Fusion of Head and Full-Body Detectors for Multi-object Tracking
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
An algorithm for quadratic programming
Frank, M., & Wolfe, P. (1956) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800030109 · Cited by 3,030 · cited 1×
“We propose to use a BQP formulation for the clustering problem that can be well approximated using the Frank-Wolfe [22] solver.”
MethodEvaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics
Bernardin, K., & Stiefelhagen, R. (2008) · EURASIP Journal on Image and Video Processing · doi:10.1155/2008/246309 · Cited by 2,918
MOT16: A Benchmark for Multi-Object Tracking
Milan, A., Leal-Taixe, L., Reid, I., Roth, S., & Schindler, K. (2016) · arXiv · doi:10.48550/arxiv.1603.00831 · Cited by 1,309 · cited 3×
“Next, we investigate the impact of the detector fusion on the tracking performance, using the training sequences of the challenging MOT16 benchmark [43].”
MethodMultiple Object Tracking Using K-Shortest Paths Optimization
Berclaz, J., Fleuret, F., Turetken, E., & Fua, P. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.21 · Cited by 1,015
Globally-optimal greedy algorithms for tracking a variable number of objects
Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995604 · Cited by 790
Stable multi-target tracking in real-time surveillance video
Benfold, B., & Reid, I. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995667 · Cited by 651
Learning to associate: HybridBoosted multi-target tracker for crowded scene
Li, Y., Huang, C., & Nevatia, R. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206735 · Cited by 633
Yang, F., Choi, W., & Lin, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.234 · Cited by 608 · cited 1×
“In crowded environments, where occlusions are common, even state-of-the-art detectors [18, 19, 48, 62] are prone to false alarms and missed detections.”
BackgroundEnd-to-End People Detection in Crowded Scenes
Stewart, R., Andriluka, M., & Ng, A. Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.255 · Cited by 539 · cited 1×
“To obtain accurate head detections, we employ [55] based on Convolutional Neural Networks and fine-tune it on the MOT16 training set [43].”
Method
Cited by
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
Luiten, J., Os̆ep, A., Dendorfer, P., Torr, P., Geiger, A., Leal-Taixé, L., & Leibe, B. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01375-2 · Cited by 1,171
Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera
von Marcard, T., Henschel, R., Black, M. J., Rosenhahn, B., & Pons-Moll, G. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_37 · Cited by 1,058
Self-citationDeep learning in video multi-object tracking: A survey
Ciaparrone, G., Luque Sánchez, F., Tabik, S., Troiano, L., Tagliaferri, R., & Herrera, F. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.023 · Cited by 665
“[155] Public Body detections are refined using head detections obtained with a CNN [156].”
MethodMOTS: Multi-Object Tracking and Segmentation
Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., & Leibe, B. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00813 · Cited by 658
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
Dendorfer, P., Os̆ep, A., Milan, A., Schindler, K., Cremers, D., Reid, I., Roth, S., & Leal-Taixé, L. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01393-0 · Cited by 374
“A number of methods employ additional fine-grained detectors and incorporate their outputs into affinity measures, e.g., a head detector in the case of FWT (Henschel et al. 2018), or a body joint detectors in JBNOT (Henschel et al. 2019), which are shown to help sig-nificantly with occlusions.”
MethodSelf-citationPeng, J., Wang, C., Wan, F., Wu, Y., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., & Fu, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58548-8_9 · Cited by 372
TransTrack: Multiple Object Tracking with Transformer
Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., & Luo, P. (2020) · arXiv · doi:10.48550/arxiv.2012.15460 · Cited by 345
Deep Affinity Network for Multiple Object Tracking
Sun, S., AKHTAR, N., Song, H., Mian, A. S., & Shah, M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2929520 · Cited by 340
Learning Multi-Object Tracking and Segmentation From Automatic Annotations
Porzi, L., Hofinger, M., Ruiz, I., Serrat, J., Bulo, S. R., & Kontschieder, P. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00688 · Cited by 82
Metadata
- Authors
- Henschel, R., Leal-Taixe, L., Cremers, D., & Rosenhahn, B.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1509-150909
- OpenAlex
- W2798875622
- Cited by
- 149
- References
- 10
- FWCI
- 8.92
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.