Motion feature descriptor based moving objects segmentation
Motion feature descriptor based moving objects segmentation
摘要
A novel moving objects segmentation method is proposed in this paper. A modified three dimensional recursive search （3DRS） algorithm is used in order to obtain motion information accurately. A motion feature descriptor （MFD） is designed to describe motion feature of each block in a picture based on motion intensity, motion in occlusion areas, and motion correlation among neighbouring blocks. Then, a fuzzy C-means clustering algorithm （FCM） is implemented based on those MFDs so as to segment moving objects. Moreover, a new parameter named as gathering degree is used to distinguish foreground moving objects and background motion. Experimental results demonstrate the effectiveness of the proposed method.
基金
Supported by the National Natural Science Foundation of China （No. 60772134, 60902081, 60902052）
the 111 Project （No.B08038）
the Fundamental Research Funds for the Central Universities（No.72105457）.
参考文献14
-
1ITU Telecom Standardization Sector of 1TU. Advanced Video Coding for Generic Audiovisual Services, ITU-T Recommendation H.264 and ISO/IEC 14496-10 AVC Standard. Geneva: ITU-T Publishers, 2009. 1-670.
-
2Bruyne S, Poppe C, Verstockt S, et al. Estimating motion reliability to improve moving object detection in the H.264/AVC domain. In: Proceedings of IEEE International Conference onMultimedia & Expo (ICME), New York City, USA, 2009. 330- 333.
-
3Niu C F, Liu Y S Moving object segmentation based on video coding information in H.264 compressed domain. In: Proceedings of International Conference on Advanced Computer Theory and Engineering (ICACTE), Cairo, Egypt, 2009. 517-525.
-
4Kas C, Nicolas H. H.264/SVC scene motion analysis. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taiwan, China, 2009. 957-960.
-
5Xu H F, Younis A A, Kabuka M R. Automatic moving object extraction for content-based applications. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14 (6): 796- 812.
-
6Feghali R. Multi-frame simultaneous motion estimation and segmentation. IEEE Transactions on Consumer Electronics, 2005, 15(1): 245-248.
-
7Kulic D, Takano W, Nakamura Y. Online segmentation and clustering f-om continuous observation of whole body motions. IEEE Trans actions on Robotics, 2009, 25(5): 1158-1166.
-
8Denman S, Fookes C, Sridharan S. Improved simultaneous computation of motion detection and optical flow for object tracking. In: Proceedings of Digital Image Computing: Techniques and Applications (DICTA), Melbourne, Australia, 2009. 175-182.
-
9Bars A G, Pitas I. Optical flow estimation and moving object segmentation based on median radial basis function network. IEEE Transactions on Image Processing, 1998, 7(5): 693-702.
-
10Murali S, Girisha R. Segmentation of motion objects from surveillance video sequences using temporal differencing combined with multiple correlation. In: Proceedings of IEEE Advanced Video and Signal Based Surveillance (AVSS), Genoa, Italy. 2009. 472-478.
-
1朱云芳,应潇潇,顾伟康.基于时空结合的运动物体分割[J].浙江大学学报（理学版）,2007,34(6):636-639. 被引量：2
-
2张美敦.模场直径[J].光通信,2003(3):67-67.
-
3〈2013年双核处理器产品将占据整个中国平板电脑市场60％～70％的份额〉[J].EDN CHINA 电子技术设计,2013(3):61-62.
-
4邓宇,李华.多特征组合和图切割支持的物体/背景分割方法[J].计算机研究与发展,2008,45(10):1724-1730. 被引量：7
-
5林延东,李平,李熙.连续变孔径法单模光纤模场直径(MFD)测量的数据处理[J].现代计量测试,1999,7(5):29-31. 被引量：1
-
6翟素兰,汤进,罗斌.一种基于结构张量的运动物体分割方法[J].计算机工程与应用,2008,44(7):54-56.
-
7LG电子与英特尔合作开发未来的MID（移动互联网设备）[J].电子与电脑,2009,9(3):105-105.
-
8李国成,梁桂香.单模光纤连接损耗研究[J].光通信技术,1992,16(3):216-219. 被引量：1
-
9谢毅.单模色散位移光纤的高斯近似理论[J].通信学报,1997,18(10):26-30.
-
10辅孔光纤中的光纤熔融现象[J].光纤光缆传输技术,2012(4):6-8.
