计算机应用 ›› 2016, Vol. 36 ›› Issue (8): 2306-2310.DOI: 10.11772/j.issn.1001-9081.2016.08.2306

• 虚拟现实与数字媒体 • 上一篇    下一篇

多信息动态融合的运动目标检测方法

何伟1,2, 齐琦1,2, 张国云1,2, 吴健辉1,2   

  1. 1. 湖南理工学院 信息与通信工程学院, 湖南 岳阳 414006;
    2. 湖南理工学院 复杂系统优化与控制湖南省普通高等学校重点实验室, 湖南 岳阳 414006
  • 收稿日期:2016-01-25 修回日期:2016-03-05 出版日期:2016-08-10 发布日期:2016-08-10
  • 通讯作者: 齐琦
  • 作者简介:何伟(1983-),男,湖南岳阳人,讲师,硕士,CCF会员,主要研究方向:数字图像处理、机器视觉;齐琦(1983-),女,山西忻州人,讲师,硕士,主要研究方向:数字图像处理、模式识别;张国云(1971-),男,湖南郴州人,教授,博士,主要研究方向:数字图像处理、模式识别;吴健辉(1977-),男,湖南娄底人,副教授,博士,主要研究方向:图像信息处理。
  • 基金资助:
    国家自然科学基金资助项目(61201435,61473118);湖南省教育厅开放基金资助项目(15K051);湖南省高校科技创新团队支持计划资助项目(湘教通[2012]318号)。

Moving object detection method based on multi-information dynamic fusion

HE Wei1,2, QI Qi1,2, ZHANG Guoyun1,2, WU Jianhui1,2   

  1. 1. School of Information and Communication Engineering, Hunan Institute of Science and Technology, Yueyang Hunan 414006, China;
    2. Key Laboratory of Optimization and Control for Complex Systems, Hunan Institute of Science and Technology, Yueyang Hunan 414006, China
  • Received:2016-01-25 Revised:2016-03-05 Online:2016-08-10 Published:2016-08-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61201435, 61473118), the Open Fund Project in Provincial Education Department of Hunan (15K051), the Aid Program for Science and Technology Innovative Research Team in Higher Educational Institutions of Hunan Province ([2012] 318).

摘要: 针对基于视觉显著性的运动目标检测算法存在时空信息简单融合及忽略运动信息的问题,提出一种动态融合视觉显著性信息和运动信息的运动目标检测方法。该方法首先计算每个像素的局部显著度和全局显著度,并通过贝叶斯准则生成空间显著图;然后,利用结构随机森林算法预测运动边界,生成运动边界图;其次,根据空间显著图和运动边界图属性的变化,动态确定最佳融合权值;最后,根据动态融合权值计算并标记运动目标。该方法既发挥了显著性算法和运动边界算法的优势,又克服了各自的不足,与传统背景差分法和三帧差分法相比,检出率和误检率的最大优化幅度超过40%。实验结果表明,该方法能够准确、完整地检测出运动目标,提升了对场景的适应性。

关键词: 运动目标检测, 视觉显著性, 结构随机森林, 运动边界, 动态融合

Abstract: Aiming at the problems of simple fusion of spatio-temporal information and ignoring moving information in moving object detection based on visual saliency, a moving object detection method based on the dynamic fusion of visual saliency and moving information was proposed. Firstly, local and global saliencies of each pixel was computed by spatial characters extracted from an image, then the spatial salient map was calculated combining those saliencies by Bayesian criteria. Secondly, with the help of structured random forest, the motion boundaries were predicted to primarily orientate the moving objects, by which the motion boundary map was built. Then, according to the change of the spatial salient and motion boundary maps, the optimal fusion weights were determined dynamically. Finally, moving objects were calculated and marked by the dynamic fusion weights. The proposed approach not only inherits the advantages of saliency algorithm and moving boundary algorithm, but also overcomes their disadvantages. In the comparison experiments with the traditional background subtraction method and three-frame difference method, the detection rate and the false alarm rate of the proposed approach are improved at most more than 40%. Experimental results show that the proposed method can detect moving objects accurately and completely, and the adaptation to scene is promoted.

Key words: moving object detection, visual saliency, structured random forest, motion boundary, dynamic fusion

中图分类号: