期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 2, 页码 743-757出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3066675
关键词
Object detection; Heuristic algorithms; Dynamics; Adaptation models; Video sequences; Interference; Robustness; Multi-scale moving objects detection; spatio-temporal online detection; exponential power distributions; low-rank matrix factorization
资金
- National Key Research and Development Program [2018XXX08241041]
- National Natural Science Foundation of China [61976179]
- Fundamental Research Funds for the Central Universities [3102019HTXM005, 3102017HQZZ003]
- Key Industrial Innovation Chain Project in Industrial Domain of Key Research and Development Program of Shaanxi Province [2018ZDCXLGY030203]
In this paper, a novel spatio-temporal online matrix factorization (STOMF) method is proposed to detect multi-scale moving objects under dynamic background. The method combines exponential power distribution and low-rank matrix factorization framework, and introduces temporal difference motion prior model and partial spatial motion information post-processing method to improve detection performance.
Detecting moving objects from the video sequences has been treated as a challenging computer vision task, since the problems of dynamic background, multi-scale moving objects and various noise interference impact the corresponding feasibility and efficiency. In this paper, a novel spatio-temporal online matrix factorization (STOMF) method is proposed to detect multi-scale moving objects under dynamic background. To accommodate a wide range of the real noise distractions, we apply a specific mixture of exponential power (MoEP) distributions to the framework of low-rank matrix factorization (LRMF). For the optimization of solution algorithm, a temporal difference motion prior (TDMP) model is proposed, which estimates the motion matrix and calculates the weight matrix. Moreover, a partial spatial motion information (PSMI) post-processing method is further designed to implement multi-scale objects extraction in varieties of complex dynamic scenes, which utilizes partial background and motion information. The superiority of the STOMF method is validated by massive experiments on practical datasets, as compared with state-of-the-art moving objects detection approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据