Local Stereo Matching Algorithm Based on Secondary Guided Filtering

Fig. 4. Disparity results of Middlebury stereo pairs by different algorithms. (a) Original color images; (b) real disparity maps; (c) disparity maps obtained by multiscale guided filtering; (d) disparity maps obtained by proposed algorithm; (e) error matching point by proposed algorithm

Download full size

Table 1. Comparison of experimental results of Middlebury stereo pairs%

View table

Table 1. Comparison of experimental results of Middlebury stereo pairs%

Algorithm	Tsukuba			Venus			Teddy			Cones			AvgPBP
Algorithm	nonocc	all	disc		nonocc	all	disc	nonocc	all	disc	nonocc	all	disc
S-NL	1.76	2.87	7.46	1.24	3.23	6.18	5.73	14.88	17.24	4.42	16.05	14.05	7.93
S-ST	2.04	3.25	8.24	1.41	3.48	6.76	6.22	15.48	17.88	4.76	16.58	14.27	8.37
S-BF	2.33	3.21	8.34	1.29	3.19	6.85	8.17	17.29	19.46	5.41	15.93	14.67	8.85
S-GF	2.3	3.4	8.56	1.09	3.16	6.53	6.99	16.61	18.86	3.23	14.2	13.35	8.19
Proposed	1.82	2.99	7.35	0.34	1.53	3.45	6.93	14.74	16.08	3.2	12.29	11.45	6.84

Table 2. Comparison of average runtime of different algorithmss
View table
Table 2. Comparison of average runtime of different algorithmss
Algorithm Tsukuba Venus Teddy Cones
S-ST 4.55 7.86 36.20 36.32
S-BF 203.76 380.71 1287.73 1391.03
S-GF 3.98 7.69 42.36 42.48
Proposed 5.64 11.03 53.49 53.54

Tools

Get Citation

Copy Citation Text

Kai Wang, Zhiwei Li, Chengde Zhu, Lu Wang, Runcai Huang, Hengchang Guo. Local Stereo Matching Algorithm Based on Secondary Guided Filtering[J]. Laser & Optoelectronics Progress, 2019, 56(8): 081004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites