The Devil is in the Crack Orientation: A New Perspective for Crack Detection

no code implementations • ICCV 2023 • Zhuangzhuang Chen, Jin Zhang, Zhuonan Lai, Guanming Zhu, Zun Liu, Jie Chen, Jianqiang Li

However, the vanilla adaptation of the existing oriented object detection methods to the crack detection tasks will result in limited performance, due to the boundary discontinuity issue and the ambiguities in sub-crack orientation.

Crack Segmentation object-detection +2

Geometry-Aware Guided Loss for Deep Crack Recognition

no code implementations • CVPR 2022 • Zhuangzhuang Chen, Jin Zhang, Zhuonan Lai, Jie Chen, Zun Liu, Jianqiang Li

Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss.