GAL: A global-attributes assisted labeling system for outdoor scenes

详细信息    查看全文

• 作者：Yuzhuo Ren ; ^{yuzhuore@usc.edu} ; Chen Chen ^{chen80@usc.edu} ; Shangwen Li ^{shangwel@usc.edu} ; C.-C. Jay Kuo ^{cckuo@sipi.usc.edu}
• 关键词：Outdoor layout estimation ; Semantic labeling ; Global attribute vector ; Convolutional neural network ; 3D reconstruction
• 刊名：Journal of Visual Communication and Image Representation
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：42
• 期：Complete
• 页码：192-206
• 全文大小：4769 K
• 卷排序：42

文摘

A three-stage geometric labeling system which integrates local information and global information is proposed. Seven global attributes for geometric labeling are proposed. The proposed system is able to handle a large variety of scenes, both urban scene and natural scene. A graphical model is proposed to integrate local and global information and to optimize geometric labeling. Our system achieves state-of-the art performance against a popular benchmark dataset.