zbMATH — the first resource for mathematics

Error aware multiple vertical planes based visual localization for mobile robots in urban environments. (English) Zbl 1343.68249
Summary: A novel error-aware visual localization method is proposed that utilizes vertical planes, such as vertical building facades in urban areas as landmarks. Vertical planes, reconstructed from coplanar vertical lines, are robust high-level features if compared with point features or line features. Firstly, the error models of vertical lines and vertical planes are built, where maximum likelihood estimation (MLE) is employed to estimate all vertical planes from coplanar vertical lines. Then, the closed-form representation of camera location error variance is derived. Finally, the minimum variance camera pose estimation is formulated into a convex optimization problem, and the weight for each vertical plane is obtained by solving this well-studied problem. Experiments are carried out and the results show that the proposed localization method has an accuracy of about 2 meters, at par with commercial GPS operating in open environments.
68T40 Artificial intelligence for robotics
Full Text: DOI
[1] Garro, V.; Galassi, M.; Fusiello, A., Visual localization for mobile surveillance, 80-81, (2011)
[2] Huang, K.; Tseng, S.; Mou, W.; etal., Simultaneous localization and scene reconstruction with monocular camera, 2102-2107, (2012)
[3] Lowe, D. G., Distinctive image features from scale-invariant keypoints, Intern J Comp Vision, 60, 91-110, (2004)
[4] Santosh, D.; Achar, S.; Jawahar, C., Autonomous image-based exploration for mobile robot navigation, 2717-2722, (2008)
[5] Cummins, M.; Newman, P., FAB-MAP: Probabilistic localization and mapping in the space of appearance, Intern J Robotics Res, 27, 647-665, (2008)
[6] Larlus, D.; Verbeek, J.; Jurie, F., Category level object segmentation by combining bag-of-words models with dirichlet processes and random fields, Intern J Comp Vision, 88, 238-253, (2010)
[7] Wu, L.; Hoi, S.; Yu, N., Semantics-preserving bag-of-words models and applications, IEEE Trans Image Proc, 19, 1908-1920, (2010) · Zbl 1371.68072
[8] Davison, A.; Reid, L.; Molton, N.; etal., Monoslam: Real-time single camera slam, IEEE Trans Pattern Anal Machine Intellig, 29, 1052-1067, (2007)
[9] Gil, A.; Mozos, O.; Ballesta, M.; etal., A comparative evaluation of interest point detectors and local descriptors for visual SLAM, Machine Vision Appl, 21, 905-920, (2010)
[10] Lemaire, T.; Lacroix, S., Monocular-vision based SLAM using line segments, 2791-2796, (2007)
[11] Elqursh, A.; Elgammal, A., Line-based relative pose estimation, 3049-3056, (2011)
[12] Delmerico, J.; David, P.; Adelphi, M.; etal., Building facade detection, segmentation, and parameter estimation for mobile localization and guidance, 1632-1639, (2011)
[13] Cham, T.; Ciptadi, A.; Tan, W.; etal., Estimating camera pose from a single urban ground-view omnidirectional image and a 2D building outline map, 366-373, (2010)
[14] Gee, A.; Chekhlov, D.; Calway, A.; etal., Discovering higher level structure in visual slam, IEEE Trans Robotics, 24, 980-990, (2008)
[15] Martinez-Carranza, J.; Calway, A., Unifying planar and point mapping in monocular slam, 43.1-43.11, (2010)
[16] Leung, K.; Clark, C.; Huissoon, J., Localization in urban environments by matching ground level video images with an aerial image, 551-556, (2008)
[17] Bansal, M.; Sawhney, H.; Cheng, H.; etal., Geo-localization of street views with aerial image databases, 1125-1128, (2011)
[18] Selnet, T.; Elgammal, A., Satellite image based precise robot localization on sidewalks, 2647-2653, (2012)
[19] Kummerle, R.; Steder, B.; Dornhege, C.; etal., Large scale graph-based SLAM using aerial images as prior information, Auton Robots, 30, 25-39, (2011)
[20] Muramatsu, S.; Tomizawa, T.; Matsuda, H.; etal., Mobile robot localization technique using Web-based aerial photos, 1886-1891, (2012)
[21] Li, H.; Song, D.; Lu, Y.; etal., A two-view based multilayer feature graph for robot navigation, 3580-3587, (2012)
[22] Li, H.; Liu, J.; Lu, X., Visual localization in urban area using orthogonal building boundaries and a GIS database, ROBOT, 34, 604-613, (2012)
[23] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision, 2nd Ed. Cambridge: Cambridge University Press, 2004. 30-35 · Zbl 1072.68104
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.