|
|
![]() |
|
當前位置：首頁 >
優秀論文
|
|
|
基于判別分類器的目標跟蹤方法綜述 |
|
| 作者：葉靜1，雷軍2，吳昊3，彭冒琦1，薛楠1 |
| 來源：本站原創 |
| 更新時間：2013/7/15 15:06:00 |
| 正文： |
(1 63801部隊，西昌，615000)
（2 國防科學技術大學信息系統與管理學院系統工程系, 長沙 410073）
（3 63928部隊 北京 100000）
A survey of object tracking based on discriminative classifier methods
Ye Jing, Lei Jun, Wu Hao, Peng Maoqi, Xue Nan
(1 63801 force, Xichang,615000,China)
(2 Dept. of System Engineering, College of Information System and Management, National University of Defense Technology, Changsha, 410073, China)
(3 63928 force, Beijing,100000,China)
Abstract: The task of object tracking is to estimate the trajectory of moving object in the sequence of images and it is one of the most important problems in computer visual. Traditional object tracking methods namely generative methods, try to track object by building a generative model to describe the visual appearance of the object. Recent years, discriminative classifier method achieves good effect in the application of object tracking. Discriminative classifier method treats object tracking as a problem of distinguishing between object and background. This paper firstly describes the generative method briefly. Then discusses the evolution of discriminative classifier method, categories those algorithms and gives the motivation and basic theories of each algorithm. Finally, compare discriminative classifier methods and generative methods and outline the future trends for object tracking.
Key words: object tracking; generative method; discriminative method; classifier.
摘 要：目標跟蹤是在連續圖像幀中估計出運動目標的運動軌跡，是計算機視覺中的重要問題之一。傳統的目標跟蹤方法即生成模型法，是通過建立描述目標的外觀模型來實現目標跟蹤。近年來，判別分類法在目標跟蹤應用中取得了較好的效果，判別分類法將目標跟蹤問題看作目標與背景的分類問題。本論文首先對生成模型法做了簡單介紹，然后討論了判別分類法的發展過程，并對判別分類法的各種算法進行了分類，闡述了各種算法提出的動機和基本原理，最后對兩類方法做了對比和展望，并概括了目標跟蹤方法的發展方向。
關鍵詞：目標跟蹤；生成模型法；判別分類法；分類器
中圖法分類號: TP37 文獻標識碼: A
參考文獻：
[1] Tang F, Brennan S, Zhao Q, Tao H. Co-Tracking Using Semi-Supervised Support Vector Machines [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2007: 1-8.
[2] Stalder S, Grabner H, van Gool L. Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition [C] // International Conference on Computer Vision, 2009:1409-1416.
[3] Santner J, Leistner C, Saffari A, et al. PROST: Parallel Robust Online Simple Tracking [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2010: 723-730.
[4] Grabner H, Leistner C, Bischof H. Semi-Supervised Online Boosting for Robust Tracking [C] // European Conference on Computer Vision, 2008:234-247.
[5] Jepson A.D., Fleet D.J., El-Maraghi T. F. Robust online appearance models for visual tracking [J], IEEE Transaction on Pattern Analysis and Machine Intelligence. 2003, 25(10), 1296-1311.
[6] Shaohua Kevin Zhou, R. Chellappa, B. Moghaddam, Visual tracking and recognition using appearance-adaptive models in particle filters, IEEE Trans. Image Process [J]. 2004, 13(11):1491-1506.
[7] Lee K, Kriegman D. Online learning of probabilistic appearance manifolds for video-based recognition and tracking [C] // In: Proceedings Computer Vision and Pattern Recognition, 2005:852–859.
[8] Xi Li, Weiming Hu, Zhongfei Zhang, et. al. Robust Visual Tracking Based on Incremental Tensor Subspace Learning [C] // In Proc. of IEEE international conference on computer vision, 2007:1-8.
[9] Faruqi F A, Davis R C. Kalman Filter Design for Target Tracking, IEEE Transactions on Aerospace and Electronic Systems [J], 1980, AES-16(4): 500-508.
[10] Arnaud E, Memin E, Cernuschi-Frias B. Conditional Filters for Image Sequence-Based Tracking---Application to Point Tracking [J], IEEE Transactions on Image Processing, 2005, 14(1): 63-79.
[11] Avidan S. Support Vector Machine [J], IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 8(26): 1064-1072.
[12] Avidan S. Ensemble Tracking [C], IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2005, 724-730.
[13] Yu Q, Dinh T B, Medioni G. Online Tracing and Reacquisition Using Co-trained Generative and Discriminative Trackers [C] // European Conference on Computer Vision, 2008: 678-691.
[14] Grabner H, Grabner M, Bischof H. Real-time Tracking via On-line Boosting [C] // British Machine Vision Conference, 2006:47-56.
[15] Babenko B, Yang M H, Belongie S. Visual Tracking with Online Multiple Instance Learning [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2009: 983-990.
[16] 焦波. 面向智能視頻監控的運動目標檢測與跟蹤技術研究 [D]. 博士論文. 國防科學技術大學, 2009.
[17] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2005:886-893.
[18] Grabner H, Bishof H. On-line Boosting and vision [C], IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2006:260-267.
[19] Grabner M, Grabner H, Bischof H. Learning Features for Tracking [C] // European Conference on Computer Vision, 2008:1-8.
[20] Kalal Z, Matas J, Mikolajczyk K. P-N learning: robust object tracking [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2010: 49-56.
[21] Kalal Z, Mikolajczyk K, Matas J. Forward-Backward Error: Autonomous Detection of Tracking Failures [C] // International Conference on Pattern Recognition, 2010:23-26.
[22] Kalal Z, Mikolajczyk K, Matas J. Face-TLD: Tracking-Learning-Detection Applied to Faces [C] // International Conference on Image Processing, 2010:3789-3792.
[23] Kalal Z, Matas J, Mikolajczyk K. P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints [C] // IEEE Computer Society Conference on Computer vision and Pattern Recognition, 2010:49-56.
[24] Kalal Z, Matas J, Mikolajczyk K. Online learning of robust object detectors during unstable tracking [J], On-line Learning for Computer Vision Workshop, 2009, 1417-1424.
[25] Kalal Z, Matas J, Mikolajczyk K. Weighted Sampling for Large-Scale Boosting [C] // British Machine Vision Conference, 2008.
[26] Yang H X, Shao L, Zheng F, et al. Recent advances and trends in visual tracking: A review [J], Neruocomputing, 2011, 74(2011): 3823-3831.
作者簡介：
葉靜（1988年--），女，浙江金華人，助理工程師，國防科學技術大學碩士研究生，現就職于西昌市63801部隊，現主要從事圖像處理與數據挖掘工作。
|
|
|
|
|
