Abstract
We consider real-time visual tracking with targets undergoing viewpoint changes. The problem is evaluated on a new and extensive dataset of vehicles undergoing large viewpoint changes. We propose an evaluation method in which tracking accuracy is measured under real-time computational complexity constraints and find that state-of-the-art agnostic trackers, as well as class detectors, are still struggling with this task. We study tracking schemes fusing real-time agnostic trackers with a non-real-time class detector used for template update, with two dominating update strategies emerging. We rigorously analyze the template update latency and demonstrate that such methods significantly outperform stand-alone trackers and class detectors. Results are demonstrated using two different trackers and a state-of-the-art classifier, and at several operating points of algorithm/hardware computational speed.
Similar content being viewed by others
References
Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: CVPR (2008)
Avidan, S.: Support vector tracking. In: PAMI (2004)
Avidan, S.: Ensemble tracking. In: CVPR (2005)
Babenko, B., Yang, M., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR (2009)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust l1 tracker using accelerated proximal gradient approach. In: CVPR (2012)
Bar-Hillel, A., Levi, D., Krupka, E., Goldberg, C.: Part-based feature synthesis for human detection. In: ECCV (2010)
Benenson, R., Mathias, M., Timofte, R., Van Gool, L.: Pedestrian detection at 100 frames per second. In: CVPR (2012)
Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. EURASIP J. Image Video Process. (2008)
Cootes, T., Edwards, G., Taylor, C.: Active appearance models. In: TPAMI (2001)
Dollár, P., Belongie, S., Perona, P.: The fastest pedestrian detector in the west. In: BMVC (2010)
Ess, A., Leibe, B., Schindler, K., Van-Gool, L.: Robust multi-person tracking from a mobile platform. In: TPAMI (2009)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results. http://www.pascal-network.org/challenges/VOC/voc2011/workshop/index.html
Fan, J., Shen, X., Wu, Y.: What are we tracking: a unified approach of tracking and recognition. IEEE Trans. Image Process. 22(2), 549–560 (2013)
Felzenszwalb, P., Girshick, R., McAllester, D.: Discriminatively Trained Deformable Part Models, Release 4. http://people.cs.uchicago.edu/pff/latent-release4/
Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade object detection with deformable part models. In: CVPR (2010)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. In: TPAMI (2010)
Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. In: IJCV 61(1) (2005)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: CVPR (2012)
Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via online boosting. In: BMVC (2006)
Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. In: TPAMI (1998)
Jia, X., Lu, H., Yang, M.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR (2012)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. In: TPAMI (2010)
Kasturi, R., Goldgof, D., Manohar, S., Garofolo, J., Bowers, R., Boonstra, M., Korzhova, V., Zhang, J.: Framework for performance evaluation of face, text, and vehicle detection and tracking in video: data, metrics, and protocol. In: PAMI (2009)
Kwon, J., Lee, K.: Visual tracking decomposition. In: CVPR (2010)
Leibe, B., Schindler, K., Cornelis, N., Van-Gool, L.: Coupled object detection and tracking from static cameras and moving vehicles. In: TPAMI (2008)
Leichter, I., Krupka, E.: Monotonicity and error type differentiability in performance measures for target detection and tracking in video. In: CVPR (2012)
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proccedings of Imageing Understanding Workshop (1981)
Matthews, I., Baker, S.: Lucas-kanade 20 years on: a unifying framework. In: IJCV (2004)
Matthews, I., Ishikawa, T., Baker, S.: The template update problem. In: TPAMI (2004)
Oron, S., Bar-Hillel, A., Levi, D., Avidan, S.: Locally orderless tracking. In: CVPR (2012)
Panin, G., Klose, S., Knoll, A.: Real-time articulated hand detection and pose estimation. In: Advances in Visual Computing (2009)
Papanikolopoulos, N., Khosla, P., Kanade, T.: Visual tracking of a moving target by a camera mounted on a robot: a combination of control and vision. In: IEEE Transactions on Robotics and Automation (1993)
Ross, D., Lim, J., Lin, R., Yang, M.: Incremental learning for robust visual tracking. In: IJCV (2007)
Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: Prost:parallel robust online simple tracking. In: CVPR (2010)
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: CVPR (2011)
Siebel, N., Maybank, S.: Fusion of multiple tracking algorithms for robust people tracking. In: ECCV (2002)
Stalder, S., Grabner, H., van Gool, L.: Beyond semi-supervised tracking: tracking should be as simple as detection, but not simpler than recognition. In: ICCV Workshops (2009)
Stauffer, C., Grimson, E.: Learning patterns of activity using real-time tracking. In: PAMI (2000)
Thirteenth IEEE International Workshop On Performance Evaluation Of Tracking And Surveillance (Pets) (2010)
Williams, O., Blake, A., Cipolla, R.: Sparse bayesian learning for efficient visual tracking. In: TPAMI (2005)
Wu, Y., Lim, J., Yang, M.: Online object tracking: a benchmark. In: CVPR (2005)
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comp. Surv. 38(4) (2006)
Zhang, K., Zhang, L., Yang, M.: Real-time compressive tracking. In: ECCV (2012)
Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparsity-based collaborative model. In: CVPR (2012)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Oron, S., Bar-Hillel, A. & Avidan, S. Real-time tracking-with-detection for coping with viewpoint change. Machine Vision and Applications 26, 507–518 (2015). https://doi.org/10.1007/s00138-015-0676-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-015-0676-z