Submodular Function Optimization for Motion Clustering and Image Segmentation

doi:10.1109/TNNLS.2018.2885591

Submodular Function Optimization for Motion Clustering and Image Segmentation

2019-09-01

49

PRE

AI

沈

沈建冰 (Jianbing Shen) *

DOI：10.1109/TNNLS.2018.2885591

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose a framework of maximizing quadratic submodular energy with a knapsack constraint approximately, to solve certain computer vision problems. The proposed submodular maximization problem can be viewed as a generalization of the classic 0/1 knapsack problem. Importantly, maximization of our knapsack constrained submodular energy function can be solved via dynamic programing. We further introduce a range-reduction step prior to dynamic programing as a two-stage procedure for more efficient maximization. In order to demonstrate the effectiveness of the proposed energy function and its maximization algorithm, we apply it to two representative computer vision tasks: image segmentation and motion trajectory clustering. Experimental results of image segmentation demonstrate that our method outperforms the classic segmentation algorithms of graph cuts and random walks. Moreover, our framework achieves better performance than state-of-the-art methods on the motion trajectory clustering task.

Keywords:

Knapsack constraint

segmentation

submodular maximization

trajectory clustering

Submodular Function Optimization for Motion Clustering and Image Segmentation

Abstract

AI Summary

Journal

Organization