期刊
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY
卷 39, 期 2, 页码 263-269出版社
CHINESE ACAD SCIENCES, INST ELECTRONICS
DOI: 10.11999/JEIT160329
关键词
Road segmentation; Scene adaptive; Deep Convolutional Neural Network (DCNN); Composite deep structure; Auto-encoder
资金
- National Natural Science Foundation of China [U1564201, 61601203, 61573171, 61403172]
- China Postdoctoral Science Foundation [2014M561592, 2015T80511]
- Key Research and Development Program of Jiangsu Province [BE2016149]
- Natural Science Foundation of Jiangsu Province [BK20140555]
- Six Talent Peaks Project of Jiangsu Province [2015-JXQC-012, 2014-DZXX-040]
The existed machine learning based road segmentation algorithms maintain obvious shortage that the detection effect decreases dramatically when the distribution of training samples and the scene target samples does not match. Focusing on this issue, a scene adaptive road segmentation algorithm based on Deep Convolutional Neural Network (DCNN) and auto encoder is proposed. Firstly, classic Slow Feature Analysis (SFA) and Gentle Boost based method is used to generate online samples whose label contain confidence value. After that, using the automatic feature extraction ability of DCNN and performing source-target scene feature similarity calculation with deep auto-encoder, a composite deep structure based scene adaptive classifier and its training method are designed. The experiment on KITTI dataset demonstrates that the proposed method outperforms the existed machine learning based road segmentation algorithms which upgrades the detection rate on average of around 4.5%.
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