_____________________________________________________________________________________________________ *Corresponding author: E-mail: shahadatku10@outlook.com, aslam.ku11@gmail.com, mrislam_66@yahoo.com; British Journal of Applied Science & Technology 19(6): 1-12, 2017; Article no.BJAST.31153 ISSN: 2231-0843, NLM ID: 101664541 SCIENCEDOMAIN international www.sciencedomain.org Human Motion Analysis from Depth Video Sequences Using Multi-scale and Multi-directional Features Md. Saifuddin Tarafder 1 , Md. Shahadat Hossain 1* and Md. Rafiqul Islam 1* 1 Mathematics Discipline, Science Engineering and Technology School, Khulna University, Khulna-9208, Bangladesh. Authors’ contributions This work was carried out in collaboration between all authors. Author MST designed the study, performed the statistical analysis, wrote the protocol, and wrote the first draft of the manuscript. Author MSH managed the analyses of the study and managed the literature searches. Author MRI gave some logistic supports. All authors read and approved the final manuscript. Article Information DOI: 10.9734/BJAST/2017/31153 Editor(s): (1) Vitaly Kober, Department of Computer Science, CICESE, Mexico. Reviewers: (1) Zhao Hong, Lanzhou University of Technology, China. (2) Radosław Jedynak, Kazimierz Pulaski University of Technology and Humanities, Poland. (3) Pawan Kumar Singh, Jadavpur University, Kolkata, India. Complete Peer review History: http://www.sciencedomain.org/review-history/18461 Received 23 rd December 2016 Accepted 5 th March 2017 Published 1 st April 2017 ABSTRACT The emerging cost-effective depth sensors have made easier the action recognition task significantly. In this paper, we propose an effective method to analysis human actions from depth video sequences based on multi-scaling and multi-directional transformation which provide additional body shape and motion information for action recognition. In our method, corresponding to the front, side and top projection views, we generate three Depth Motion Maps (DMMs) over the entire video sequences. More specially, the multi-scaling and multi-directional transformations are implemented on the generated DMMs of a depth video sequence. Finally, the concatenation of these features is used as a feature descriptor for the depth video sequence. With this new feature descriptor, the l 2 -regularized collaborative representation classifier (l 2 - CRC) is utilized to recognize Original Research Article