Humanising GrabCut: learning to segment humans using the Kinect
The Kinect provides an opportunity to collect large quantities of training data for visual learning algorithms relatively effortlessly. To this end we investigate learning to automatically segment humans from cluttered images (without depth information) given a bounding box. For this algorithm, obta...
Main Authors: | Gulshan, V, Lempitsky, V, Zisserman, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2012
|
Similar Items
-
Pylon model for semantic segmentation
by: Lempitsky, V, et al.
Published: (2012) -
Geodesic star convexity for interactive image segmentation
by: Gulshan, V, et al.
Published: (2010) -
BiCoS: a bi-level co-segmentation method for image classification
by: Chai, Y, et al.
Published: (2012) -
Learning to count objects in images
by: Lempitsky, V, et al.
Published: (2011) -
Texture aware image segmentation using graph cuts and active contours
by: Zhou, Hailing, et al.
Published: (2013)