期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 57, 期 10, 页码 7339-7351出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2019.2912985
关键词
Aerial image; deep learning; scene context-driven; vehicle detection
类别
资金
- National Natural Science Foundation of China [41771458, 41601352]
- Natural Science Foundation of Hunan Province, China [2017JJ3378]
- Young Elite Scientists Sponsorship Program by Hunan Province of China [2018RS3012]
- Land and Resource Department Scientific Research Program of Hunan Province, China [2017-13]
- Hunan Science and Technology Department Innovation Platform Open Fund Project [18K005]
As the spatial resolution of remote sensing images is improving gradually, it is feasible to realize scene-object collaborative image interpretation. Unfortunately, this idea is not fully utilized in vehicle detection from high-resolution aerial images, and most of the existing methods may be promoted by considering the variability of vehicle spatial distribution in different image scenes and treating vehicle detection tasks scene-specific. With this motivation, a scene context-driven vehicle detection method is proposed in this paper. At first, we perform scene classification using the deep learning method and, then, detect vehicles in roads and parking lots separately through different vehicle detectors. Afterward, we further optimize the detection results using different postprocessing rules according to different scene types. Experimental results show that the proposed approach outperforms the state-of-the-art algorithms in terms of higher detection accuracy rate and lower false alarm rate.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据