Abstract | ||
---|---|---|
In order to segment interest objects from multi-view images accurately, an epipolar plane image (EPI) analysis based object segmentation algorithm is proposed. Firstly, the straight lines in EPI are extracted by an improved Hough transform. Then, according to the depth of object, the corresponding straight lines are converted into original image space to get an initial contour. Following that, we design a boundary growing algorithm to shorten the gaps between broken edge segments. Finally, a contour linking algorithm is applied to obtain a closed segmentation curve. Experimental results show that, the proposed method can extract frontal objects from complicated scene correctly. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ISCSCT.2008.82 | ISCSCT (2) |
Keywords | Field | DocType |
epipolar plane image,boundary growing algorithm,large hospital,multi-view object segmentation,contour linking,image segmentation,high-quality patient treatment,clinical pathway,hospital stay,feature extraction,multiview object segmentation,epipolar plane image analysis,straight lines extraction,hough transform,boundary growing,contour linking algorithm,hough transforms,image processing,pixel,algorithm design and analysis | Computer vision,Scale-space segmentation,Epipolar geometry,Pattern recognition,Segmentation,Image processing,Segmentation-based object categorization,Hough transform,Feature extraction,Image segmentation,Artificial intelligence,Mathematics | Conference |
Volume | ISBN | Citations |
2 | 978-1-4244-3746-7 | 0 |
PageRank | References | Authors |
0.34 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liangzhong Fan | 1 | 7 | 3.00 |
Xin Yu | 2 | 0 | 0.34 |
Zhenyu Shu | 3 | 7 | 1.55 |
Qiaowen Zhang | 4 | 1 | 1.06 |