期刊
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
卷 138, 期 -, 页码 281-294出版社
ELSEVIER
DOI: 10.1016/j.isprsjprs.2018.02.014
关键词
Geospatial object detection; High spatial resolution (HSR) remote sensing imagery; Residual network; Pre-training mechanism; Position-sensitive balancing
类别
资金
- National Key Research and Development Program of China [2017YFB0504202]
- National Natural Science Foundation of China [41622107, 41771385]
- Natural Science Foundation of Hubei Province in China [2016CFA029]
Multi-class geospatial object detection from high spatial resolution (HSR) remote sensing imagery is attracting increasing attention in a wide range of object-related civil and engineering applications. However, the distribution of objects in HSR remote sensing imagery is location-variable and complicated, and how to accurately detect the objects in HSR remote sensing imagery is a critical problem. Due to the powerful feature extraction and representation capability of deep learning, the deep learning based region proposal generation and object detection integrated framework has greatly promoted the performance of multi-class geospatial object detection for HSR remote sensing imagery. However, due to the translation caused by the convolution operation in the convolutional neural network (CNN), although the performance of the classification stage is seldom influenced, the localization accuracies of the predicted bounding boxes in the detection stage are easily influenced. The dilemma between translation invariance in the classification stage and translation-variance in the object detection stage has not been addressed for HSR remote sensing imagery, and causes position accuracy problems for multi-class geospatial object detection with region proposal generation and object detection. In order to further improve the performance of the region proposal generation and object detection integrated framework for HSR remote sensing imagery object detection, a position-sensitive balancing (PSB) framework is proposed in this paper for multi-class geospatial object detection from HSR remote sensing imagery. The proposed PSB framework takes full advantage of the fully convolutional network (FCN), on the basis of a residual network, and adopts the PSB framework to solve the dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage. In addition, a pre-training mechanism is utilized to accelerate the training procedure and increase the robustness of the proposed algorithm. The proposed algorithm is validated with a publicly available 10-class object detection dataset. (C) 2018 Published by Elsevier B.V. on behalf of International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).
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