Title :
An Evolutionary Based Slow and Fast Moving Video Object Detection Scheme Using Compound Markov Random Field Model
Author :
Subudhi, Badri Narayan ; Nanda, Pradipta Kumar
Author_Institution :
Dept. of Electr. Eng., Nat. Inst. of Technol., Rourkela
Abstract :
We propose an evolving scheme to detect slow as well as fast moving objects in a video sequence. The proposed scheme employ both spatio-temporal and temporal segmentation to obtain the video object plane and hence detection. We propose a compound Markov random field model as the a priori image model that takes into account the spatial distribution of the current frame, temporal frames and the edge maps of the temporal frames. The spatio-temporal segmentation is cast as a pixel labeling problem and the labels are the MAP estimates. The MAP estimates of a frame are obtained by a hybrid algorithm. The spatial segmentation of a given frame evolves to generate the spatial segmentation of the subsequent frames. The evolved spatial segmentation together with the temporal segmentation produces the Video Object Plane (VOP) and hence detection. Our scheme does require the computation of spatio-temporal segmentation of the initial frame thus speeding up the whole process. The results of the proposed scheme are compared with JSEG method are found to be better in terms of the misclassification error.
Keywords :
Markov processes; evolutionary computation; image motion analysis; image resolution; image segmentation; image sequences; maximum likelihood estimation; object detection; video signal processing; MAP estimates; a priori image model; compound Markov random field model; moving video object detection; pixel labeling problem; spatio-temporal segmentation; temporal segmentation; video object plane; video sequence; Computer graphics; Computer vision; Context modeling; Dissolved gas analysis; Genetic algorithms; Image segmentation; Markov random fields; Object detection; Stochastic processes; Video sequences; Covariance matrices; Feature extraction; Gaussian distribution; Gaussian process; Image edge analysis; Image segmentation; MAP Estimation; Modeling; Simulated Annealing; pattern recognition;
Conference_Titel :
Computer Vision, Graphics & Image Processing, 2008. ICVGIP '08. Sixth Indian Conference on
Conference_Location :
Bhubaneswar
Print_ISBN :
978-0-7695-3476-3
Electronic_ISBN :
978-0-7695-3476-3
DOI :
10.1109/ICVGIP.2008.38