Occlusion cues for image scene layering |
| |
| Authors: | Xiaowu Chen Qing Li Dongyue Zhao Qinping Zhao |
| |
| Affiliation: | 1. School of Automation, Southeast University, Nanjing 210096, China;2. Department of Communication Engineering, Communication University of China, Beijing 100024, China;1. Department of Psychiatry, Yale University School of Medicine, New Haven, CT, USA;2. The John B. Pierce Laboratory, New Haven, CT, USA;1. Department of Industrial Management, National Taiwan University of Science and Technology, No. 43, Sec. 4, Keelung Rd., Da‘an Dist., Taipei City 10607, Taiwan, ROC;2. Industrial Engineering Department, Bunda Mulia University, Lodan Raya Street No. 2 North Jakarta – 14430, Jakarta, Indonesia |
| |
| Abstract: | To bring computer vision closer to human vision, we attempt to enable computer to understand the occlusion relationship in an image. In this paper, we propose five low dimensional region-based occlusion cues inspired by the human perception of occlusion. These cues are semantic cue, position cue, compactness cue, shared boundary cue and junction cue. We apply these cues to predict the region-wise occlusion relationship in an image and infer the layer sequence of the image scene. A preference function, trained with samples consisting of these cues, is defined to predict the occlusion relationship in an image. Then we put all the occlusion predictions into the layering algorithm to infer the layer sequence of the image scene.The experiments on rural, artificial and outdoor scene datasets show the effectiveness of our method for occlusion relationship prediction and image scene layering. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
