Title :
Depth edge based trilateral filter method for stereo matching
Author :
Dongming Chen;Mohsen Ardabilian;Liming Chen
Author_Institution :
Ecole Centrale de Lyon, LIRIS, UMR 5205, 69134 Ecully, France
Abstract :
Recently, trilateral filter based method is more accurate than other local stereo matching methods on Middlebury benchmark. The boundary strength term is the key part of this method, which is computed from a color edge map. In this paper, we prove that boundary strength term, computed from a depth edge map, produces more accurate results. Then, we propose a depth edge detection technique to obtain an accurate depth edge map and present a depth edge based trilateral filter method. The experimental evaluation on the Middlebury benchmark shows that the proposed method outperforms the original trilateral filter method and also other local methods.
Keywords :
"Image edge detection","Image color analysis","Junctions","Benchmark testing","Detectors","Color","Joining processes"
Conference_Titel :
Image Processing (ICIP), 2015 IEEE International Conference on
DOI :
10.1109/ICIP.2015.7351208