Rapid human action recognition in H.264/AVC compressed domain for video surveillance

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

1. INTRODUCTION

Human action recognition has been an area of keen interest to Computer Vision researchers for the past few decades. Day by day, length and breadth of the problem statement is expanding and researchers have come up with solutions to tackle scale, appearance, illumination, orientation variations, and occlusions. Speed of recognition has not been given ample thrust in the evaluations. The sole aim of our research is to take action recognition to a new dimension, where recognition rate is also considered a benchmark evaluation criteria.