Topological localization using optical flow descriptors
作者： Navid Nourani-Vatani , Paulo V K Borges , Jonathan M Roberts , Mandyam V Srinivasan
DOI: 10.1109/ICCVW.2011.6130364
关键词: Node (circuits) 、 Artificial intelligence 、 Computer vision 、 Key (cryptography) 、 Field (computer science) 、 Frame (networking) 、 Mahalanobis distance 、 Mathematics 、 Topology 、 Flow (mathematics) 、 Optical flow 、 Position (vector)
摘要: We propose a topological localization method based on optical flow information. analyse the statistical characteristics of signal and demonstrate that vectors can be used to identify describe key locations in environment. The (nodes) correspond significant scene changes depth discontinuities. Since contain position, magnitude angle information, for each node, we extract low high order moments use them as descriptors node. Once database nodes their corresponding features is created, robot perform by using Mahalanobis distance between current frame database. This supported field trials, which illustrate repeatability proposed detecting describing indoor outdoor environments challenging diverse lighting conditions.
uq.edu.au参考文章(20)
Oscar Firschein, Martin A. Fischler, Readings in computer vision: issues, problems, principles, and paradigms Morgan Kaufmann Publishers Inc.. ,(1987)
J.-Y. Bouguet, Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm OpenCV Documents. ,(1999)
Felix Werner, Frederic Maire, Joaquin Sitte, Topological SLAM Using Fast Vision Techniques Lecture Notes in Computer Science. ,vol. 5744, pp. 187- 196 ,(2009) , 10.1007/978-3-642-03983-6_23
D. Radhakrishnan, I.R. Nourbakhsh, Topological robot localization by training a vision-based transition detector intelligent robots and systems. ,vol. 1, pp. 468- 473 ,(1999) , 10.1109/IROS.1999.813048
D. Kortenkamp, L.D. Baker, T. Weymouth, Using Gateways To Build A Route Map intelligent robots and systems. ,vol. 3, pp. 2209- 2214 ,(1992) , 10.1109/IROS.1992.602138
D.M. Bradley, R. Patel, N. Vandapel, S.M. Thayer, Real-time image-based topological localization in large outdoor environments intelligent robots and systems. pp. 3670- 3677 ,(2005) , 10.1109/IROS.2005.1545442
Jonathan Roberts, Ashley Tews, Cedric Pradalier, Kane Usher, Autonomous Hot Metal Carrier - Navigation and Manipulation with a 20 tonne industrial vehicle international conference on robotics and automation. pp. 2770- 2771 ,(2007) , 10.1109/ROBOT.2007.363888
N Nourani-Vatani, C Pradalier, Scene change detection for vision-based topological mapping and localization intelligent robots and systems. pp. 3792- 3797 ,(2010) , 10.1109/IROS.2010.5652556
Stefan Hrabar, Gaurav Sukhatme, Optimum Camera Angle for Optic Flow-Based Centering Response intelligent robots and systems. pp. 3922- 3927 ,(2006) , 10.1109/IROS.2006.281824
B. Galvin, B. McCane, K. Novins, D. Mason, S. Mills, Recovering Motion Fields: An Evaluation of Eight Optical Flow Algorithms british machine vision conference. pp. 1- 10 ,(1998) , 10.5244/C.12.20