Please use this identifier to cite or link to this item:
標題: 單視覺虛擬平面障礙物偵測與方向規劃
Obstacle Detection and Direction Decision for Monocular Visual Based Robots
作者: 林展源
Lin, Jan-Yuan
關鍵字: monocular vision
computer vision
obstacle detection
direction decision
出版社: 資訊科學與工程學系所
引用: [1] 范俊海、莊劍嵐、賴文復,動態車輛周圍資訊偵測系統之研究, 2004, 國科 會專題研究計畫編號 NSC 92-2211-E-032-027- [2] A. Miranda, Neto, and L. Rittner, A simple and efficient Road Detection Algorithm for Real Time Autonomous Navigation based on Monocular Vision, 2006, Robotics Symposium IEEE [3] A. Miranda Neto, L. Rittner, D.E.Zampieri and A. Correa-Victorino, Nondeterministic Criteria to Discard Redundant Information in Real Time Autonomous Navigation Systems based on Monocular Vision, 2008, IEEE International Symposium on Intelligent Control [4] Andrew J. Davison, Ian D. Reid, Nicholas D. Molton, and Olivier Stasse, MonoSLAM: Real-Time Single Camera SLAM, 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence [5] Antonio Adan, Alberto Martin, Ricardo Chacon, and Vicente Dominguez, Monocular Model-Based 3D Location for Autonomous Robots, 2008, Mexican International Conference on Artificial Intelligence [6] B. Lucas and T. Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision, 1981, Proceedings of the 1981 DARPA Image Understanding Workshop [7] Giuseppina Gini, Alberto Marchi, Indoor Robot Navigation with Single Camera Vision, 2002, Proceedings of the 2nd International Workshop on Pattern Recognition in Information Systems [8] Hui Wang、Kui Yuan、Wei Zou、Yizhun Peng, Real-Time Obstacle Detection with a Single Camera, 2005, Industrial Technology [9] Iwan Ulrich and Illah Nourbakhsh, Appearance-Based Obstacle Detection with Monocular Color Vision, 2000, AAAI National Conference on Artificial Intelligence [10] Jason Campbell, Rahul Sukthankar, Illah Nourbakhsh, Aroon Pahwa, A Robust Visual Odometry and Precipice Detection System Using Consumer-grade Monocular Vision, 2005, IEEE International Conference on Robotics and Automation [11] Jianbo Shi、Tomasi, C, Good features to track, 1993, IEEE Conference on Computer Vision and Pattern Recognition [12] Jean-Yves Bouguet, Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the algorithm, 2000, Intel Corporation Microprocessor Research Labs [13] Joan Sol`a, Andr’e Monin and Michel Devy, BiCamSLAM: Two times mono is more than stereo, 2007, IEEE International Conference on Robotics and Automation [14] Koichiro Yamaguchi, Takeo Kato, Yoshiki Ninomiya, Moving Obstacle Detection using Monocular Vision, 2006 Intelligent Vehicles Symposium [15] Naoya Tada, Keisuke Murata, Takeshi Saitoh, Tomoyuki Osaki, Ryosuke Konishi, Monocular Vision based Indoor Mobile Robot, 2008, The 23rd Internation Technical Conference on Circuits System [16] T.Taylor, S.Geva, and W.W.Boles, Monocular Vision as a Range Sensor, 2004, ISBN:1740881885 M. Mohammadian (Ed.) [17] T.K. ten Kate, M.B. van Leewen, S.E. Moro-Ellenberger, B.J.F. Driessen, A.H.G. Versluis, F.C.A. Groen, Mid-range and Distant Vehicle Detection with a Mobile Camera, 2004, IEEE Intelligent Vehicles Symposium [18] Zezhi Chen, Nick Pears, Bojian Liang, Monocular obstacle detection using reciprocal-polar rectification, 2006, Image and Vision Computing
摘要: 現今機器人與行車安全監控電腦等是相當熱門的議題,很多研究利用多樣感應器研究用於監控周圍環境保護載具安全,其又以直接使用電腦視覺最為熱門。有相當多的雙視覺研究,建立立體環境空間來偵測路徑上的障礙物。但單視覺障礙物偵測通常能有更低的建造成本與更簡易的架設方式,使用者不需高檔設備或精密安裝即有不錯效果。本文提出一種基於單視覺電腦視覺與LK 光流法(Lucas–Kanade Optical Flow Method),使用一般webcam 並輸入架設參數,建出地面視野的座查表,再即時依照畫面中物體移動模式來判斷使否有不在地面視野帄面移動的物體,並於每次偵測時都能一併依危險特徵點位置決定路徑方向的方法。
Nowadays researches on robotics and vehicle safety are very popular.Various researches use multiple sensors detecting surrounding environment to protect vehicles. Lots of researches detect obstacles by using stereo vision to create three-dimension environment, nevertheless monocular vision is of lower cost and easy setup, and user can get great result without advanced equipment and accurately installation. This thesis proposes a method based on monocular vision, Lucas-Kanade optical flow, and a normal webcam with few setup parameters, to create a horizon plane. By Observing objects in sight and check whether they are in the plane or not, we can obtain a safe path for vehicle.
其他識別: U0005-0507201016105500
Appears in Collections:資訊科學與工程學系所



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.