An Improved Recurrent Motion Image Framework for Outdoor Objects Recognition
Chuan Ern Wong, Teong Joo Ong · 2009
In this paper, we present an extension to the Recurrent Motion Image (RMI) motion-based object recognition framework for use in development of automated video surveillance systems. We extended the original object classes of RMI to include four-legged animals (such as dog and cat). Various enhancements are made to the object detection and classification algorithms for better object segmentation, error tolerance and wider range of recognition. Under the new framework, object blobs obtained from background subtraction of scenes are tracked using region correspondence. In turn, we calculate the RMI signatures based on the silhouettes of the object blobs for proper classification. This new framework is tested on several real world 320 x 240 resolution color image sequences captured with a low-end digital camera, and also on the PETS 2001 dataset. A recognition rate of approximately 98 percent (39 out of 40 moving objects in the experiments were correctly classified) was achieved, indicating the applicability of the new framework in similar task environment.