Submodular Function Optimization for Motion Clustering and Image Segmentation

Jianbing Shen, Xingping Dong, Jianteng Peng, Xiaogang Jin, Ling Shao, Fatih Porikli

    Research output: Contribution to journalArticlepeer-review

    48 Citations (Scopus)

    Abstract

    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.

    Original languageEnglish
    Pages (from-to)2637-2649
    Number of pages13
    JournalIEEE Transactions on Neural Networks and Learning Systems
    Volume30
    Issue number9
    DOIs
    Publication statusPublished - 1 Sept 2019

    Fingerprint

    Dive into the research topics of 'Submodular Function Optimization for Motion Clustering and Image Segmentation'. Together they form a unique fingerprint.

    Cite this