Object Detection From Videos Captured by Moving Camera by Fuzzy Edge Incorporated Markov Random Field and Local Histogram Matching

被引:37
作者
Ghosh, Ashish [1 ]
Subudhi, Badri Narayan [1 ]
Ghosh, Susmita [2 ]
机构
[1] Indian Stat Inst, Machine Intelligence Unit, Kolkata 700108, India
[2] Jadavpur Univ, Dept Comp Sci & Engn, Kolkata 700032, India
关键词
Edge analysis; fuzzy sets; image segmentation; maximum a posteriori probability estimation; motion analysis; IMAGE SEGMENTATION; RECOGNITION; TRACKING; MODEL;
D O I
10.1109/TCSVT.2012.2190476
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we put forward a novel region matching-based motion estimation scheme to detect objects with accurate boundaries from videos captured by moving camera. Here, a fuzzy edge incorporated Markov random field (MRF) model is considered for spatial segmentation. The algorithm is able to identify even the blurred boundaries of objects in a scene. Expectation Maximization algorithm is used to estimate the MRF model parameters. To reduce the complexity of searching, a new scheme is proposed to get a rough idea of maximum possible shift of objects from one frame to another by finding the amount of shift in positions of the centroid. We propose a chi(2)-test-based local histogram matching scheme for detecting moving objects from complex scenes from low illumination environment and objects that change size from one frame to another. The proposed scheme is successfully applied for detecting moving objects from video sequences captured in both real-life and controlled environments. It is also noticed that the proposed scheme provides better results with less object background misclassification as compared to existing techniques.
引用
收藏
页码:1127 / 1135
页数:9
相关论文
共 28 条
[11]   Unsupervised video object segmentation and tracking based on new edge features [J].
Kim, BG ;
Park, DJ .
PATTERN RECOGNITION LETTERS, 2004, 25 (15) :1731-1742
[12]   Automatic extraction of moving objects for head-shoulder video sequence [J].
Kuo, CM ;
Hsieh, CH ;
Huang, YR .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2005, 16 (01) :68-92
[13]   Automatic image segmentation for concealed object detection using the expectation-maximization algorithm [J].
Lee, Dong-Su ;
Yeom, Seokwon ;
Son, Jung-Young ;
Kim, Shin-Hwan .
OPTICS EXPRESS, 2010, 18 (10) :10659-10667
[14]  
Li Stan Z., 2001, COMP SCI W, P165
[15]   Activity recognition using a combination of category components and local models for video surveillance [J].
Lin, Welyao ;
Sun, Ming-Ting ;
Poovendran, Radha ;
Zhang, Zhengyou .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2008, 18 (08) :1128-1139
[16]  
Lucas B., 1981, Proc. DARPA Image Understanding Workshop, P121
[17]   ON EDGE-DETECTION OF X-RAY IMAGES USING FUZZY-SETS [J].
PAL, SK ;
KING, RA .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1983, 5 (01) :69-77
[18]   Geodesic active contours and level sets for the detection and tracking of moving objects [J].
Paragios, N ;
Deriche, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (03) :266-280
[19]   SOME GENERALIZED ORDER-DISORDER TRANSFORMATIONS [J].
POTTS, RB .
PROCEEDINGS OF THE CAMBRIDGE PHILOSOPHICAL SOCIETY, 1952, 48 (01) :106-109
[20]   Robust Video Surveillance for Fall Detection Based on Human Shape Deformation [J].
Rougier, Caroline ;
Meunier, Jean ;
St-Arnaud, Alain ;
Rousseau, Jacqueline .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2011, 21 (05) :611-622