AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
Improving these components will further advance the state of the art of online object tracking

Online Object Tracking: A Benchmark

CVPR, no. 1 (2013): 2411-2418

Cited: 5635|Views196
EI WOS

Abstract

Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online obje...More

Code:

Data:

0
Introduction
  • Object tracking is one of the most important components in a wide range of applications in computer vision, such as surveillance, human computer interaction, and medical imaging [60, 12].
  • There exist several datasets for visual tracking in the surveillance scenarios, such as the VIVID [13], CAVIAR [21], and PETS databases.
  • Some tracking datasets [47, 5, 33] for generic scenes are annotated with bounding box, most of them are not.
  • For sequences without labeled ground truth, it is difficult to evaluate tracking algorithms as the reported results are based on inconsistently annotated object locations
Highlights
  • Object tracking is one of the most important components in a wide range of applications in computer vision, such as surveillance, human computer interaction, and medical imaging [60, 12]
  • Object tracking has been studied for several decades, and much progress has been made in recent years [28, 16, 47, 5, 40, 26, 19], it remains a very challenging problem
  • For better evaluation and analysis of the strength and weakness of tracking approaches, we propose to categorize the sequences by annotating them with the 11 attributes shown in Table 2
  • For temporal robustness evaluation, each sequence is partitioned into 20 segments and each tracker is performed on around 310,000 frames
  • We report the most important findings in this manuscript and more details and figures can be found in the supplement
  • Improving these components will further advance the state of the art of online object tracking
Results
  • The default parameters with the source code are used in all evaluations.
  • More detailed speed statistics, such as minimum and maximum, are available in the supplement.
  • For OPE, each tracker is tested on more than 29,000 frames.
  • For SRE, each tracker is evaluated 12 times on each sequence, where more than 350,000 bounding box results are generated.
  • For TRE, each sequence is partitioned into 20 segments and each tracker is performed on around 310,000 frames.
  • The authors report the most important findings in this manuscript and more details and figures can be found in the supplement
Conclusion
  • Concluding Remarks

    In this paper, the authors carry out large scale experiments to evaluate the performance of recent online tracking algorithms.
  • Local models are important for tracking as shown in the performance improvement of local sparse representation (e.g., ASLA and SCM) compared with the holistic sparse representation (e.g., MTT and L1APG)
  • They are useful when the appearance of target is partially changed, such as partial occlusion or deformation.
  • Good location prediction based on the dynamic model could reduce the search range and improve the tracking efficiency and robustness
  • Improving these components will further advance the state of the art of online object tracking
Tables
  • Table1: Evaluated tracking algorithms (MU: model update, FPS: frames per second). For representation schemes, L: local, H: holistic, T: template, IH: intensity histogram, BP: binary pattern, PCA: principal component analysis, SPCA: sparse PCA, SR: sparse representation, DM: discriminative model, GM: generative model. For search mechanism, PF: particle filter, MCMC: Markov Chain Monte Carlo, LOS: local optimum search, DS: dense sampling search. For the model update, N: No, Y: Yes. In the Code column, M: Matlab, C:C/C++, MC: Mixture of Matlab and C/C++, suffix E: executable binary code
  • Table2: List of the attributes annotated to test sequences. The threshold values used in this work are also shown
Download tables as Excel
Related work
  • In this section, we review recent algorithms for object tracking in terms of several main modules: target representation scheme, search mechanism, and model update. In addition, some methods have been proposed that build on combing some trackers or mining context information. Representation Scheme. Object representation is one of major components in any visual tracker and numerous schemes have been presented [35]. Since the pioneering work of Lucas and Kanade [37, 8], holistic templates (raw intensity values) have been widely used for tracking [25, 39, 2]. Subsequently, subspace-based tracking approaches [11, 47] have been proposed to better account for appearance changes. Furthermore, Mei and Ling [40] proposed a tracking approach based on sparse representation to handle the corrupted appearance and recently it has been further improved [41, 57, 64, 10, 55, 42]. In addition to template, many other visual features have been adopted in tracking algorithms, such as color histograms [16], histograms of oriented gradients (HOG) [17, 52], covariance region descriptor [53, 46, 56] and Haar-like features [54, 22]. Recently, the discriminative model has been widely adopted in tracking [15, 4], where a binary classifier is learned online to discriminate the target from the background. Numerous learning methods have been adapted to the tracking problem, such as SVM [3], structured output SVM [26], ranking SVM [7], boosting [4, 22], semiboosting [23] and multi-instance boosting [5]. To make trackers more robust to pose variation and partial occlusion, an object can be represented by parts where each one is represented by descriptors or histograms. In [1] several local histograms are used to represent the object in a pre-defined grid structure. Kwon and Lee [32] propose an approach to automatically update the topology of local patches to handle large pose changes. To better handle appearance variations, some approaches regarding integration of multiple representation schemes have recently been proposed [62, 51, 33]. Search Mechanism. To estimate the state of the target objects, deterministic or stochastic methods have been used. When the tracking problem is posed within an optimization framework, assuming the objective function is differentiable with respect to the motion parameters, gradient descent methods can be used to locate the target efficiently [37, 16, 20, 49]. However, these objective functions are usually nonlinear and contain many local minima. To alleviate this problem, dense sampling methods have been adopted [22, 5, 26] at the expense of high computational load. On the other hand, stochastic search algorithms such as particle filters [28, 44] have been widely used since they are relatively insensitive to local minima and computationally efficient [47, 40, 30]. Model Update. It is crucial to update the target representation or model to account for appearance variations. Matthews et al [39] address the template update problem for the Lucas-Kanade algorithm [37] where the template is updated with the combination of the fixed reference template extracted from the first frame and the result from the most recent frame. Effective update algorithms have also been proposed via online mixture model [29], online boosting [22], and incremental subspace update [47]. For discriminative models, the main issue has been improving the sample collection part to make the online-trained classifier more robust [23, 5, 31, 26]. While much progress has been made, it is still difficult to get an adaptive appearance model to avoid drifts. Context and Fusion of Trackers. Context information is also very important for tracking. Recently some approaches have been proposed by mining auxiliary objects or local visual information surrounding the target to assist tracking [59, 24, 18]. The context information is especially helpful when the target is fully occluded or leaves the image region [24]. To improve the tracking performance, some tracker fusion methods have been proposed recently. Santner et al [48] proposed an approach that combines static, moderately adaptive and highly adaptive trackers to account for appearance changes. Even multiple trackers [34] or multiple feature sets [61] are maintained and selected in a Bayesian framework to better account for appearance changes.
Funding
  • The work is supported partly by NSF CAREER Grant #1149783 and NSF IIS Grant #1152576
  • Wu is also with Nanjing University of Information Science and Technology, China and supported partly by NSFC Grant #61005027
Reference
  • A. Adam, E. Rivlin, and I. Shimshoni. Robust Fragments-based Tracking using the Integral Histogram. In CVPR, 2006.
    Google ScholarLocate open access versionFindings
  • N. Alt, S. Hinterstoisser, and N. Navab. Rapid Selection of Reliable Templates for Visual Tracking. In CVPR, 2010.
    Google ScholarLocate open access versionFindings
  • S. Avidan. Support Vector Tracking. PAMI, 26(8):1064–1072, 2004.
    Google ScholarLocate open access versionFindings
  • S. Avidan. Ensemble Tracking. PAMI, 29(2):261–271, 2008.
    Google ScholarLocate open access versionFindings
  • B. Babenko, M.-H. Yang, and S. Belongie. Visual Tracking with Online Multiple Instance Learning. In CVPR, 2009.
    Google ScholarLocate open access versionFindings
  • B. Babenko, M.-H. Yang, and S. Belongie. Robust Object Tracking with Online Multiple Instance Learning. PAMI, 33(7):1619–1632, 2011.
    Google ScholarLocate open access versionFindings
  • Y. Bai and M. Tang. Robust Tracking via Weakly Supervised Ranking SVM. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • S. Baker and I. Matthews. Lucas-Kanade 20 Years On: A Unifying Framework. IJCV, 56(3):221–255, 2004.
    Google ScholarLocate open access versionFindings
  • S. Baker, S. Roth, D. Scharstein, M. J. Black, J. Lewis, and R. Szeliski. A Database and Evaluation Methodology for Optical Flow. In ICCV, 2007.
    Google ScholarFindings
  • C. Bao, Y. Wu, H. Ling, and H. Ji. Real Time Robust L1 Tracker Using Accelerated Proximal Gradient Approach. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [13] R. Collins, X. Zhou, and S. K. Teh. An Open Source Tracking Testbed and Evaluation Web Site. In PETS, 2005.
    Google ScholarLocate open access versionFindings
  • [15] R. T. Collins, Y. Liu, and M. Leordeanu. Online Selection of Discriminative Tracking Features. PAMI, 27(10):1631–1643, 2005.
    Google ScholarLocate open access versionFindings
  • [16] D. Comaniciu, V. Ramesh, and P. Meer. Kernel-Based Object Tracking. PAMI, 25(5):564–577, 2003.
    Google ScholarLocate open access versionFindings
  • [17] N. Dalal and B. Triggs. Histograms of Oriented Gradients for Human Detection. In CVPR, 2005.
    Google ScholarLocate open access versionFindings
  • [18] T. B. Dinh, N. Vo, and G. Medioni. Context Tracker: Exploring Supporters and Distracters in Unconstrained Environments. In CVPR, 2011.
    Google ScholarLocate open access versionFindings
  • [19] J. Fan, X. Shen, and Y. Wu. Scribble Tracker: A Matting-based Approach for Robust Tracking. PAMI, 34(8):1633–1644, 2012.
    Google ScholarLocate open access versionFindings
  • [20] J. Fan, Y. Wu, and S. Dai. Discriminative Spatial Attention for Robust Tracking. In ECCV, 2010.
    Google ScholarLocate open access versionFindings
  • [22] H. Grabner, M. Grabner, and H. Bischof. Real-Time Tracking via On-line Boosting. In BMVC, 2006.
    Google ScholarLocate open access versionFindings
  • [23] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised On-Line Boosting for Robust Tracking. In ECCV, 2008.
    Google ScholarLocate open access versionFindings
  • [24] H. Grabner, J. Matas, L. V. Gool, and P. Cattin. Tracking the Invisible: Learning Where the Object Might be. In CVPR, 2010.
    Google ScholarLocate open access versionFindings
  • [25] G. D. Hager and P. N. Belhumeur. Efficient Region Tracking With Parametric Models of Geometry and Illumination. PAMI, 20(10):1025–1039, 1998.
    Google ScholarLocate open access versionFindings
  • [26] S. Hare, A. Saffari, and P. H. S. Torr. Struck: Structured Output Tracking with Kernels. In ICCV, 2011.
    Google ScholarLocate open access versionFindings
  • [27] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. In ECCV, 2012.
    Google ScholarLocate open access versionFindings
  • [28] M. Isard and A. Blake. CONDENSATION–Conditional Density Propagation for Visual Tracking. IJCV, 29(1):5–28, 1998.
    Google ScholarLocate open access versionFindings
  • [29] A. D. Jepson, D. J. Fleet, and T. F. El-Maraghi. Robust Online Appearance Models for Visual Tracking. PAMI, 25(10):1296–1311, 2003.
    Google ScholarLocate open access versionFindings
  • [30] X. Jia, H. Lu, and M.-H. Yang. Visual Tracking via Adaptive Structural Local Sparse Appearance Model. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [31] Z. Kalal, J. Matas, and K. Mikolajczyk. P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints. In CVPR, 2010.
    Google ScholarLocate open access versionFindings
  • [32] J. Kwon and K. M. Lee. Tracking of a Non-Rigid Object via Patchbased Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling. In CVPR, 2009.
    Google ScholarLocate open access versionFindings
  • [33] J. Kwon and K. M. Lee. Visual Tracking Decomposition. In CVPR, 2010.
    Google ScholarLocate open access versionFindings
  • [34] J. Kwon and K. M. Lee. Tracking by Sampling Trackers. In ICCV, 2011.
    Google ScholarLocate open access versionFindings
  • [35] X. Li, W. Hu, C. Shen, Z. Zhang, A. Dick, and A. Hengel. A Survey of Appearance Models in Visual Object Tracking. TIST, 2013, in press.
    Google ScholarLocate open access versionFindings
  • [36] B. Liu, J. Huang, L. Yang, and C. Kulikowsk. Robust Tracking using
    Google ScholarFindings
  • [37] B. D. Lucas and T. Kanade. An Iterative Image Registration Technique with An Application to Stereo Vision. In IJCAI, 1981.
    Google ScholarLocate open access versionFindings
  • [38] D. R. Martin, C. C. Fowlkes, and J. Malik. Learning to Detect Natural
    Google ScholarLocate open access versionFindings
  • [39] I. Matthews, T. Ishikawa, and S. Baker. The Template Update Problem. PAMI, 26(6):810–815, 2004.
    Google ScholarLocate open access versionFindings
  • [40] X. Mei and H. Ling. Robust Visual Tracking using L1 Minimization. In ICCV, 2009.
    Google ScholarLocate open access versionFindings
  • [41] X. Mei, H. Ling, Y. Wu, E. Blasch, and L. Bai. Minimum Error Bounded Efficient L1 Tracker with Occlusion Detection. In CVPR, 2011.
    Google ScholarLocate open access versionFindings
  • [42] X. Mei, H. Ling, Y. Wu, E. Blasch, and L. Bai. Efficient Minimum Error Bounded Particle Resampling L1 Tracker with Occlusion Detection. TIP, 2013, in press.
    Google ScholarLocate open access versionFindings
  • [43] S. Oron, A. Bar-Hillel, D. Levi, and S. Avidan. Locally Orderless Tracking. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [44] P. Perez, C. Hue, J. Vermaak, and M. Gangnet. Color-Based Probabilistic Tracking. In ECCV, 2002.
    Google ScholarLocate open access versionFindings
  • [45] P. Phillips, H. Moon, S. Rizvi, and P. Rauss. The FERET Evaluation Methodology for Face-Recognition Algorithms. PAMI, 22(10):1090–1104, 2000.
    Google ScholarLocate open access versionFindings
  • [46] F. Porikli, O. Tuzel, and P. Meer. Covariance Tracking using Model Update based on Lie Algebra. In CVPR, 2006.
    Google ScholarLocate open access versionFindings
  • [47] D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental Learning for Robust Visual Tracking. IJCV, 77(1):125–141, 2008.
    Google ScholarLocate open access versionFindings
  • [48] J. Santner, C. Leistner, A. Saffari, T. Pock, and H. Bischof. PROST: Parallel Robust Online Simple Tracking. In CVPR, 2010.
    Google ScholarLocate open access versionFindings
  • [49] L. Sevilla-Lara and E. Learned-Miller. Distribution Fields for Tracking. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [50] S. Stalder, H. Grabner, and L. van Gool. Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition. In ICCV Workshop, 2009.
    Google ScholarLocate open access versionFindings
  • [51] B. Stenger, T. Woodley, and R. Cipolla. Learning to Track with Multiple Observers. In CVPR, 2009.
    Google ScholarLocate open access versionFindings
  • [52] F. Tang, S. Brennan, Q. Zhao, and H. Tao. Co-Tracking Using SemiSupervised Support Vector Machines. In CVPR, 2007.
    Google ScholarLocate open access versionFindings
  • [53] O. Tuzel, F. Porikli, and P. Meer. Region Covariance: A Fast Descriptor for Detection and Classification. In ECCV, 2006.
    Google ScholarLocate open access versionFindings
  • [54] P. Viola and M. J. Jones. Robust Real-Time Face Detection. IJCV, 57(2):137–154, 2004.
    Google ScholarLocate open access versionFindings
  • [55] D. Wang, H. Lu, and M.-H. Yang. Online Object Tracking with Sparse Prototypes. TIP, 22(1):314–325, 2013.
    Google ScholarLocate open access versionFindings
  • [56] Y. Wu, J. Cheng, J. Wang, H. Lu, J. Wang, H. Ling, E. Blasch, and L. Bai. Real-time Probabilistic Covariance Tracking with Efficient Model Update. TIP, 21(5):2824–2837, 2012.
    Google ScholarLocate open access versionFindings
  • [57] Y. Wu, H. Ling, J. Yu, F. Li, X. Mei, and E. Cheng. Blurred Target Tracking by Blur-driven Tracker. In ICCV, 2011.
    Google ScholarLocate open access versionFindings
  • [58] Y. Wu, B. Shen, and H. Ling. Online Robust Image Alignment via Iterative Convex Optimization. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [59] M. Yang, Y. Wu, and G. Hua. Context-Aware Visual Tracking. PAMI, 31(7):1195–1209, 2008.
    Google ScholarLocate open access versionFindings
  • [60] A. Yilmaz, O. Javed, and M. Shah. Object Tracking: A Survey. ACM Computing Surveys, 38(4):1–45, 2006.
    Google ScholarLocate open access versionFindings
  • [61] J. H. Yoon, D. Y. Kim, and K.-J. Yoon. Visual Tracking via Adaptive Tracker Selection with Multiple Features. In ECCV, 2012.
    Google ScholarLocate open access versionFindings
  • [62] L. Yuan, A. Haizhou, T. Yamashita, L. Shihong, and M. Kawade. Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Life Spans. PAMI, 30(10):1728–1740, 2008.
    Google ScholarLocate open access versionFindings
  • [63] K. Zhang, L. Zhang, and M.-H. Yang. Real-time Compressive Tracking. In ECCV, 2012.
    Google ScholarLocate open access versionFindings
  • [64] T. Zhang, B. Ghanem, S. Liu, and N. Ahuja. Robust Visual Tracking via Multi-task Sparse Learning. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
  • [65] W. Zhong, H. Lu, and M.-H. Yang. Robust Object Tracking via Sparsity-based Collaborative Model. In CVPR, 2012.
    Google ScholarLocate open access versionFindings
0
Your rating :

No Ratings

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn