Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19758
標題: 使用多重CAMSHIFT追蹤的方式來改善機器人的視覺追蹤及自動控制
Improving the Ability of Visual Tracking and Automatic Controlling on Robot by Applying Multi-CAMSHIFT
作者: 陳柏志
Chen, Bo-Chih
關鍵字: CAMSHIFT演算法;Tzung-Her Chen;物件追蹤;自動控制;Kuen-Fang Jea;Hung-Min Sun
出版社: 資訊科學與工程學系所
引用: 參考文獻 [1]林易增、洪國寶, “使用邊緣特徵改善CAMShift的物件追蹤方法之效能” , 國立中興大學資訊科學與工程學系碩士學位論文 [2]CAMSHIFT演算法流程說明http://tonysh-thu.blogspot.com/2007/04/camshift_03.html [3]HSV與HSL色彩空間上的差異http://en.wikipedia.org/wiki/HSL_and_HSV [4]Gary Bradski, Adrian Kaehler, Learning OpenCV Computer Vision with the OpenCV Library 2008 1st edition,chapter10 [5]Bo Pu, Shuang Liang, Yongming Xie, Zhang Yi, Pheng-Ann Heng, “Video Facial Feature Tracking with Enhanced ASM and Predicted Meanshift”, 2010 Second International Conference on Computer Modeling and Simulation, pp. 151 – 155 [6]Feng Lin, Xiangxu Dong, Ben M. Chen, Kai-Yew Lum, Tong H. Lee “A Robust Real-Time Embedded Vision System on an Unmanned Rotorcraft for Ground Target Following” IEEE Transactions on Industrial Electronics, February 2012 VOL. 59, NO. 2, pp.1038 – 1049 [7]Feng Xue, Zengwei Jiang, “An Improved Mean Shift Algorithm For Object Tracking”, 2011 International Conference on Multimedia Technology, pp.4833 – 4836 [8]Gang Tian, Rui-Min Hu, Zhong-Yuan Wang, Zhu Li, “Object Tracking Algorithm Based on Meanshift Algorithm Combining with Motion Vector analysis”, 2009 First International Workshop on Education Technology and Computer Science Vol.1 pp.987 - 990 [9]Hui-xuan Fu, Feng Sun, and Sheng Liu,“Anti-occlusion Tracking Algorithm Based on LSSVM Prediction and Kalman-MeanShift”, 2010 8th World Congress Intelligent Control and Automation, pp.6031 – 6036 [10]Kai Zhou, Rui-Xia Fan, Wei-Xing Li, “A MeanShift-Particle Fusion Tracking Algorithm Based on SIFT”, 2010 29th Chinese Control Conference, pp.2717 - 2720 [11]Kwang In Kim, Keechul Jung, and Jin Hyung Kim, “Texture-Based Approach for Text Detection in Images Using Support Vector Machines and Continuously Adaptive Mean Shift Algorithm” , IEEE Transactions on Pattern Analysis and Machine Intelligence, December 2003, Vol. 25, No.12 pp.1631 – 1639 [12]Min-Chun Hu,Ming-Hsiu Chang, Ja-Ling Wu, Lin Chi, “Robust Camera Calibration and Player Tracking in Broadcast Basketball Video”, IEEE Transactions on Multimedia, April 2011, Vol. 13, No. 2, pp.266 – 279 [13]Mingxin Jiang, Min Li and Hongyu Wang, “A Robust Combined Algorithim of Object Tracking Based on Moving Object Detection” 2010 International Conference on Intelligent Control and Information Processing, pp.619 – 622 [14]Olivares-Mendez, Miguel A., Mondragon, Ivan, Campoy Cervera, Pascual, Mejias, Luis, & Martinez, Carol (2011) “Aerial object following using visual fuzzy servoing” . Centro Avanzado de Tecnologías Aeroespaciales, Seville, Spain, pp. 61-70. [15]Ould-Dris Nouar, Ganoun Ali, and Canals Raphaël , “Improved Object Tracking with CAMSHIFT Algorithm”,in proceedings 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.II [16]Peter Meer,Dorin Comaniciu,Visvanathan Ramesh , “Real-Time tracking of Non-Rigid Objects using Mean Shift”, in Proceedings 2000 IEEE Conference Computer Vision and Pattern Recognition . Vol.2 pp.142 -149 [17]Prahlad Vadakkepat, Peter Lim, Liyanage C. De Silva, Liu Jing, Li Li Ling, “Multimodal Approach to Human-Face Detection and Tracking”, IEEE Transactions on Industrial Electronics, March 2008, Vol. 55, No. 3, pp.1385 - 1393 [18]Rustam Stolkin, Ionut Florescu, Morgan Baron, Colin Harrier and Boris Kocherov, “Efficient visual servoing with the ABCshift tracking algorithm”, 2008 IEEE International Conference on Robotics and Automation, pp.3219 – 3224 [19]Shuhua Li, Gaizhi Guo, “The application of improved HSV color space model in image processing”, 2010 2nd International Conference on Future Computer and Communication (ICFCC), Vol.2 pp.10 – 13 [20]Weiguo Zhang, Xin Tian, “New Method of Object Tracking under Complex Circumstance”, 2010 International Conference on E-Business and E-Government pp.1613 - 1615 [21]Yonghong Long, Xiyu Xiao, Xiaohua Shu, Shenglan Chen, “Vehicle Tracking Method Using Background Subtraction and MeanShift Algorithm”, 2010 International Conference on E-Product E-Service and E-Entertainment, pp.1 – 4 [22]Zhelong Wang, Chuan Dai, Hongyu Zhao, “A Real Time Object Tracking System for Contrast Media Injection”, 2010 IEEE International Conference on Systems Man and Cybernetics (SMC) , pp.3749 – 3753
摘要: 
物件追蹤是影像視覺中應用很廣泛的領域,它可以應用在很多地方,像是行車系統、監視系統等等。本篇論文探討如何利用物件追蹤的方法應用在機器人的視覺上。我們使用調整過的CAMSHIFT演算法用在機器人上對物體追蹤,為了讓CAMSHIFT演算法能夠成功地用在機器人上,我們加入一些影像處理的技術強化它的準確性,並且用多重的CAMSHIFT演算法,使之在追蹤失敗時,在某種程度上還可以重新在影像中找回被追蹤的物體。
我們用樂高積木組裝成車子的形狀充當機器人,藉由程式來控制馬達的轉動,以達成移動的動作,再配合網路攝影機讀取到的畫面來判斷要做哪一種的移動。我們的貢獻主要著重在多重的CAMSHIFT演算法能夠有效地找回追蹤失敗的物件重新做追蹤,以達到機器人應用的實用性。

Object tracking is a kind of research widely used in image processing. It can be used in many cases, such as driving support system, monitoring, and robotic vision. In this thesis, we discuss how to adopt object tracking to robotic vision. We modify CAMSHIFT algorithm and apply it to a robot to do self-tracking on the specific object. In order to make it more successful on the robot, we use some techniques of image processing for robustness, and use multi-CAMSHIFT algorithm to recover from the failure of tracking, which makes it find the target object which CAMSHIFT algorithm missed.
We use LEGO NXT bricks to construct a car-shaped robot, and combine it with a webcam. We write programs to control the robot and let it drive automatically. It will automatically decide to do which kind of movement depends on the images that webcam captured. Our contributions mainly focus on using multi-CAMSHIFT algorithm to find the missing target object, and on making the robot re-tracking to improve the robustness of application.
URI: http://hdl.handle.net/11455/19758
Appears in Collections:資訊科學與工程學系所

Files in This Item:
File SizeFormat Existing users please Login
nchu-101-7099056035-1.pdf2.19 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record
 

Google ScholarTM

Check


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