diagram showing a hardware configuration example of the product identification device 20.
  • the product identification device 20 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.
  • the bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the input / output interface 1050, and the network interface 1060 to transmit and receive data to each other.
  • the method of connecting the processors 1020 and the like to each other is not limited to the bus connection.
  • the processor 1020 is a processor realized by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.
  • the memory 1030 is a main storage device realized by a RAM (RandomAccessMemory) or the like.
  • the storage device 1040 is an auxiliary storage device realized by an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like.
  • the storage device 1040 stores a program module that realizes each function of the product specifying device 20 (for example, an acquisition unit 210, an image processing unit 220, and a storage processing unit 230).
  • the processor 1020 reads each of these program modules into the memory 1030 and executes them, each function corresponding to the program module is realized.
  • the storage device 1040 also functions as a storage unit 240.
  • the input / output interface 1050 is an interface for connecting the product specifying device 20 and various input / output devices.
  • the network interface 1060 is an interface for connecting the product specifying device 20 to the network.
  • This network is, for example, LAN (Local Area Network) or WAN (Wide Area Network).
  • the method of connecting the network interface 1060 to the network may be a wireless connection or a wired connection.
  • the product identification device 20 may communicate with the image pickup device 10 via the network interface 1060.
  • the hardware configuration of the image pickup apparatus 10 is also the same as the example shown in FIG.
  • FIG. 4 is a flowchart showing a first example of the process performed by the product specifying device 20.
  • the image pickup apparatus 10 takes an image of the product shelf 40 a plurality of times while changing the parameters.
  • the imaging device 10 performs imaging a plurality of times while changing the parameters for each region.
  • the image pickup apparatus 10 may perform this image pickup according to a program installed in the image pickup apparatus 10, or may perform this image pickup according to an input from a user.
  • the acquisition unit 210 of the product identification device 20 acquires a plurality of images generated by the image pickup device 10 (step S10).
  • the acquisition unit 210 may acquire a plurality of images from the image pickup device 10 via a communication line, or may acquire the images from a storage device that stores the plurality of images. In the latter case, the timing at which the product specifying device 20 performs processing may or may not be immediately after the image pickup device 10 has generated a plurality of images.
  • the image processing unit 220 of the product specifying device 20 processes a plurality of images to specify the position and type of the product 50 placed on the product shelf 40 (step S20). Then, the storage processing unit 230 stores the information indicating the specific result of the image processing unit 220 in the storage unit 240 (step S30).
  • FIG. 5 is a flowchart showing a first detailed example of step S20 in FIG.
  • the image processing unit 220 individually processes each of the plurality of images and recognizes the position and type of the product 50 for each image (step S102). Specifically, the image processing unit 220 specifies the feature points of the product and their positions for each image. Then, the image processing unit 220 recognizes the position and type of the product 50 for each image by performing the matching process of the feature points. In this matching process, the image processing unit 220 uses data in which feature points and product identification information are associated with each other. Then, the image processing unit 220 uses these plurality of recognition results to specify the position and type of the product 50 arranged on the product shelf 40 (step S104).
  • the image processing unit 220 aggregates a plurality of recognition results and uses the aggregated results. Specifically, the image processing unit 220 totals the types of the product 50 for each position of the product 50, and determines that the type having the largest N number is the type of the product 50 at that position.
  • the image processing unit 220 uses the aggregated results. Specifically, the image processing unit 220 totals the types of the product 50 for each position of the product 50, and determines that the type having the largest N number is the type of the product 50 at that position.
  • a slight difference may occur in the positions of the same product 50, but this difference is allowed and treated as the same position when performing aggregation.
  • the image processing unit 220 determines that the type indicated by the recognition result is the type of the product 50 for the product 50 whose existence is detected only in one recognition result. However, even if the image processing unit 220 considers that only the product 50 whose existence is detected in the recognition result of a predetermined number or more (however, the predetermined number is an integer of 2 or more) is placed on the product shelf 40. good.
  • FIG. 6 is a flowchart showing a second detailed example of step S20 in FIG.
  • the image processing unit 220 generates feature point data of the product 50 for each image.
  • This feature point data shows the feature points of the product 50 and the positions of the feature points (step S112).
  • the image processing unit 220 collects the plurality of feature point data generated in step S112 into one integrated feature point data (step S114).
  • each of the plurality of feature point data has at least one set of a feature point and a combination of the positions of the feature points.
  • the integrated feature point data is a collection of the above combinations of the plurality of feature point data as one data.
  • the integrated feature point data includes both the feature points of the first image data and the feature points of the second image data. Therefore, the integrated feature point data includes the entire feature points of the product 50.
  • the image processing unit 220 specifies the position of the product 50 and its type by performing feature point matching on the integrated feature point data (step S116).
  • FIG. 8 is a flowchart showing a second example of the process performed by the product specifying device 20.
  • the product specifying device 20 when the product specifying device 20 satisfies a specific condition, the product specifying device 20 requests the image pickup device 10 to have a plurality of images having different parameters at the time of imaging.
  • the image pickup device 10 first generates one image of the product shelf 40 (hereinafter referred to as the first image).
  • the acquisition unit 210 of the product identification device 20 acquires this first image (step S12).
  • the acquisition unit 210 acquires the first image from the image pickup device 10 via the communication line immediately after the image pickup device 10 generates the first image (that is, before the next image is generated). ..
  • the image processing unit 220 determines whether or not the first image meets the criteria for re-imaging (step S14).
  • the first example of the reference used here is when at least a part of the first image is overexposed (for example, all the values of the red pixel, the green pixel, and the blue pixel are equal to or higher than the reference value). (When there is more than a predetermined area).
  • the second example of this reference is a case where the exposure of the first image is insufficient (for example, when the values of all the pixels are equal to or less than the reference value).
  • the image processing unit 220 processes the first image to form the type of the product 50 on the product shelf 40 and the product thereof. The position is specified (step S20). Then, the storage processing unit 230 stores the specific result of the image processing unit 220 in the storage processing unit 230 (step S30).
  • the image processing unit 220 tells the image pickup apparatus 10 that the parameters at the time of imaging are different from those of the first image.
  • a process for requesting an image is performed (step S16).
  • the image pickup apparatus 10 displays to that effect.
  • the user of the image pickup apparatus 10 changes the parameters at the time of image pickup from the first image, and images the product shelf 40 again to generate an image.
  • the image pickup apparatus 10 generates a plurality of images while changing the parameters at the time of imaging. Then, the image pickup device 10 transmits the generated image to the product identification device 20.
  • the acquisition unit 210 of the product identification device 20 acquires this image (step S18). Then, the image processing unit 220 of the product specifying device 20 specifies the type and position of the product 50 on the product shelf 40 by performing the processing shown in FIG. 5 or FIG. 6 (step S20). Then, the storage processing unit 230 stores the specific result of the image processing unit 220 in the storage processing unit 230 (step S30).
  • the image pickup apparatus 10 images the product shelf 40 a plurality of times while changing the parameters at the time of image pickup, and generates a plurality of images. Then, the product specifying device 20 identifies the position and type of the product 50 arranged on the product shelf 40 by processing these a plurality of images. Therefore, the recognition accuracy of the product 50 by the image analysis does not decrease.
  • the image pickup apparatus 10 performs a part of the processing performed by the image processing unit 220 of the product identification apparatus 20.
  • FIG. 9 is a flowchart showing a process performed by the product specifying device 20 according to the first modification.
  • the example shown in this figure corresponds to the process shown in FIG.
  • the image pickup apparatus 10 generates data indicating the feature points of the product 50 and the positions of the feature points for each of the plurality of images.
  • the image pickup device 10 transmits analysis data indicating this data for each of a plurality of images to the product identification device 20.
  • the acquisition unit 210 of the product identification device 20 acquires this analysis data (step S200).
  • the image processing unit 220 of the product specifying device 20 identifies the position and type of the product 50 placed on the product shelf 40 by performing the processing shown in FIG. 5 or FIG. 6 (step S202).
  • the storage processing unit 230 stores the specific result of the image processing unit 220 in the storage unit 240 (step S204).
  • a plurality of images obtained by capturing a product display area in which a product and / or a product sample are arranged, and a plurality of images in which the parameters of the imaging means at the time of imaging are different from each other are acquired.
  • a product identification device equipped with. 2.
  • the image processing means recognizes the position of the product or the product sample and the type of the product or the product sample for each of the plurality of images, and uses the recognition result for each image to obtain the product located in the product display area.
  • the image processing means is For each of the plurality of images, feature points of the product or product sample and feature point data indicating the positions of the feature points are generated.
  • a product identification device that collects the plurality of the feature point data as one integrated feature point data and uses the integrated feature point data to specify the product or the product sample located in the product display area.
  • the parameter is a product identification device that is exposure. 5.
  • the acquisition means is a product identification device that requests the plurality of images from the image pickup means when a specific condition is satisfied. 6.
  • the acquisition means The first image is acquired from the image pickup means, and the first image is obtained.
  • the image pickup means is requested to request another image having different parameters from the first image, assuming that the specific condition is satisfied.
  • the image processing means processes the first image to identify the product or the product sample located in the product display area. Specific device. 7. Analysis data showing the feature points of the product or the product sample and the positions of the feature points for each of the plurality of images, which is the result of processing a plurality of images of the product display area in which the product and / or the product sample are lined up.
  • the computer recognizes the position of the product or the product sample and the type of the product or the product sample for each of the plurality of images, and uses the recognition result for each image to position the product in the product display area.
  • the computer For each of the plurality of images, feature points of the product or product sample and feature point data indicating the positions of the feature points are generated.
  • a product identification method in which the plurality of the feature point data are combined into one integrated feature point data, and the product or the product sample located in the product display area is specified by using the integrated feature point data. 11.
  • the parameter is the product identification method of exposure.
  • the computer is a product identification method that requests the plurality of images from the image pickup means when a specific condition is satisfied.
  • the computer In the product identification method described in 12 above, In the acquisition, the computer The first image is acquired from the image pickup means, and the first image is obtained. When the first image meets the criteria, the image pickup means is requested to request another image having different parameters from the first image, assuming that the specific condition is satisfied.
  • the computer when the first image does not meet the criteria, the computer processes the first image to identify the product or the product sample located in the product display area. How to identify the product. 13.
  • the computer Analysis data showing the feature points of the product or the product sample and the positions of the feature points for each of the plurality of images, which is the result of processing a plurality of images of the product display area in which the product and / or the product sample are lined up. Acquired, By processing the analysis data, the product or the product sample located in the product display area is specified, and the specific result is output.
  • the plurality of images are a product identification method in which the parameters of the imaging means at the time of imaging are different from each other. 14.
  • An acquisition function for acquiring a plurality of images in which a product and / or a product display area in which product samples are lined up, and the parameters of the imaging means at the time of imaging are different from each other.
  • An image processing function that identifies the product or the product sample located in the product display area by processing the plurality of images and outputs the specific result.
  • the image processing function recognizes the position of the product or product sample and the type of the product or product sample for each of the plurality of images, and uses the recognition result for each image to display the product located in the product display area. Or a program that identifies the product sample. 16.
  • the image processing function is For each of the plurality of images, feature points of the product or product sample and feature point data indicating the positions of the feature points are generated.
  • the parameter is a program that is exposure.
  • the acquisition function is a program that requests the plurality of images from the image pickup means when a specific condition is satisfied. 19.
  • the acquisition function is The first image is acquired from the image pickup means, and the first image is obtained. When the first image meets the criteria, the image pickup means is requested to request another image having different parameters from the first image, assuming that the specific condition is satisfied.
  • the image processing function is a program that identifies the product or the product sample located in the product display area by processing the first image when the first image does not meet the criteria. .. 20.
  • On the computer Analysis data showing the feature points of the product or the product sample and the positions of the feature points for each of the plurality of images, which is the result of processing a plurality of images of the product display area in which the product and / or the product sample are lined up.
  • the acquisition function to acquire and A data processing function that identifies the product or the product sample located in the product display area by processing the analysis data and outputs the specific result.
  • the plurality of images are programs in which the parameters of the imaging means at the time of imaging are different from each other.
  • Image pickup device 20
  • Product identification device 40
  • Product shelf 50
  • Product 210
  • Acquisition unit 220
  • Image processing unit 230
  • Storage processing unit 240 Storage unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
PCT/JP2020/019259 2020-05-14 2020-05-14 商品特定装置、商品特定方法、及びプログラム Ceased WO2021229754A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2020/019259 WO2021229754A1 (ja) 2020-05-14 2020-05-14 商品特定装置、商品特定方法、及びプログラム
JP2022522438A JP7400962B2 (ja) 2020-05-14 2020-05-14 商品特定装置、商品特定方法、及びプログラム
US17/923,288 US20230368535A1 (en) 2020-05-14 2022-05-14 Product identification apparatus, product identification method, and non-transitory computer-readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/019259 WO2021229754A1 (ja) 2020-05-14 2020-05-14 商品特定装置、商品特定方法、及びプログラム

Publications (1)

Publication Number Publication Date
WO2021229754A1 true WO2021229754A1 (ja) 2021-11-18

Family

ID=78525549

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/019259 Ceased WO2021229754A1 (ja) 2020-05-14 2020-05-14 商品特定装置、商品特定方法、及びプログラム

Country Status (3)

Country Link
US (1) US20230368535A1 (https=)
JP (1) JP7400962B2 (https=)
WO (1) WO2021229754A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025177500A (ja) * 2024-05-23 2025-12-05 株式会社マーケットヴィジョン 情報処理システム

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009187482A (ja) * 2008-02-08 2009-08-20 Nippon Sogo System Kk 棚割再現方法、棚割再現プログラム、棚割評価方法、棚割評価プログラム及び記録媒体
WO2016117600A1 (ja) * 2015-01-22 2016-07-28 日本電気株式会社 商品棚割管理装置及び商品棚割管理方法
JP2018005682A (ja) * 2016-07-05 2018-01-11 日立オートモティブシステムズ株式会社 画像処理装置
JP2019012413A (ja) * 2017-06-30 2019-01-24 日立オートモティブシステムズ株式会社 画像処理装置
JP2019160328A (ja) * 2019-04-16 2019-09-19 株式会社マーケットヴィジョン 画像認識システム
JP2019211869A (ja) * 2018-05-31 2019-12-12 株式会社マーケットヴィジョン 検索対象情報絞込システム
JP2020071809A (ja) * 2018-11-02 2020-05-07 ソニーセミコンダクタソリューションズ株式会社 画像処理装置および画像処理方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10241593B2 (en) * 2013-02-04 2019-03-26 Pixart Imaging Inc. Optical processing apparatus and light source luminance adjustment method thereof
CN109414819A (zh) * 2016-01-08 2019-03-01 4D空间天才股份有限公司 用于自动化图像获取的机器人
WO2018186398A1 (ja) * 2017-04-07 2018-10-11 日本電気株式会社 学習データ生成装置、学習データ生成方法、および記録媒体
EP3738073B1 (en) * 2018-01-10 2025-06-25 Trax Technology Solutions Pte Ltd. Automatically monitoring retail products based on captured images

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009187482A (ja) * 2008-02-08 2009-08-20 Nippon Sogo System Kk 棚割再現方法、棚割再現プログラム、棚割評価方法、棚割評価プログラム及び記録媒体
WO2016117600A1 (ja) * 2015-01-22 2016-07-28 日本電気株式会社 商品棚割管理装置及び商品棚割管理方法
JP2018005682A (ja) * 2016-07-05 2018-01-11 日立オートモティブシステムズ株式会社 画像処理装置
JP2019012413A (ja) * 2017-06-30 2019-01-24 日立オートモティブシステムズ株式会社 画像処理装置
JP2019211869A (ja) * 2018-05-31 2019-12-12 株式会社マーケットヴィジョン 検索対象情報絞込システム
JP2020071809A (ja) * 2018-11-02 2020-05-07 ソニーセミコンダクタソリューションズ株式会社 画像処理装置および画像処理方法
JP2019160328A (ja) * 2019-04-16 2019-09-19 株式会社マーケットヴィジョン 画像認識システム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025177500A (ja) * 2024-05-23 2025-12-05 株式会社マーケットヴィジョン 情報処理システム

Also Published As

Publication number Publication date
US20230368535A1 (en) 2023-11-16
JPWO2021229754A1 (https=) 2021-11-18
JP7400962B2 (ja) 2023-12-19

Similar Documents

Publication Publication Date Title
US20230214989A1 (en) Defect detection method, electronic device and readable storage medium
CN110784644B (zh) 图像处理方法及装置
CN114719966A (zh) 光源确定方法、装置、电子设备及存储介质
CN114332993B (zh) 人脸识别方法、装置、电子设备及计算机可读存储介质
US20210012456A1 (en) Information processing method, image processing apparatus, and storage medium
CN110865911B (zh) 图像测试方法、装置、存储介质、图像采集卡及上位机
CN116362659A (zh) 物品分播方法、自动分播墙、设备、介质和程序产品
WO2021229754A1 (ja) 商品特定装置、商品特定方法、及びプログラム
CN115134677A (zh) 视频封面选择方法、装置、电子设备以及计算机存储介质
CN117636137A (zh) 一种gpu裸金属算力资源分配调度方法、装置及存储介质
EP1976308A2 (en) Device and method for measuring noise characteristics of image sensor
US12567124B2 (en) Technologies for improved whole slide imaging
JP2023181293A (ja) 画像記憶装置、画像記憶方法、及びプログラム
JP6575628B1 (ja) 情報処理装置、情報処理システム、制御方法、及びプログラム
EP3890312A1 (en) Distributed image analysis method and system, and storage medium
JP7428244B2 (ja) 商品特定装置、商品特定方法、およびプログラム
KR20210089808A (ko) 딥러닝을 활용한 소변검사 방법
CN112770111B (zh) 一种鉴定镜头光轴与图像传感器中心重合的装置及方法
JPWO2021229754A5 (https=)
CN111860136B (zh) 包裹定位方法、装置、设备及计算机可读存储介质
CN116558781B (zh) 用于显示屏体检测的方法、装置、终端设备及系统
JP6939855B2 (ja) 情報処理装置、情報処理システム、制御方法、及びプログラム
CN109857880B (zh) 一种基于模型的数据处理方法、装置及电子设备
JP2023095926A (ja) 情報処理装置、情報処理システム、制御方法、及びプログラム
CN115048068B (zh) 一种4kled显示屏图像显示控制系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20935752

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022522438

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20935752

Country of ref document: EP

Kind code of ref document: A1