Multi-class Semantic Video Segmentation with Exemplar-Based Object Reasoning

Buyu Liu, Xuming He, Stephen Gould
2015 2015 IEEE Winter Conference on Applications of Computer Vision  
We tackle the problem of semantic segmentation of dynamic scene in video sequences. We propose to incorporate foreground object information into pixel labeling by jointly reasoning semantic labels of super-voxels, object instance tracks and geometric relations between objects. We take an exemplar approach to object modeling by using a small set of object annotations and exploring the temporal consistency of object motion. After generating a set of moving object hypotheses, we design a CRF
more » ... ork that jointly models the supervoxel and object instances. The optimal semantic labeling is inferred by the MAP estimation of the model, which is solved by a single move-making based optimization procedure. We demonstrate the effectiveness of our method on three public datasets and show that our model can achieve superior or comparable results than the stateof-the-art with less object-level supervision.
doi:10.1109/wacv.2015.140 dblp:conf/wacv/LiuHG15 fatcat:pumpr6xq3ndxrc4nx4rqmwf6pe