caa a22 4500 605446997 CHVBK 20210128100130.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s11042-014-2083-2 doi (NATIONALLICENCE)springer-10.1007/s11042-014-2083-2 Compressed domain human action recognition in H.264/AVC video streams [Elektronische Daten] [Manu Tom, R. Babu, R Praveen] 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 the proposed 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 result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed ( > 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms. Springer Science+Business Media New York, 2014 H.264/AVC nationallicence Human action recognition nationallicence Compressed domain video analysis nationallicence Motion vectors nationallicence Quantization parameters nationallicence Tom Manu Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut Babu R. Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut Praveen R. Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9323-9338 1380-7501 74:21<9323 2015 74 11042 https://doi.org/10.1007/s11042-014-2083-2 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-2083-2 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Tom Manu Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut NATIONALLICENCE 700 1- Babu R. Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut NATIONALLICENCE 700 1- Praveen R. Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9323-9338 1380-7501 74:21<9323 2015 74 11042