公开(公告)号：US20240005469A1

公开(公告)日：2024-01-04

申请号：US18129819

申请日：2023-03-31

Applicant: Contemporary Amperex Technology Co., Limited

Inventor： Guannan Jiang ,  Annan Shu ,  Qiangwei Huang

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/136

CPC classification number: G06T7/0002 ,  G06T2207/20081 ,  G06T7/136 ,  G06T7/11

Abstract: Embodiments of this application provide a defect detection method and apparatus. The method includes: obtaining an image for inspection; performing anomaly detection on the image for inspection to obtain an anomaly region image corresponding to the image for inspection; and performing defect classification on the anomaly region image to obtain defect detection information of the image for inspection. The defect detection method of the embodiments of this application is divided into two steps of anomaly detection and defect classification. Anomaly detection is performed on the image for inspection first, and then defect classification needs to be performed only on an anomaly region, reducing the workload of defect classification, thereby improving the efficiency of defect detection.

公开(公告)号：US11823457B2

公开(公告)日：2023-11-21

申请号：US18131379

申请日：2023-04-06

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Guannan Jiang ,  Qiangwei Huang ,  Annan Shu

IPC: G06V20/50 ,  G06V10/82 ,  G06V10/44 ,  G06V10/26 ,  G06V10/70

CPC classification number: G06V20/50 ,  G06V10/26 ,  G06V10/44 ,  G06V10/768 ,  G06V10/82

Abstract: An image recognition method may include: acquiring a target image, where the target image may include a weld bead region; performing initial segmentation on the target image, to obtain a first recognition result, where the first recognition result may include first recognition information for the weld bead region in the target image; performing feature extraction on the target image, to obtain a region representation; obtaining a context representation based on the first recognition result and the region representation, where the context representation may be used for representing a correlation between each pixel and remaining pixels in the target image; and obtaining a second recognition result based on the context representation, where the second recognition result may include second recognition information for the weld bead region in the target image.

公开(公告)号：US12100130B2

公开(公告)日：2024-09-24

申请号：US17885671

申请日：2022-08-11

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Liangjin Hu ,  Jinghua Huang ,  Kunming Zhang ,  Guannan Jiang ,  Lin Ma

IPC: G06T7/00 ,  G06T7/60 ,  H04N23/56 ,  H04N23/69

CPC classification number: G06T7/0004 ,  G06T7/60 ,  H04N23/56 ,  H04N23/69 ,  G06T2207/20221 ,  G06T2207/30242

Abstract: This application provides an apparatus and method for detecting tab folds, and an image analyzer. The apparatus for detecting tab folds includes: a first image obtaining module, configured to obtain a first image of a first lateral face of tabs of a battery cell; a second image obtaining module, configured to obtain a second image of a second lateral face of the tabs, where the second lateral face is different from the first lateral face; and an image analyzer, configured to obtain, based on the first image, a first number of layers of the tabs corresponding to the first lateral face, and obtain, based on the second image, a second number of layers of the tabs corresponding to the second lateral face, and determine, based on at least one of the first number of layers or the second number of layers, whether the tabs are in a folded state.

公开(公告)号：US12056916B2

公开(公告)日：2024-08-06

申请号：US18204406

申请日：2023-06-01

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Guannan Jiang ,  Xi Wang ,  Zhiyu Wang

IPC: G06T7/00 ,  G06V10/776

CPC classification number: G06V10/776 ,  G06T7/001 ,  G06T2207/30108

Abstract: Embodiments of the present application provide a detection method, a detection device, and a storage medium. The detection method may comprise: obtaining a to-be-detected image; obtaining a plurality of confidence levels corresponding to a plurality of detection items according to the to-be-detected image; and determining a detection result of the to-be-detected image according to the plurality of confidence levels and a plurality of detection thresholds, where the plurality of detection thresholds may be corresponding to the plurality of detection items and may be a non-inferior solution of objective functions of an overkill rate and a missed detection rate, the overkill rate may be the ratio of qualified ones detected as defective, and the missed detection rate may be the ratio of defective ones detected as qualified.

公开(公告)号：US12045974B2

公开(公告)日：2024-07-23

申请号：US18306657

申请日：2023-04-25

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Qiangwei Huang ,  Guannan Jiang ,  Zhiyu Wang

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/187 ,  G06T7/194 ,  G06T7/60

CPC classification number: G06T7/0006 ,  G06T7/11 ,  G06T7/187 ,  G06T7/194 ,  G06T7/60 ,  G06T2207/30108 ,  G06T2207/30242

Abstract: A tab bending detection method and apparatus, an electronic device, and a storage medium are provided. The method includes: performing skeleton extraction on a sectional image of multiple layers of tabs to obtain a skeleton image of the multiple layers of tabs; merging damaged connected components in the skeleton image to obtain a merged connected component, where the damaged connected components are connected components on which breaking occurs in a same tab section; calculating a target number of the multiple layers of tabs based on the merged connected component and an undamaged connected component; and detecting, based on the target number and a preset number, whether any tab in the multiple layers of tabs is in a bending state. The damaged connected components are merged to obtain the merged connected component.

公开(公告)号：US11915410B2

公开(公告)日：2024-02-27

申请号：US18138501

申请日：2023-04-24

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Lu Li ,  Zhiyu Wang ,  Guannan Jiang

IPC: G06T3/60 ,  G06T5/20 ,  G06T7/00 ,  G06T7/13 ,  G06V10/25 ,  G06V10/28 ,  G06V10/74 ,  G06V10/75

CPC classification number: G06T7/0008 ,  G06T3/60 ,  G06T5/20 ,  G06T7/13 ,  G06V10/25 ,  G06V10/28 ,  G06V10/751 ,  G06V10/761 ,  G06T2207/20164

Abstract: A method and an apparatus for inspecting tab appearance of cell assembly, an electronic device, a non-transitory computer-readable storage medium, and a computer program product are provided. The method includes: obtaining an image for inspection that includes a background region and a cell assembly image region, where the cell assembly image region includes a body zone and a plurality of tab stacking regions, each tab stacking region adjoining a top edge or a bottom edge of the body zone; determining each root corner of the plurality of tab stacking regions in the image for inspection; determining two side edges of the body zone in the image for inspection; determining at least one reference edge line in the image for inspection based on the two side edges of the body zone in the image for inspection; and determining result information of the tab appearance inspection based on each root corner of the plurality of tab stacking regions in the image for inspection and the at least one reference edge line.

公开(公告)号：US20240062422A1

公开(公告)日：2024-02-22

申请号：US18499238

申请日：2023-11-01

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Qian Wu ,  Jiwei Chen ,  Guannan Jiang

IPC: G06T7/80 ,  H04N23/60

CPC classification number: G06T7/80 ,  H04N23/64

Abstract: The present application relates to a camera calibration method and apparatus, a computer device, a storage medium, and a program product. The method includes: obtaining a first operation instruction based on a camera calibration interface; determining, from configuration information, target configuration information matching the first operation instruction and set based on the camera calibration interface; and then executing a corresponding operation in a camera calibration process based on the first operation instruction and the target configuration information. However, the camera calibration process provided by embodiments of the present application is implemented based on the camera calibration interface, without switching back and forth between a plurality of tools, thereby making the camera calibration process less cumbersome.

公开(公告)号：US11804037B1

公开(公告)日：2023-10-31

申请号：US18332289

申请日：2023-06-09

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Guannan Jiang ,  Jv Huang ,  Chao Yuan

IPC: G06K9/00 ,  G06V10/82 ,  G06T5/00 ,  G06T7/00 ,  G06V10/771 ,  G06V20/70 ,  G06T7/12

CPC classification number: G06V10/82 ,  G06T5/002 ,  G06T7/0008 ,  G06T7/12 ,  G06V10/771 ,  G06V20/70 ,  G06T2207/20081 ,  G06T2207/20132

Abstract: The present application provides a method and a system for generating an image sample having a specific feature. The method includes: training a generative adversarial network-based sample generation model, where the generative adversarial network includes a generator and two discriminators: a global discriminator configured to perform global discrimination on an image, and a local discriminator configured to perform local discrimination on a specific feature; and inputting, to a trained generator that serves as a sample generation model, a semantic segmentation image that indicates a location of the specific feature and a corresponding real image not having the specific feature, to obtain a generated image sample having the specific feature.

公开(公告)号：US11763549B1

公开(公告)日：2023-09-19

申请号：US18308374

申请日：2023-04-27

Applicant: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

Inventor： Annan Shu ,  Guannan Jiang ,  Zhiyu Wang

IPC: G06K9/00 ,  G06V10/774 ,  G06T7/00 ,  G06V10/764 ,  G06V10/44 ,  G06V10/74

CPC classification number: G06V10/774 ,  G06T7/0004 ,  G06V10/44 ,  G06V10/761 ,  G06V10/764 ,  G06T2207/20081 ,  G06T2207/30108

Abstract: A method for training a cell defect detection model includes training a defect classification model that includes an output layer using a plurality of first sample images so that a defect classification model obtained through training is capable of predicting a plurality of first-preset-category defects of a cell, inputting a second sample image to a defect classification model with at least an output layer removed to obtain a sample feature vector of the second sample image, inputting the sample feature vector of the second sample image to a backbone model to obtain a predicted defect classification result of the second sample image, and adjusting, based on a second-preset-category defect and the predicted defect classification result of the second sample image, parameters of the backbone model and the defect classification model with at least the output layer removed.