Motion detection using Horn-Schunck optical flow

• Main Authors: Wan Nur Azhani, W. Samsudin, Kamarul Hawari, Ghazali
• Format: Conference or Workshop Item
• Language: English
• Published: Springer, Berlin, Heidelberg 2012
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/26650/1/Motion%20detection%20using%20Horn-Schunck%20optical%20flow.pdf; http://umpir.ump.edu.my/id/eprint/26650/; https://doi.org/10.1007/978-3-642-35594-3_29
• Institution: Universiti Malaysia Pahang Al-Sultan Abdullah

This system is design to detect motion in a crowd using one of the optical flow algorithms, Horn-Schunck method. By performing some appropriate feature extraction techniques, this system allows us to achieve better results in detecting motion and determining the velocity of that motion in order to analyze the human behaviour based on its velocities. This research works able to help human observer to monitor video recorded by closed-circuit television systems (CCTVs) attached in the region of interest (ROI) area.