Modeling Multi-Granularity Context Information Flow for Pavement Crack Detection

arXiv:2404.12702v1 Announce Type: new
Abstract: Crack detection has become an indispensable, interesting yet challenging task in the computer vision community. Specially, pavement cracks have a highly complex spatial structure, a low contrasting background and a weak spatial continuity, posing a significant challenge to an effective crack detection method. In this paper, we address these problems from a view that utilizes contexts of the cracks and propose an end-to-end deep learning method to model the context information flow. To precisely localize …

abstract arxiv become challenge community computer computer vision context continuity cs.cv detection flow information low modeling paper spatial type vision