US 12,406,349 B2
Method and apparatus for detecting defect on surface of cell
Hongji Sun, Ningde (CN); Fei Chen, Ningde (CN); and Guannan Jiang, Ningde (CN)
Assigned to CONTEMPORARY AMPEREX TECHNOLOGY (HONG KONG) LIMITED, Hong Kong (CN)
Filed by CONTEMPORARY AMPEREX TECHNOLOGY (HONG KONG) LIMITED, Hong Kong (CN)
Filed on Aug. 23, 2023, as Appl. No. 18/454,184.
Application 18/454,184 is a continuation of application No. PCT/CN2023/085076, filed on Mar. 30, 2023.
Claims priority of application No. 202210907837.9 (CN), filed on Jul. 29, 2022.
Prior Publication US 2024/0037726 A1, Feb. 1, 2024
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01)
CPC G06T 7/0004 (2013.01) [G06T 7/11 (2017.01); G06T 2207/10024 (2013.01); G06T 2207/20084 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer implemented method for detecting a defect on a surface of a battery cell, comprising: obtaining an initial image of the surface of the cell by using an image acquisition unit; preprocessing the initial image to obtain at least one image to be detected of the surface of the cell; and inputting the at least one image to be detected into a defect detection neural network model, and obtaining a detection result outputted by the defect detection neural network model, the detection result being used to indicate whether there is a defect on the surface of the cell;
wherein the at least one image to be detected comprises a plurality of images to be detected, and the initial image contains a cell surface area where the surface of the cell is located; and the preprocessing the initial image to obtain at least one image to be detected of the surface of the cell comprises: extracting the cell surface area from the initial image; and segmenting the cell surface area to obtain the plurality of images to be detected;
wherein the initial image has a first exposure; and the extracting the cell surface area from the initial image comprises: directly extracting the cell surface area from the initial image; and adjusting an exposure of the cell surface area to obtain a cell surface area having a second exposure, wherein the first exposure is higher than the second exposure;
wherein the first exposure is configured such that a pixel value range of the cell surface area in the initial image is different from a pixel value range of other areas in the initial image than the cell surface area;
wherein the extracting the cell surface area from the initial image further comprises: extracting a cell surface area with a preset color channel from the cell surface area having the second exposure; and the segmenting the cell surface area to obtain the plurality of images to be detected comprises: segmenting the cell surface area with the preset color channel to obtain the plurality of images to be detected.