Aug 2026
Real-time detection of outdoor non-obvious anthropogenic trace via texture contrast learning
Experiments demonstrate that the proposed self-supervised machine vision framework effectively segments camouflaged traces in low-quality, unlabeled outdoor images captured by a mobile robot, outperforming existing COD models in adaptation speed and segmentation accuracy on a challenging custom rescue dataset.
Shuai Wang, Jiajie Sha, Wei You et al.
· Machine Vision and Applicati... · 0 citations