Professional Documents
Culture Documents
SHESHGIRI
COLLEGE OF ENGINEERING
AND TECHNOLOG,BELGAUM
Depth Imaging System For
Human Posture Recognition
Introduction
Literature Survey
Explanation Of Paper
Conclusion
References
Abstract
The proposed system is able to efficiently model human postures by
exploiting the depth information captured by an RGB-D camera
1 B. Boulay, F. Bremond, and M. Thonnat, Human A background subtraction method is used to extract the
posture recognition in video sequence. IEEE human silhouette. A 3D model of posture is then built
International Workshop on VS-PETS, Visual using geometric features covering the position and the
Surveillance and Performance Evaluation of orientation.
Tracking and Surveillance, 2003.
2 T. Moeslund and E. Granum, 3D human pose Authors in paper proposed an alternative representation
estimation using 2D-data and an alternative to build the silhouette 3D model of the body, where
phase space representation. Procedure Humans, human posture estimation is based on kinematic
2000. constraints.
3 A. Agarwal and B. Triggs, Recovering 3D human A work is proposed to build a 3D human body from
pose from monocular images. IEEE transactions monocular silhouettes using direct sparse regression of
on pattern analysis and machine intelligence, joint angles. The silhouettes are extracted using
28(1): 44–58, 2006.. background segmentation and encoded by an histogram-
of-shape-context.
Explanation Of Paper
The system uses a single RGB-D camera (Microsoft Kinectv2) to capture
depth maps and build a body skeleton.
The two feature sets D and A are then concatenated in a single feature
vector to form the final representation of human posture F = [D, A]
Posture Classification
Once the body pose is modeled, posture recognition is performed in a
supervised classification approach using SVM classifier.
With its different kind of kernels, SVM has the ability to generate non-
linearly as well as high-dimensional classification issue.
Distinguish and learn the significance of RGB image and Depth image
in pose estimation.