单目图像深度结构恢复研究.pdfVIP

Computer Science and Application 计算机科学与应用, 2018, 8(4), 522-531 Published Online April 2018 in Hans. /journal/csa /10.12677/csa.2018.84058 Research for Scene Depth Structure of Monocular Image Dan Sun, Kewei Wu, Yongxuan Sun, Zhao Xie School of Computer and Information, Hefei University of Technology, Hefei Anhui th st th Received: Apr. 6 , 2018; accepted: Apr. 21 , 2018; published: Apr. 28 , 2018 Abstract Due to the inaccurate depth perception of the existing single depth cues, inspired by the archi- tecture of collecting images and successfully building three-dimensional information created by Marr, an approach combined with multiple depth cues is presented for depth ordering of mo- nocular images in outdoor scenes. First of all, the input monocular image is segmented to de- termine the ordering objects. Then those objects are labeled with regional attribute, which is labeled as one of ground, sky and vertical. The depth of the regions labeled as sky are fixed to the furthest, and the depth of the regions labeled as ground are fixed to the nearest, and other regions are ordered by local occlusion cues and global depth cues. Furthermore, based on above depth cues, we construct a graph model, and belief propagation is leveraged to enforce global depth reasoning. Finally, considering appearance characteristics of the regions, we group re- gions belonging to the same objects on the same depth layer to account for over-segmentation issues, and a hybrid evolution algorithm is utilized to minimize global energy. The properties of depth ordering of the proposed method are evaluated on the BSDS500 dataset, and the experi- mental