A line based pose representation for human action recognition
Please cite this item using this persistent URLhttp://hdl.handle.net/11693/20987
Signal Processing: Image Communication
- Research Paper 
In this paper, we utilize a line based pose representation to recognize human actions in videos. We represent the pose in each frame by employing a collection of line-pairs, so that limb and joint movements are better described and the geometrical relationships among the lines forming the human figure are captured. We contribute to the literature by proposing a new method that matches line-pairs of two poses to compute the similarity between them. Moreover, to encapsulate the global motion information of a pose sequence, we introduce line-flow histograms, which are extracted by matching line segments in consecutive frames. Experimental results on Weizmann and KTH datasets emphasize the power of our pose representation, and show the effectiveness of using pose ordering and line-flow histograms together in grasping the nature of an action and distinguishing one from the others. © 2013 Elsevier B.V. All rights reserved.
Showing items related by title, author, creator and subject.
A hybrid classification model for digital pathology using structural and statistical pattern recognition Ozdemir, E.; Gunduz-Demir, C. (2013)Cancer causes deviations in the distribution of cells, leading to changes in biological structures that they form. Correct localization and characterization of these structures are crucial for accurate cancer diagnosis and ...
Öksüz Ö.; Güdükbay, U.; Çetin, A.E. (2008)In this paper we present a video based text and equation editor for LaTeX. The system recognizes what is written onto paper and generates the LaTeX code. Text and equations are written on a regular paper using a board ...
Kiliboz, N.Ç.; Güdükbay, U. (Academic Press Inc., 2015)We propose an approach to recognize trajectory-based dynamic hand gestures in real time for human-computer interaction (HCI). We also introduce a fast learning mechanism that does not require extensive training data to ...