Who Blocks Who: Simultaneous Segmentation of Occluded Objects  

作　　者：王楠 艾海舟 汤锋 

机构地区：[1]Department of Computer Science and Technology, Tsinghua University [2]Multimedia Interaction and Understanding Lab, HP Labs

出　　处：《Journal of Computer Science & Technology》2013年第5期890-906,共17页计算机科学技术学报（英文版）

基　　金：supported in part by the National Natural Science Foundation of China under Grant No.61075026;the National Basic Research 973 Program of China under Grant No.2011CB302203.

摘　　要：In this paper we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophis- ticated shape priors with the consideration of blocking relationship between nearby objects. Different from conventional layered model which attempts to solve the full ordering problem, we decompose the problem into a series of pairwise ones and this makes our algorithm scalable to a large number of objects. Objects are segmented in pixel level with higher-order soft constraints from superpixels, by a dual-level conditional random field. The model is optimized alternately by object layout and pixel-wise segmentation. V^e evaluate our system on different objects, i.e., clothing and pedestrian, and show impressive segmentation results and significant improvement over state-of-the-art segmentation algorithms.In this paper we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophis- ticated shape priors with the consideration of blocking relationship between nearby objects. Different from conventional layered model which attempts to solve the full ordering problem, we decompose the problem into a series of pairwise ones and this makes our algorithm scalable to a large number of objects. Objects are segmented in pixel level with higher-order soft constraints from superpixels, by a dual-level conditional random field. The model is optimized alternately by object layout and pixel-wise segmentation. V^e evaluate our system on different objects, i.e., clothing and pedestrian, and show impressive segmentation results and significant improvement over state-of-the-art segmentation algorithms.

关 键 词：object segmentation occlusion reasoning object graph conditional random field random forest 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]