Abstract
We consider the problem of detection and tracking of multiple people in crowded street scenes. State-of-the-art methods perform well in scenes with relatively few people, but are severely challenged by scenes with many subjects that partially occlude each other. This limitation is due to the fact that current people detectors fail when persons are strongly occluded. We observe that typical occlusions are due to overlaps between people and propose a people detector tailored to various occlusion levels. Instead of treating partial occlusions as distractions, we leverage the fact that person/person occlusions result in very characteristic appearance patterns that can help to improve detection results. We demonstrate the performance of our occlusion-aware person detector on a new dataset of people with controlled but severe levels of occlusion and on two challenging publicly available benchmarks outperforming single person detectors in each case.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
The training and test datasets are available at www.d2.mpi-inf.mpg.de/datasets
References
Andriluka, M., Roth, S., & Schiele, B. (2008). People-tracking-by-detection and people-detection-by-tracking. In CVPR’08.
Andriyenko, A., & Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In CVPR’11.
Andriyenko, A., Schindler, K., & Roth, S. (2012). Discrete-continuous optimization for multi-target tracking. In CVPR’12.
Barinova, O., Lempitsky, V., & Kohli, P. (2010). On detection of multiple object instances using hough transform. In CVPR’10.
Bernardin, K. & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The CLEAR MOT metrics. Image and Video Processing, 1, 1–10.
Bourdev, L., & Malik J. (2009). Poselets: Body part detectors trained using 3D human pose annotations. In ICCV’09.
Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., & Van Gool, L. (2009). Robust tracking-by-detection using a detector confidence particle filter. In ICCV’09.
Desai, C., & Ramanan, D. (2012). Detecting actions, poses, and objects with relational phraselets. In ECCV’12.
Dollár, P., Wojek, C., Schiele, B., & Perona, P. (2009). Pedestrian detection: A benchmark. In CVPR’09.
Enzweiler, M., Eigenstetter, A., Schiele, B., & Gavrila, D. M. (2010). Multi-cue pedestrian classification with partial occlusion handling. In CVPR’10.
Farhadi, A., & Sadeghi, M. A. (2011). Recognition using visual phrases. In CVPR’11.
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part-based models. In PAMI’10.
Girshick, R. B., Felzenszwalb, P. F., & McAllester, D. (2010). LSVM-MDPM Release 4 Notes.
Huang, C., Wu, B., & Nevatia, R. (2008). Robust object tracking by hierarchical association of detection responses. In ECCV’08.
Leibe, B., Seemann, E., & Schiele, B. (2005). Pedestrian detection in crowded scenes. In CVPR’05.
Marin, J., Vazquez, D., Geronimo, D., & Lopez, A. M. (2010). Learning appearance in virtual scenarios for pedestrian detection. In CVPR’10.
Ouyang, W., & Wang, X. (2013). Single-pedestrian detection aided by multi-pedestrian detection. In CVPR’13.
Pepik, B., Stark, M., Gehler, P., & Schiele, B. (2013). Occlusion patterns for object class detection. In CVPR’13.
Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011). Globally-optimal greedy algorithms for tracking a variable number of objects. In CVPR’11.
Pishchulin, L., Jain, A., Wojek, C., Andriluka, M., Thormählen, T., & Schiele, B. (2011). Learning people detection models from few training samples. In CVPR’11.
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., & Blake, A. (2011). Real-time human pose recognition in parts from a single depth image. In CVPR’11.
Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., & Schiele, B. (2013). Learning people detectors for tracking in crowded scenes. In ICCV’13.
Tang, S., Andriluka, M., & Schiele, B. (2012). Detection and tracking of occluded people. In BMVC’12.
Walk, S., Majer, N., Schindler, K., & Schiele, B. (2010). New features and insights for pedestrian detection. In CVPR’10.
Wang, X., Han, T. X., & Yan, S. (2009). An hog-lbp human detector with partial occlusion handling. In ICCV’09.
Wojek, C., Walk, S., Roth, S., & Schiele, B. (2011). Monocular 3d scene understanding with explicit occlusion reasoning. In CVPR’11.
Wu, B., & Nevatia, R. (2007). Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. In IJCV’07.
Acknowledgments
The authors are thankful to Bojan Pepik for the code and suggestion on DPM and to Anton Andriyenko for the help with the multi-people tracking evaluation.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tang, S., Andriluka, M. & Schiele, B. Detection and Tracking of Occluded People. Int J Comput Vis 110, 58–69 (2014). https://doi.org/10.1007/s11263-013-0664-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-013-0664-6