TY  - JOUR
T1  - Scene Structure Registration for Localization and Mapping
A1  - Fernández-Moral, Eduardo
A1  - Rives, Patrick
A1  - Arevalo-Espejo, Vicente
A1  - Gonzalez-Jimenez, Javier
JA  - Robotics and Autonomous Systems
Y1  - 2016
VL  - 75 (Part B)
SP  - 649
EP  - 660
M2  - doi: doi:10.1016/j.robot.2015.09.009
N2  - Image registration, and more generally scene registration, needs to be solved in mobile robotics for a number of tasks including localization, mapping, object recognition, visual odometry and loop-closure. This paper presents a flexible strategy to register scenes based on its planar structure, which can be used with different sensors that acquire 3D data like LIDAR, time-of-flight cameras, RGB-D sensors and stereo vision. The proposed strategy is based on the segmentation of the planar surfaces from the scene, and its representation using a graph which stores the geometric relationships between neighbouring planar patches. Uncertainty information from the planar patches is exploited in a hierarchical fashion to improve both the robustness and the efficiency of registration. Quick registration is achieved in indoor structured scenarios, offering advantages like a compact representation, and flexibility to adapt to different environments and sensors. Our method is validated with different sensors: a hand-held RGB-D camera and an omnidirectional RGB-D sensor; and for different applications: from visual-range odometry to loop closure and SLAM.
M1  - img_url=http%3A%2F%2Fmapir.isa.uma.es%2Fvarevalo%2Fdrafts%2Ffernandez2016ras.png
M1  - rank_indexname=JCR%202016
M1  - rank_pos_in_category=60
M1  - rank_num_in_category=133
M1  - rank_cat_name=COMPUTER%20SCIENCE%2C%20ARTIFICIAL%20INTELLIGENCE
M1  - impact_factor=1.950
ER  -