TY - GEN
T1 - Underwater terrain reconstruction from forward-looking sonar imagery
AU - Wang, Jinkun
AU - Shan, Tixiao
AU - Englot, Brendan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - In this paper, we propose a novel approach for underwater simultaneous localization and mapping using a multibeam imaging sonar for 3D terrain mapping tasks. The high levels of noise and the absence of elevation angle information in sonar images present major challenges for data association and accurate 3D mapping. Instead of repeatedly projecting extracted features into Euclidean space, we apply optical flow within bearing-range images for tracking extracted features. To deal with degenerate cases, such as when tracking is interrupted by noise, we model the subsea terrain as a Gaussian Process random field on a Chow-Liu tree. Terrain factors are incorporated into the factor graph, aimed at smoothing the terrain elevation estimate. We demonstrate the performance of our proposed algorithm in a simulated environment, which shows that terrain factors effectively reduce estimation error. We also show ROV experiments performed in a variable-elevation tank environment, where we are able to construct a descriptive and smooth height estimate of the tank bottom.
AB - In this paper, we propose a novel approach for underwater simultaneous localization and mapping using a multibeam imaging sonar for 3D terrain mapping tasks. The high levels of noise and the absence of elevation angle information in sonar images present major challenges for data association and accurate 3D mapping. Instead of repeatedly projecting extracted features into Euclidean space, we apply optical flow within bearing-range images for tracking extracted features. To deal with degenerate cases, such as when tracking is interrupted by noise, we model the subsea terrain as a Gaussian Process random field on a Chow-Liu tree. Terrain factors are incorporated into the factor graph, aimed at smoothing the terrain elevation estimate. We demonstrate the performance of our proposed algorithm in a simulated environment, which shows that terrain factors effectively reduce estimation error. We also show ROV experiments performed in a variable-elevation tank environment, where we are able to construct a descriptive and smooth height estimate of the tank bottom.
UR - http://www.scopus.com/inward/record.url?scp=85071420628&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071420628&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2019.8794473
DO - 10.1109/ICRA.2019.8794473
M3 - Conference contribution
AN - SCOPUS:85071420628
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 3471
EP - 3477
BT - 2019 International Conference on Robotics and Automation, ICRA 2019
T2 - 2019 International Conference on Robotics and Automation, ICRA 2019
Y2 - 20 May 2019 through 24 May 2019
ER -