Document Type

Conference Proceeding

Publication Date


Publication Title

IV Conference on Articulated Motion and Deformable Objects


Silhouette recognition can reconstruct the three-dimensional pose of a human subject in monocular video so long as the camera’s view remains unoccluded by other objects. This paper develops a shape representation that can describe and compare partial shapes, extending the silhouette recognition technique to apply to video with occlusions. The new method operates without human intervention, and experiments demonstrate that it can reconstruct accurate three-dimensional articulated pose tracks from single-camera walking video despite occlusion of one-third to one-half of the subject.

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


© Nicholas Howe


Author’s submitted manuscript.

Follow link below to page containing video to supplement the paper Boundary Fragment Matching and Articulated Pose Under Occlusion, accepted to the IV Conference on Articulated Motion and Deformable Objects, July 2006. For clarity, time has been slowed down in these videos. All videos use MPEG-4 compression.

amdo06talk.pdf (8328 kB)



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.