Wavelet mach filter for omnidirectional human activity recognition
Tyzzkae Ang, Alan Wee-Chiat Tan, Chu Kiong Loo, Wai Kit Wong · Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University) · 2012
Abstract. Action recognition is important in the field of intelligent security and surveil-lance. However, most surveillance cameras can only capture in one direction with limited viewing angle. This paper proposes an edge enhancement template-based method of om-nidirectional action recognition that is able to detect specific actions at a 360 degree of view. A MACH filter captures intra-class variability by synthesizing a single action MACH filter for a given action class. The proposed method, based on the wavelet MACH filter, provides additional flexibility of an adaptive choice of wavelet scale factors and, in doing so, enables the selection of the size and orientation of the smoothing function in edge enhancement to optimize the performance of the MACH filter. Moreover, the use of wavelet transform improves the performance of the MACH filter by enhancing the cross-correlation peak intensity in the recognition process. The unwarping of an omnidi-rectional image into a panoramic image further enables action recognition in 360 degree wide angle of view.