PERANCANGAN DAN PEMBUATAN APLIKASI TRACKING OBJECT PADA VIDEO DENGAN METODE KERNEL - BASED

Wilson -(1*), Liliana -(2), Kartika Gunadi(3),


(1) Universitas Kristen Petra
(2) Universitas Kristen Petra
(3) Universitas Kristen Petra
(*) Corresponding Author

Abstract


Utilization as a surveillance camera (CCTV) still has many weaknesses. The camera just record it, so it still takes control of guard constantly. With these limitations it needed an additional capability to boost surveillance cameras work. One of the additional capabilities that can be used is the motion detection which helps signal the event of unusual movements were caught on camera.

Detection of object motion can be used to capture movements recorded from a CCTV. Detection process starts by reading each video frame, from frame - frame segmentation process will be carried out so that objects that are obtained from the video. After that, the object - the object stored will be processed using the kernel method - based on detecting movement going from object - the object.

The end result is a software application that can signal the moving objects from the video. The software was tested with some video with different conditions - different. If the object in the video is too big or too small tracking process will be inaccurate.

Keywords


Motion Detection, Motion Tracking, Kernel – Based, Bhattacharyya, Mean – shift.

Full Text:

PDF

References


Baviskar, S.P., Ujgare, N,S. (2010). Kernel Based Object Tracking Using Means Shift Method, Prentice Hall Horngren, Charles T., Foster, George. (1994).

Comaniciu, D., Ramesh, V., Meer, P. (2003). Kernel – Based Object Tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence Volume 25, no.5, May 2003

Dedeoglu, Y. (2004). Moving Object Detection, Tracking and Classification for Smart Video Surveillance, Dept. Of Computer Engineering, Bilkent University

Hudson, F., Thacker, N., Rockett, P. (1998).The Bhattacharyya Metric as an Absolute Similiarity Measure for Frequency Coded Data, Versailles, France

Kadarla, S.K. (2009). Object Tracking in Video Image Based On Image Segmentation and Pattern Matching, Dept. Of Electrical Engineering,Rourkela

Liu R., Jing Z. (2011). Robust kernel – based tracking algortihm with background contrasting, School of Aeronautics and Astronautics, Jiao Tong University, Shanghai


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :