Video Anomaly Detection using Kalman Based Support Vector Technique

Abstract

Abstract

The digital video processing technology has boomed since last many years. The video processing is done using sum of absolute differences and with the image processing block set. We first calculate motion vectors between successive frames and use them to reduce redundant information. The method uses optical flow algorithm to calculate changes in the intensity of the pixels of the images. Median filtering is used for background extraction which is later subtracted from the motion frames for object detection. The distance traveled by the vehicle is calculated using the movement of the centroid over the frames. In this study, we perform object tracking for real time video which detects the motion by using Kalman based support vector machine (KBSVM). First we have taken an object as reference object or image then the next successive object is compared with this reference object or image establishing, Kalman filter motion model which performs the feature extraction and finds out the position of moving objects. Each time the successive object is compared with the reference object, an absolute difference is obtained, then the summation of all these differences gives the sum of absolute difference and calculates pixel value with respect to frame index using MATLAB 2014Ra.

 Keyword: Object tracking, SVM, Gabor optical flow, Median filter, Kalman filter

Cite this Article

Neetu Gupta, Munish Vashishath, Rajiv Kapoor. Video Anomaly Detection using Kalman Based Support Vector Technique. Current Trends in Signal Processing. 2018; 8(2): 4–11p.