论文成果
CHANGE DETECTION OF MARINE RECLAMATION USING MULTISPECTRAL IMAGES VIA PATCH-BASED RECURRENT NEURAL NETWORK
- 点击次数：
- 论文类型：会议论文
- 发表时间：2017-01-01
- 收录刊物：EI、CPCI-S
- 文献类型：A
- 卷号：2017-July
- 页面范围：612-615
- 关键字：Change detection; marine reclamation; recurrent neural network;
multispectral image
- 摘要：Marine reclamation plays an increasingly important role in expanding living space, which should be monitored to ensure legitimate development. In this paper, a patch-based recurrent neural network is developed for change detection of marine reclamation. To capture spatial difference of image patches in two images, a patch-based recurrent neural network is proposed to extract features, where patches from two multi-spectral images are stacked as a sequence for inputting. After training the deep network, Softmax classifier is applied to detect the changed region. It is illustrated that our network can obtain the difference of two images to improve detection accuracies. Experiments on the study area of the Jinzhou Bay demonstrate that the proposed method outperforms other approaches.
