Human action recognition employing negative space features

We proposed a region based method to recognize human actions from video sequences. Unlike other region based methods, it works with the surrounding regions of the human silhouette termed as negative space. This paper further extends the idea of negative space to cope with the changes in viewpoints. It also addresses the problem of long shadows which is one of the major challenges of human action recognition. Some systems attempt suppressing shadows during the segmentation process but our system takes input of segmented binary images of which the shadow is not suppressed. This makes our system less dependent on segmentation process. Further, this approach can complement the positive space (silhouette) based methods to boost recognition. The system consists of a hierarchical processing: histogram analysis on segmented input image, followed by motion and shape feature extraction, pose sequence analysis by employing Dynamic Time Warping and at last classification by Nearest Neighbor classifier. We evaluated our system by most commonly used datasets and achieved higher accuracy than the state of the arts methods. Our system can also retrieve video sequences from queries of human action sequences.

► Extracted features from negative space to describe human poses.
► Addresses the problem of long shadow and can recognize human actions effectively in presence of long shadow.
► The system can query for complex human activity in a single video.
► The accuracy of the system is higher than the state of the arts methods for common datasets.
► The system is robust to viewpoint change, different clothing, shadow and partial occlusion.