Abstract | ||
---|---|---|
This paper presents a new hardware-oriented approach for the extraction of disparity maps from stereo images. The proposed method is based on the herein named Adaptive Census Transform that exploits adaptive support weights during the image transformation; the adaptively weighted sum of SADs is then used as the dissimilarity metric. Quality tests show that the proposed method reaches significantly better accuracy than alternative hardware-oriented approaches. To demonstrate the practical hardware feasibility, a specific architecture has been designed and its implementation has been carried out using a single FPGA chip. Such a VLSI implementation allows a frame rate up to 68fps to be reached for 640x480 stereo images, using just 80,000 slices and 32 RAM blocks of a Virtex6 chip. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.cviu.2012.10.003 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
new hardware-oriented approach,single fpga chip,stereo image,virtex6 chip,stereovision algorithm,ram block,adaptive census transform,alternative hardware-oriented approach,adaptive support weight,vlsi implementation,vlsi | Computer vision,Computer science,Chip,Exploit,Image transformation,Census transform,Artificial intelligence,Frame rate,Computer hardware,Very-large-scale integration,Fpga chip | Journal |
Volume | Issue | ISSN |
117 | 1 | 1077-3142 |
Citations | PageRank | References |
8 | 0.61 | 27 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stefania Perri | 1 | 264 | 33.11 |
Pasquale Corsonello | 2 | 278 | 38.06 |
Giuseppe Cocorullo | 3 | 106 | 17.00 |