World representations Stereo Processing Experimental results Conclusion A Constant-Time Efficient Stereo SLAM System Christopher Mei 1 , Gabe Sibley 2 , Mark Cummins 2 , Paul Newman 2 and Ian Reid 1 1 Active Vision Group, 2 Mobile Robotics Group, University of Oxford C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 1/25
World representations Stereo Processing Experimental results Conclusion Simultaneous Localisation and Mapping Goal of SLAM : to estimate the trajectory of a sensor in a iterative fashion, build a representation of the environment. What makes SLAM challenging ? computationally expensive (the complexity grows with the size of the environment), requires robust data fusion algorithms. C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 2/25
World representations Stereo Processing Experimental results Conclusion A constant time stereo SLAM system This talk will describe... a continuous relative representation (CRR) providing a way to represent precisely the local environment and improve accuracy at loop closure without global estimation, low-level vision tasks: image pyramids, quadtree feature selection, scale invariance through stereo, relocalisation and sub-pixel minimisation to provide improved accuracy and robustness. ... to obtain a constant-time precise and robust stereo SLAM system. C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 3/25
World representations Stereo Processing Experimental results Conclusion Outline World representations 1 Stereo Processing 2 3 Experimental results Conclusion 4 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 4/25
World representations Stereo Processing Experimental results Conclusion Outline World representations 1 Stereo Processing 2 3 Experimental results Conclusion 4 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 5/25
World representations Stereo Processing Experimental results Conclusion Global representations Global Representations “standard” representation: robot poses and landmarks are represented in a global frame, robocentric representation: global frame centred on the current robot position. Improves the consistency of EKF-SLAM [Castellanos et al IFAC 2004] C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 6/25
World representations Stereo Processing Experimental results Conclusion Sub-mapping Sub-maps sub-maps: robot poses and landmarks are grouped in smaller maps. Each sub-map uses a global or relative representation ([Estrada et al. ITRO 2005] [Bosse et al. IJRR 2004] ) , reduces the complexity and improves consistency, limitations: sharing information between sub-maps is a difficult problem in particular when updating the estimates after loop closure. C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 7/25
World representations Stereo Processing Experimental results Conclusion Continuous Relative Representation Changing the representation has a profound impact on the mapping process. In particular, the maximum likelihood cost functions for the global representation and CRR are different : See [Sibley et. al RSS 2009] C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 8/25
World representations Stereo Processing Experimental results Conclusion Example with a loop closure C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 9/25
World representations Stereo Processing Experimental results Conclusion Change of perspective Before loop closure After loop closure Change of perspective a robot should be able to evolve in an environment with non observable ego-motion, a challenge is to find the places where such events occur (lifts, trains, planes, ...) C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 10/25
World representations Stereo Processing Experimental results Conclusion Advantages and limitations of the CRR Advantages simplifies loop closure and data association, the precision at loop closure is the same as during exploration. Limitations to obtain a coherent global Euclidean representation, global estimation is required (with a complexity dependent on the size of the map), but is this often acquired? C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 11/25
World representations Stereo Processing Experimental results Conclusion Outline World representations 1 Stereo Processing 2 3 Experimental results Conclusion 4 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 12/25
World representations Stereo Processing Experimental results Conclusion Stereo SLAM processing steps Pose initialisation Pre-processing Feature extraction (SSD rotation) Robust estimation Image to map data Adding of new landmarks of the robot pose association Loop closure is done using a bag of words approach: FabMap [Cummins and Newman IJRR 2008]. C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 13/25
World representations Stereo Processing Experimental results Conclusion Components of the SLAM system Processing steps that greatly effect the system’s performance Pose initialisation by image-based rotation estimation ([Mei et. al ITRO 2008]), Better pose conditioning by spreading features using quadtrees, Sub-pixel minimisation for each landmark to image matching to improve precision, Efficient scale invariance by using the landmark distance (“true scale”). C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 14/25
World representations Stereo Processing Experimental results Conclusion Improving conditioning using quadtrees Without quadtrees With quadtrees C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 15/25
World representations Stereo Processing Experimental results Conclusion Improving precision through sub-pixel minimisation Applying sub-pixel minimisation (eg. Kanade-Lucas-Tomasi tracker) greatly improves precision and data association. Without sub-pixel minimisation With sub-pixel minimisation C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 16/25
World representations Stereo Processing Experimental results Conclusion Efficient scale invariance Scale invariance in SIFT: obtained by 35 30 looking for a maximum score response Patch size (pixels) 25 at different scales in a DoG pyramid, 20 this is an expensive process, 15 10 Alternative: choose a fixed 3-D 5 0 20 40 60 80 100 Distance (m) template size for computing the descriptors, (“true scale”). Problem: the camera image size is insufficient to represent large changes in depth, Solution: split the 3-D space in regions (“bands”) where the 3-D templates have the same size. C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 17/25
World representations Stereo Processing Experimental results Conclusion Outline World representations 1 Stereo Processing 2 3 Experimental results Conclusion 4 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 18/25
World representations Stereo Processing Experimental results Conclusion Experimental results Begbroke Science Park (1.1km) New College (1.8km) C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 19/25
World representations Stereo Processing Experimental results Conclusion Importance of loop closure on precision (1/2) Trajectory estimates with/without loop closure. Begbroke New College −140 −200 −120 35 −150 −100 30 25 −80 −100 20 x (m) −60 15 y (m) −50 −40 10 5 −20 0 0 x (m) 0 −5 20 50 −10 −50 0 50 100 −50 0 50 100 150 200 250 −40 −30 −20 −10 0 10 150 200 250 y (m) x (m) y (m) 15 10 2 z (m) 5 1.5 20 0 1 z (m) 0 z (m) 0.5 −5 −20 400 300 200 0 200 200 100 −0.5 100 0 0 50 0 30 −50 20 10 0 10 −100 0 −100 0 −20 −10 −200 −150 −10 −30 y (m) −200 x (m) y (m) x (m) y (m) x (m) −100 −200 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 20/25
World representations Stereo Processing Experimental results Conclusion Importance of loop closure on precision (2/2) Begbroke New College Distance Travelled 1.08 km 2.26 km Frames Processed 23K 51K Reprojection Error 0.003 / 0.17 / 0.55 pixels 0.03 / 0.13 / 1.01 pixels Min/Avg/Max Accuracy without ∼ 1m in (x-y) plane, ∼ 1m ∼ 15-25m in (x-y) plane, loop closure in z ∼ 15m in z Accuracy with loop ∼ 1cm in (x-y) plane, ∼ 10cm in (x-y) plane, closure ∼ 1cm in z ∼ 10cm in z C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 21/25
World representations Stereo Processing Experimental results Conclusion Results on difficult sequences Large changes in view- Blur point Lens Flare and Saturation C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 22/25
World representations Stereo Processing Experimental results Conclusion Outline World representations 1 Stereo Processing 2 3 Experimental results Conclusion 4 C. Mei et. al BMVC 2009 - Constant-Time Stereo SLAM - 23/25
Recommend
More recommend
