Geodesic Distance Histogram Feature for Video Segmentation

31 Mar 2017  ·  Hieu Le, Vu Nguyen, Chen-Ping Yu, Dimitris Samaras ·

This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms. The feature is a joint histogram of intensity and geodesic distances, where the geodesic distances are computed as the shortest paths between superpixels via their boundaries. We also incorporate adaptive voting weights and spatial pyramid configurations to include spatial information into the geodesic histogram feature and show that this further improves results. The feature is generic and can be used as part of various algorithms. In experiments, we test the geodesic histogram feature by incorporating it into two existing video segmentation frameworks. This leads to significantly better performance in 3D video segmentation benchmarks on two datasets.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Segmentation SegTrack v2 GDHF Accuracy 86.86 # 1

Methods


No methods listed for this paper. Add relevant methods here