Video Action Classification: A New Approach Combining Spatio-temporal Krawtchouk Moments and Laplacian Eigenmaps

Action classification and recognition is a challenging research area that has significant applications in computer vision domain including robotics, video surveillance, human-computer interaction and multimedia retrieval. Action classification domain uses a large variety of approaches. This paper proposes a new approach for video actions classification based on extension of Krawtchouk moments in spatio-temporal domain. In fact, Krawtchouk moments have interesting properties for describing structural and temporal information of a time varying video sequence. The proposed approach is composed of three main steps. First, the original video is transformed into a spatiotemporal volume of images. Then, silhouettes of human in movement are extracted from these images to define a 3D shape. In the third step, higher order spatio-temporal Krawtchouk moments are applied to the obtained 3D shapes and Laplacian eigenmaps is used to achieve dimension reduction for different moments vectors. Finally, we use SVM algorithm and computed descriptors to classify actions in videos. This new approach has been validated on the two video datasets Weizmann and KTH. Experimental results show a good classification rate compared to other approaches using different descriptors.