AP-Net: a metallic surface defect detection approach with lightweight adaptive attention and enhanced feature pyramid.
Faquan ChenMiaolei DengHui GaoXiaoya YangDexian ZhangPublished in: Clust. Comput. (2024)
Keyphrases
- lightweight
- defect detection
- textured surfaces
- d objects
- multiscale
- input image
- communication infrastructure
- feature extraction
- multiresolution
- automated visual inspection
- wireless sensor networks
- three dimensional
- surface reconstruction
- feature vectors
- image features
- visual attention
- rfid tags
- dos attacks
- development environments
- histogram of oriented gradients
- computer vision