Human Motion Analysis from Depth Video Sequences Using Multi-scale and Multi-directional Features

Journal Title: Current Journal of Applied Science and Technology - Year 2017, Vol 19, Issue 6

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 l2-regularized collaborative representation classifier (l2- CRC) is utilized to recognize human actions. The recognition results of Microsoft Research (MSR) Action3D dataset show that our method significantly outperforms than the other existing methods, although our representation is much more compact.

Authors and Affiliations

Md. Saifuddin Tarafder, Md. Shahadat Hossain, Md. Rafiqul Islam

Keywords

Related Articles

A Study on Knowledge and Adoption Level of Improved Animal Husbandry Practices by Farm Women of Haryana

The study was conducted in kurukshetra district of Haryana to assess the extent of knowledge and adoption level of farm women for improved animal husbandry practices. Four villages were selected at random from randomly s...

Effect of Nusselt Number Dependence on Reynolds Number in Solar Air Heaters of Varying Constructal Rib Geometries

The most serious challenge in solar air heater is that the thermal performance is generally poor due to low heat transfer coefficient between the absorber plate and air flowing in the channel. Thermal performance in sola...

Spatial Epidemiology of Road Traffic Crashes and Mortality in Nigeria, 2007-2015

Background: Road traffic accidents (RTA) are an important public health problem with considerable morbidity, mortality and disability especially in low income countries. Spatial analysis tool has been used in the study o...

Effect of Extrusion Processing Variables on Finger Millet Flours with Respect to Their Functional Properties Using Response Surface Methodology

Finger millet is fiber rich nutritious food which can be used by diabetic patients and also by healthy persons to maintain body weight owing to their inherent good amount of resistant starch and dietary fiber. Various de...

Design and Development of Power Operated Rotary Weeder for Rice

Weeds are serious problem in all crops but they are even more so in “kharif” crops. For weed problem several study and research work has carried out for its effective control and measure by...

Download PDF file
  • EP ID EP318476
  • DOI 10.9734/BJAST/2017/31153
  • Views 92
  • Downloads 0

How To Cite

Md. Saifuddin Tarafder, Md. Shahadat Hossain, Md. Rafiqul Islam (2017). Human Motion Analysis from Depth Video Sequences Using Multi-scale and Multi-directional Features. Current Journal of Applied Science and Technology, 19(6), 1-12. https://europub.co.uk/articles/-A-318476