animal tracking using background subtraction on multi threshold segmentation
D.Vaishnav,M.Vijaymurugan,S.Prakash
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:4 Issue:3 Year: 05 April,2016 Pages:931-939
Abstract
The proposed project performs motion detection and animal tracking based on background subtraction using multi threshold approach with mathematical morphology. Here the techniques frame differences , multi threshold based detection will be used. Along with this multi threshold, mathematical morphology also used which has an ability to attenuate color variations produced by background motions which will highlight moving objects. After the object foreground detection, the parameters like animal or human will be detected. The data which has been processed from the above process until segmentation on objects will be taken as a data for patterns matching and will be stored in the data base for further use .So when an input video is processed with the help of the above process methods it reaches to the classifier step. In this step data will be retrieved from the data base which has been already retrieved from the above process and has been stored in it and then could be used for classification of the data with the input video for obtaining the perfect output of the system. The object is tracked by comparing the mean value obtained from input video with already stored mean value in the data template. The classification part is carried out with the help of the SVM classifier which is nothing but Support Vector Machine. When the classifier classifies and finds that its target is achieved it immediately sends the signal to the output ports which immediately creates an alert to the user using the machine. Hence when the output port gets the trigger signal from the classifier the first output port which is assigned with a buzzer which creates an alarm sound and followed by the second output port which displays a warning message at the screen of the main server so immediately when the user gets an alert he could immediately response to it even if he is not present at that spot.
Kewords
SVM classifier
Reference
1. A. Yilmaz, O. Javed, and M. Shah, “Object tracking: A survey,” ACM Comput. Surv., vol. 38, Dec. 2006. 2. C.Wren, A. Azarbayejani, T. Darrell, and A. Pentland, “Pfinder: Realtime tracking of the animal body,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 19, no. 7, pp. 780,785, Jul. 1997. 3. C. Stauffer and W. Grimson, “Adaptive background mixture models for real-time tracking,” in IEEE Comput. Soc. Conf. CVPR, 1999, pp. 246,252. 4. I. Haritaoglu, D. Harwood, and L. Davis, “W4: Real-time surveillance of animal and their activities,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 22, no. 8, pp. 809,830, Aug. 2000.
