Unconstrained self-calibration of stereo camera on visually impaired assistance devices

Huabing Li; Huabing Li; Kaiwei Wang; Kailun Yang; Kailun Yang; Kailun Yang; Ruiqi Cheng; Chen Wang; Lei Fei

doi:10.1364/AO.58.006377

Applied Optics
Vol. 58,
Issue 23,
pp. 6377-6387
(2019)
•https://doi.org/10.1364/AO.58.006377

Unconstrained self-calibration of stereo camera on visually impaired assistance devices

Huabing Li, Kaiwei Wang, Kailun Yang, Ruiqi Cheng, Chen Wang, and Lei Fei

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Huabing Li, Kaiwei Wang, Kailun Yang, Ruiqi Cheng, Chen Wang, and Lei Fei, "Unconstrained self-calibration of stereo camera on visually impaired assistance devices," Appl. Opt. 58, 6377-6387 (2019)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Abstract

Stereo cameras are widely used in wearable visually impaired assistance devices (VIADs). However, the inevitable vibration, shock, and mechanical stress may make the camera pair become misaligned and cause a sharp decline in the quality of the acquired depth map, which significantly influences the performance of VIADs. In this paper, we propose an epipolar-constraint-based unconstrained self-calibration method that requires neither user involvement nor specific environment, while achieving a rotation accuracy of 0.83 mrad and a translation accuracy of 0.42 mm. Several approaches are proposed to address the image matching issues, including blurred images removal, mismatched key points removal, etc. Based on correctly matched key point pairs, a planar quadric-distribution approach is proposed to ensure the quality and consistency of the final key point group. These collection approaches ensure the reliability of key point pairs, which is the most important factor to realize high accuracy with minimum constraint. A comprehensive set of experiments demonstrates the high robustness of the proposed methods, which are suitable for VIADs. We also present a field test with blindfolded users to validate the flexibility and applicability of the approach.

Full Article | PDF Article

More Like This

Self-calibration approach to stereo cameras with radial distortion based on epipolar constraint

Banglei Guan, Yingjian Yu, Ang Su, Yang Shang, and Qifeng Yu
Appl. Opt. 58(31) 8511-8521 (2019)

Planar self-calibration for stereo cameras with radial distortion

Banglei Guan, Yang Shang, and Qifeng Yu
Appl. Opt. 56(33) 9257-9267 (2017)

Camera calibration using a planar target with pure translation

Mao Yang, Xiaobo Chen, and Chengyi Yu
Appl. Opt. 58(31) 8362-8370 (2019)

Previous Article Next Article

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (16)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (3)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (19)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Index	Rotations/mrad			Translation/mm
Index	Yaw	Pitch	Roll	$t_{x}$	$t_{y}$	$t_{z}$
1	−0.17	−6.52	5.99	−69.88	−1.42	−0.89
2	−0.11	−6.82	5.53	−69.89	−1.15	−0.24
3	−0.02	−5.85	5.34	−69.88	−1.36	−1.05
4	0.06	−6.18	5.35	−69.88	−1.15	−1.55
5	0.02	−4.71	5.26	−69.89	−1.32	−0.64
6	0.00	−6.70	5.51	−69.89	−1.33	−0.36
7	−0.04	−4.97	5.06	−69.88	−1.45	−1.03
Mean	−0.04	−5.97	5.43	−69.88	−1.31	−0.82
S.D.	0.08	0.84	0.29	0.01	0.12	0.45

Index	Rotation/mrad			Translation/mm
Index	Yaw	Pitch	Roll	$t_{x}$	$t_{y}$	$t_{z}$
1	0.43	−6.79	5.83	−70.02	−1.46	0.33
2	0.22	−5.43	6.66	−70.02	−1.05	0.97
3	0.16	−6.39	4.92	−69.89	−0.88	4.37
4	0.36	−7.51	5.16	−69.97	−1.32	−2.50
5	0.16	−5.64	6.90	−69.96	−0.37	3.20
6	0.28	−5.69	5.04	−69.99	−1.48	−1.83
7	0.51	−7.01	5.87	−69.99	−1.56	−1.75
8	0.43	−6.79	5.83	−70.02	−1.46	0.33
Mean	0.30	−6.35	5.77	−69.98	−1.16	0.40
Baseline	−0.04	−5.97	5.43	−69.88	−1.31	−0.82
RMSE	0.36	0.83	0.80	0.10	0.42	2.74

	Rotation/mrad				Translation/mm
	Yaw	Pitch	Roll	Mean	$t_{x}$	$t_{y}$	$t_{z}$	Mean
QD ^a	0.36	0.83	0.80	0.66	0.10	0.42	2.74	1.09
ED ^b	0.33	1.52	1.42	1.09	0.49	1.55	6.62	2.89
ND ^c	1.12	4.99	2.99	3.03	4.24	2.94	17.09	8.09
AP ^d	0.51	2.76	1.57	1.61	0.85	1.15	8.81	3.60

Index	Rotations/mrad			Translation/mm
Index	Yaw	Pitch	Roll	$t_{x}$	$t_{y}$	$t_{z}$
1	−0.17	−6.52	5.99	−69.88	−1.42	−0.89
2	−0.11	−6.82	5.53	−69.89	−1.15	−0.24
3	−0.02	−5.85	5.34	−69.88	−1.36	−1.05
4	0.06	−6.18	5.35	−69.88	−1.15	−1.55
5	0.02	−4.71	5.26	−69.89	−1.32	−0.64
6	0.00	−6.70	5.51	−69.89	−1.33	−0.36
7	−0.04	−4.97	5.06	−69.88	−1.45	−1.03
Mean	−0.04	−5.97	5.43	−69.88	−1.31	−0.82
S.D.	0.08	0.84	0.29	0.01	0.12	0.45

Index	Rotation/mrad			Translation/mm
Index	Yaw	Pitch	Roll	$t_{x}$	$t_{y}$	$t_{z}$
1	0.43	−6.79	5.83	−70.02	−1.46	0.33
2	0.22	−5.43	6.66	−70.02	−1.05	0.97
3	0.16	−6.39	4.92	−69.89	−0.88	4.37
4	0.36	−7.51	5.16	−69.97	−1.32	−2.50
5	0.16	−5.64	6.90	−69.96	−0.37	3.20
6	0.28	−5.69	5.04	−69.99	−1.48	−1.83
7	0.51	−7.01	5.87	−69.99	−1.56	−1.75
8	0.43	−6.79	5.83	−70.02	−1.46	0.33
Mean	0.30	−6.35	5.77	−69.98	−1.16	0.40
Baseline	−0.04	−5.97	5.43	−69.88	−1.31	−0.82
RMSE	0.36	0.83	0.80	0.10	0.42	2.74

Abstract

Cited By

Figures (16)

Tables (3)

Equations (19)

Applied Optics