Contemporary Amperex Technology Co., Ltd.

Contemporary Amperex Technology (hong Kong) Limited

Contemporary Amperex Technology Limited

Chao Yuan

Guannan Jiang

Annan Shu

Lili Han

Jv Huang

A correction method for a depth image of a battery includes obtaining the depth image of the battery. The depth image includes two adjacent surfaces of a shell assembly of the battery and an intersecting line between the two adjacent surfaces. The method further includes extracting the intersecting line from the depth image, determining planes in the depth image in which the two adjacent surfaces are located, and obtaining a datum plane based on the intersecting line and the planes in which the two adjacent surfaces are located. The datum plane is parallel to the intersecting line, and included angles between the datum plane and the planes in which the two adjacent surfaces are located are equal to each other. The method also includes projecting and mapping points in the depth image to the datum plane, to obtain depth information of points in a corrected depth image.

Correction method and apparatus for depth image, and method for welding inspection of shell assembly of battery

The present application provides a method and system for defect detection. The method includes: acquiring a two-dimensional (2D) picture of an object to be detected; inputting the acquired 2D picture to a trained defect segmentation model to obtain a segmented 2D defect mask, where the defect segmentation model is trained based on a multi-level feature extraction instance segmentation network with intersection over union (IoU) thresholds being increased level by level, and the 2D defect mask includes information about a defect type, a defect size, and a defect location of a segmented defect region; and determining the segmented 2D defect mask based on a predefined defect rule to output a defect detection result.

Method and system for defect detection

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.

Growing community of inventors

Ningde, China

Chao Yuan