• 更多栏目

    戚金清

    • 副教授       硕士生导师
    • 性别:男
    • 毕业院校:东京工业大学
    • 学位:博士
    • 所在单位:信息与通信工程学院
    • 学科:通信与信息系统. 信号与信息处理
    • 电子邮箱:jinqing@dlut.edu.cn

    访问量:

    开通时间:..

    最后更新时间:..

    Co-Bootstrapping Saliency

    点击次数:

    论文类型:期刊论文

    第一作者:Lu, Huchuan

    通讯作者:Lu, HC (reprint author), Dalian Univ Technol, Sch Informat & Commun Engn, Fac Elect Informat & Elect Engn, Dalian 116024, Peoples R China.

    合写作者:Zhang, Xiaoning,Qi, Jinqing,Tong, Na,Ruan, Xiang,Yang, Ming-Hsuan

    发表时间:2017-01-01

    发表刊物:IEEE TRANSACTIONS ON IMAGE PROCESSING

    收录刊物:SCIE、EI

    卷号:26

    期号:1

    页面范围:414-425

    ISSN号:1057-7149

    关键字:Saliency detection; weak saliency model; strong saliency model; co-bootstrapping

    摘要:In this paper, we propose a visual saliency detection algorithm to explore the fusion of various saliency models in a manner of bootstrap learning. First, an original bootstrapping model, which combines both weak and strong saliency models, is constructed. In this model, image priors are exploited to generate an original weak saliency model, which provides training samples for a strong model. Then, a strong classifier is learned based on the samples extracted from the weak model. We use this classifier to classify all the salient and non-salient superpixels in an input image. To further improve the detection performance, multi-scale saliency maps of weak and strong model are integrated, respectively. The final result is the combination of the weak and strong saliency maps. The original model indicates that the overall performance of the proposed algorithm is largely affected by the quality of weak saliency model. Therefore, we propose a co-bootstrapping mechanism, which integrates the advantages of different saliency methods to construct the weak saliency model thus addresses the problem and achieves a better performance. Extensive experiments on benchmark data sets demonstrate that the proposed algorithm outperforms the stateof- the-art methods.