Context-Enhanced Detector For Building Detection From Remote Sensing Images

作     者：Huang, Ziyue Zhang, Mingming Liu, Qingjie Wang, Wei Dong, Zhe Wang, Yunhong 

作者机构：The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Hangzhou Innovation Institute Beihang University Hangzhou310051 China The National Disaster Reduction Center of China Beijing100124 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Semantic Segmentation 

摘      要：The field of building detection from remote sensing images has made significant progress, but faces challenges in achieving high-accuracy detection due to the diversity in building appearances and the complexity of vast scenes. To address these challenges, we propose a novel approach called Context-Enhanced Detector (CEDet). Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy. Specifically, we introduce two modules: the Semantic Guided Contextual Mining (SGCM) module, which aggregates multi-scale contexts and incorporates an attention mechanism to capture long-range interactions, and the Instance Context Mining Module (ICMM), which captures instance-level relationship context by constructing a spatial relationship graph and aggregating instance features. Additionally, we introduce a semantic segmentation loss based on pseudo-masks to guide contextual information extraction. Our method achieves state-of-the-art performance on three building detection benchmarks, including CNBuilding-9P, CNBuilding-23P, and SpaceNet. Copyright © 2023, The Authors. All rights reserved.