9 November 2017 RGB-D foreground extraction from a moving camera using nonlinear pixel classification
Author Affiliations +
Abstract
We propose a foreground extraction method from a freely moving RGB-D video camera that uses a nonlinear optimization function to classify pixels in every frame as either foreground or background. The method starts with extracting sparse features in every frame. These features are then matched to create a nonlinear optimization function that is used to label each pixel in the depth image as either foreground or background. Finally, the inverse mapping from depth to RGB data is used to extract the foreground from the RGB image. Our results show that even in the presence of high camera motion, it is possible to reliably extract the foreground from the RGB-D video data captured from a freely moving camera.
© 2017 SPIE and IS&T
Naveed Ahmed, Imran Junejo, "RGB-D foreground extraction from a moving camera using nonlinear pixel classification," Journal of Electronic Imaging 26(6), 063009 (9 November 2017). https://doi.org/10.1117/1.JEI.26.6.063009 . Submission: Received: 20 May 2017; Accepted: 19 October 2017
Received: 20 May 2017; Accepted: 19 October 2017; Published: 9 November 2017
JOURNAL ARTICLE
10 PAGES


SHARE
RELATED CONTENT

Semantically enabled image similarity search
Proceedings of SPIE (May 21 2015)
Human object articulation for CCTV video forensics
Proceedings of SPIE (March 19 2013)
mEdgeBoxes: objectness estimation for depth image
Proceedings of SPIE (December 14 2015)
Foreground extraction for moving RGBD cameras
Proceedings of SPIE (February 08 2017)
Model-assisted object tracking
Proceedings of SPIE (January 17 2005)
Recognizing persons in images by learning from videos
Proceedings of SPIE (January 29 2007)

Back to Top