Multi-Person Articulated Tracking With Spatial and Temporal Embeddings

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ◽

10.1109/cvpr.2019.00581 ◽

2019 ◽

Cited By ~ 13

Author(s):

Sheng Jin ◽

Wentao Liu ◽

Wanli Ouyang ◽

Chen Qian

Keyword(s):

Articulated Tracking

Download Full-text

Natural metrics and least-committed priors for articulated tracking

Image and Vision Computing ◽

10.1016/j.imavis.2011.11.009 ◽

2012 ◽

Vol 30 (6-7) ◽

pp. 453-461 ◽

Cited By ~ 11

Author(s):

Søren Hauberg ◽

Stefan Sommer ◽

Kim Steenstrup Pedersen

Keyword(s):

Articulated Tracking

Download Full-text

Dynamic High Resolution Deformable Articulated Tracking

2017 International Conference on 3D Vision (3DV) ◽

10.1109/3dv.2017.00015 ◽

2017 ◽

Cited By ~ 3

Author(s):

Aaron Walsman ◽

Weilin Wan ◽

Tanner Schmidt ◽

Dieter Fox

Keyword(s):

High Resolution ◽

Articulated Tracking

Download Full-text

Multiple view human articulated tracking using charting and particle swarm optimisation

Proceedings of the 1st international workshop on 3D video processing - 3DVP '10 ◽

10.1145/1877791.1877805 ◽

2010 ◽

Cited By ~ 3

Author(s):

Vijay John ◽

Emanuele Trucco

Keyword(s):

Particle Swarm ◽

Particle Swarm Optimisation ◽

Multiple View ◽

Articulated Tracking

Download Full-text

Data-Driven Importance Distributions for Articulated Tracking

Lecture Notes in Computer Science - Energy Minimization Methods in Computer Vision and Pattern Recognition ◽

10.1007/978-3-642-23094-3_21 ◽

2011 ◽

pp. 287-299

Author(s):

Søren Hauberg ◽

Kim Steenstrup Pedersen

Keyword(s):

Data Driven ◽

Articulated Tracking

Download Full-text

HUMAN MOTION PERCEPTION THROUGH VIDEO MODEL-BASED TRACKING

International Journal of Humanoid Robotics ◽

10.1142/s0219843606000813 ◽

2006 ◽

Vol 03 (03) ◽

pp. 341-350

Author(s):

JEAN-BAPTISTE DE LA RIVIÈRE ◽

PASCAL GUITTON

Keyword(s):

Tracking System ◽

Robot Vision ◽

Human Motion ◽

Video Tracking ◽

The Body ◽

Body Motion ◽

Model Based ◽

Processing Step ◽

Articulated Tracking ◽

Video Model

As computer vision enables the robot to be aware of its human counterpart, such algorithms could help machines to achieve human-like interaction. However, many video tracking algorithms are not able to cope with some robot vision requirements. The articulated tracking system we develop solves some of those issues. It relies on model-based algorithms, which we believe are more suitable to robot vision than appearance-based ones. Indeed, as they update all the relevant parameters of a surrounding world model, results include some knowledge of the camera and objects relative positions. Our system relies on 3D model silhouette matching and runs in real time. We increase the algorithm robustness by introducing a pre-processing step based on image moments. This allows the iteration refinement to start in a better position by roughly estimating the body motion from one frame to the next.

Download Full-text