A surveillance system based on motion detection and motion estimation using optical flow

In today's world Surveillance system is playing an important role in the field of security. Moving object detection has been widely used in video surveillance system. As well as motion estimation is an important part of surveillance video processing such as video filtering and compression from video frames. This paper proposes a simple and efficient surveillance system based on motion detection with motion vector estimation from surveillance video frames. Motion is detected with a new approach-edge region determination which makes detection faster. The surveillance video is then processed for motion estimation using optical flow with Horn-Schunck algorithm for estimating motion vector for its reasonable performance and simplicity. This method is computationally faster without requiring any special hardware for image processing. So it can be more applicable to embedded systems.

[1]  Dileep Kumar Yadav,et al.  Efficient method for moving object detection in cluttered background using Gaussian Mixture Model , 2014, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[2]  Dileep Kumar Yadav,et al.  Moving object detection in real-time visual surveillance using background subtraction technique , 2014, 2014 14th International Conference on Hybrid Intelligent Systems.

[3]  Jenq-Neng Hwang,et al.  Fast and automatic video object segmentation and tracking for content-based applications , 2002, IEEE Trans. Circuits Syst. Video Technol..

[4]  Md. Hazrat Ali,et al.  Motion Detection Techniques Using Optical Flow , 2009 .

[5]  Patrick Bouthemy,et al.  Optical flow modeling and computation: A survey , 2015, Comput. Vis. Image Underst..

[6]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[7]  Jian Ding,et al.  Object Tracking and Detecting Based on Adaptive Background Subtraction , 2012 .