SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
Dynamic Graph Cuts for Efficient Inference in Markov Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Natural Video Matting with Depth
PG '07 Proceedings of the 15th Pacific Conference on Computer Graphics and Applications
Time-consistent foreground segmentation of dynamic content from color and depth video
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
| Hi-index | 0.00 |
This work describes an approach to color image segmentation by supporting an iterative graph cut segmentation algorithm with depth data collected by time-of-flight (TOF) cameras. The graph cut algorithm uses an energy minimization approach to segment an image, taking account of both color and contrast information. The foreground and background color distributions of the images subject to segmentation are represented by Gaussian mixture models, which are optimized iteratively by parameter learning. These models are initialized by a preliminary segmentation created from depth data, automating the model initialization step, which otherwise relies on user input.