TY - GEN
T1 - Multi-Spectral Visual Odometry without Explicit Stereo Matching
AU - Dai, Weichen
AU - Zhang, Yu
AU - Sun, Donglei
AU - Hovakimyan, Naira
AU - Li, Ping
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they can help to overcome certain limitations of standard cameras under complicated illumination conditions. However, due to the difference in the information source of the two types of cameras, their images usually share very low texture similarity. Hence, traditional texture-based feature matching methods cannot be directly applied to obtain stereo correspondences. To tackle this problem, a multi-spectral visual odometry method without explicit stereo matching is proposed in this paper. Bundle adjustment of multi-view stereo is performed on the visible and the thermal images using direct image alignment. Scale drift can be avoided by additional temporal observations of map points with the fixed-baseline stereo. Experimental results indicate that the proposed method can provide accurate visual odometry results with recovered metric scale. Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.
AB - Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they can help to overcome certain limitations of standard cameras under complicated illumination conditions. However, due to the difference in the information source of the two types of cameras, their images usually share very low texture similarity. Hence, traditional texture-based feature matching methods cannot be directly applied to obtain stereo correspondences. To tackle this problem, a multi-spectral visual odometry method without explicit stereo matching is proposed in this paper. Bundle adjustment of multi-view stereo is performed on the visible and the thermal images using direct image alignment. Scale drift can be avoided by additional temporal observations of map points with the fixed-baseline stereo. Experimental results indicate that the proposed method can provide accurate visual odometry results with recovered metric scale. Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.
KW - Egomotion estimation
KW - Multi spectral sensors
KW - Visual Odometry
UR - http://www.scopus.com/inward/record.url?scp=85075016823&partnerID=8YFLogxK
U2 - 10.1109/3DV.2019.00056
DO - 10.1109/3DV.2019.00056
M3 - Conference contribution
AN - SCOPUS:85075016823
T3 - Proceedings - 2019 International Conference on 3D Vision, 3DV 2019
SP - 443
EP - 452
BT - Proceedings - 2019 International Conference on 3D Vision, 3DV 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on 3D Vision, 3DV 2019
Y2 - 15 September 2019 through 18 September 2019
ER -