Single-Task Joint Learning Model for an Online Multi-Object Tracking Framework
Source abstract
Abstract
Multi-object tracking faces critical challenges, including occlusions, ID switches, and erroneous detection boxes, which significantly hinder tracking accuracy in complex environments. To address these issues, this study proposes a single-task joint learning (STJL) model integrated into an online multi-object tracking framework to enhance feature extraction and model robustness across diverse scenarios. Employing cross-dataset training, the model has improved generalization capabilities and can effectively handle various tracking conditions. A key innovation is the refined tracker initialization strategy that combines detection and tracklet confidence, which significantly reduces the number of false positives and ID switches. Additionally, the framework employs a combination of Mahalanobis and cosine distances to optimize data association, further improving tracking accuracy. The experimental results demonstrate that the proposed model outperformed state-of-the-art methods on standard benchmark datasets, achieving superior MOTA and reduced ID switches, confirming its effectiveness in dynamic and occlusion-heavy environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Fire Detection and Safety Systems · Energy Efficient Wireless Sensor Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, Fu Jen Catholic University, New Taipei 242, Taiwan
Holistic Education Center, Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei 242, Taiwan
References (50)
Show source-provided references
1. Zhang, L., Li, Y., and Nevatia, R. (2008, January 23–28). Global data association for multi-object tracking using network flows. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA.
2. Cross-camera trajectories help person retrieval in a camera network10.1109/TIP.2023.3290515 ↗
3. Dai, P., Weng, R., Choi, W., Zhang, C., He, Z., and Ding, W. (2021, January 20–25). Learning a proposal classifier for multiple object tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00247 ↗
4. Efficient combination graph model based on conditional random field for online multi-object tracking10.1007/s40747-022-00922-3 ↗
5. Leon, F., and Gavrilescu, M. (2021). A review of tracking and trajectory prediction methods for autonomous driving. Mathematics, 9.10.3390/math9060660 ↗
6. Multi-Camera Multi-Object Tracking: A Review of Current Trends and Future Advances10.1016/j.neucom.2023.126558 ↗
7. Bae, S.-H., and Yoon, K.-J. (2014, January 23–28). Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.159 ↗
8. Bewley, A., Ge, Z., Ott, L., Ramos, F., and Upcroft, B. (2016). Simple Online and Realtime Tracking. arXiv.10.1109/ICIP.2016.7533003 ↗
9. A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects10.1109/TNNLS.2021.3084827 ↗
10. Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking10.1109/TPAMI.2017.2691769 ↗
11. A New Approach to Track Multiple Vehicles with the Combination of Robust Detection and Two Classifiers10.1109/TITS.2017.2756989 ↗
12. Wojke, N., Bewley, A., and Paulus, D. (2017, January 17–20). Simple online and realtime tracking with a deep association metric. Proceedings of the IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296962 ↗
13. Shafiq, M., and Gu, Z. (2022). Deep Residual Learning for Image Recognition: A Survey. Appl. Sci., 12.10.3390/app12188972 ↗
14. Multi-Metric Re-Identification for Online Multi-Person Tracking10.1109/TCSVT.2021.3059250 ↗
15. Chen, L., Ai, H., Shang, C., Zhuang, Z., and Bai, B. (2017, January 17–20). Online Multi-Object Tracking with Convolutional Neural Networks. Proceedings of the IEEE International Conference on Image Processing, Beijing, China.10.1109/ICIP.2017.8296360 ↗
16. Tian, R., Zhang, X., Chen, D., and Hu, Y. (2021, January 14–17). Multi-object Tracking Based on Nearest Optimal Template Library. Proceedings of the Artificial Neural Networks and Machine Learning–ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia. Proceedings, Part I 30.10.1007/978-3-030-86362-3_27 ↗
17. Wang, Y.-K., Guo, J., and Pan, T.-M. (2022). Multidomain Joint Learning of Pedestrian Detection for Application to Quadrotors. Drones, 6.10.3390/drones6120430 ↗
18. Li, W., Zhao, R., Xiao, T., and Wang, X. (2014, January 23–28). DeepReID: Deep Filter Pairing Neural Network for Person Re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.27 ↗
19. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., and Tian, Q. (2015, January 7–13). Scalable Person Re-identification: A Benchmark. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.133 ↗
20. Tracking Social Groups Within and Across Cameras10.1109/TCSVT.2016.2607378 ↗
21. A Survey on Multi-Task Learning10.1109/TKDE.2021.3070203 ↗
22. Yang, Y., Cui, H., and Yang, C. (2022, January 17–20). PTGN: Pre-Train Graph Neural Networks for Brain Network Analysis. Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.10.1109/BigData55660.2022.10020314 ↗
23. CNN Based Age Estimation Using Cross-Dataset Learning
24. Tokmakov, P., Li, J., Burgard, W., and Gaidon, A. (2021, January 10–17). Learning to Track with Object Permanence. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.01068 ↗
25. Cross-Dataset Learning for Age Estimation10.1109/ACCESS.2022.3154403 ↗
26. Joint domain symmetry and predictive balance for cross-dataset EEG emotion recognition10.1016/j.jneumeth.2023.109978 ↗
27. Gominski, D., Gouet-Brunet, V., and Chen, L. (2022, January 19–20). Cross-dataset Learning for Generalizable Land Use Scene Classification. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, LA, USA.10.1109/CVPRW56347.2022.00144 ↗
28. Image manipulation localization using attentional cross-domain cnn features10.1109/TNNLS.2021.3130168 ↗
29. Zhou, X., Koltun, V., and Krähenbühl, P. (2020). Tracking Objects as Points. European Conference on Computer Vision, Springer International Publishing.10.1007/978-3-030-58548-8_28 ↗
30. Pan, T.-M., Fan, K.-C., and Wang, Y.-K. (2019). Object-Based Approach for Adaptive Source Coding of Surveillance Video. Appl. Sci, 9.10.3390/app9102003 ↗
31. Intelligent Mobile Video Surveillance System with Multilevel Distillation
32. Heterogeneous Information Fusion and Visualization for a Large-Scale Intelligent Video Surveillance System10.1109/TSMC.2016.2531671 ↗
33. Wang, Y., Xu, B., Guo, X., and Yang, G. (2021, January 18–20). A Multi-task Deep Network for video-based Person Re-identification. Proceedings of the ICCIR’21: 2021 1st International Conference on Control and Intelligent Robotics, Guangzhou, China.10.1145/3473714.3473770 ↗
34. Zhao, H., Tian, M., Sun, S., Shao, J., Yan, J., Yi, S., Wang, X., and Tang, X. (2017, January 21–26). Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.103 ↗
35. Xiao, T., Li, H., Ouyang, W., and Wang, X. (July, January 26). Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
36. Sanchez-Matilla, R., Poiesi, F., and Cavallaro, A. (2016, January 8–16). Online Multi-target Tracking with Strong and Weak Detections. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-48881-3_7 ↗
37. Kim, H.-U., and Kim, C.-S. (2016). CDT: Cooperative Detection and Tracking for Tracing Multiple Objects in Video Sequences. European Conference on Computer Vision (ECCV), Springer.10.1007/978-3-319-46466-4_51 ↗
38. Xiang, Y., Alahi, A., and Savarese, S. (2015, January 7–13). Learning to Track: Online Multi-object Tracking by Decision Making. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.534 ↗
39. Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation10.1109/TPAMI.2016.2551245 ↗
40. Chu, P., Fan, H., Tan, C.C., and Ling, H. (2019, January 7–11). Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV.2019.00023 ↗
41. Wojke, N., and Bewley, A. (2018, January 12–15). Deep Cosine Metric Learning for Person Re-identification. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.10.1109/WACV.2018.00087 ↗
42. Large margin learning in set-to-set similarity comparison for person re-identification
43. Zheng, L., Yang, Y., and Hauptmann, A.G. (2016). Person Re-identification: Past, Present and Future. arXiv.
44. Zheng, L., Bie, Z., Sun, Y., Wang, J., Su, C., Wang, S., and Tian, Q. (2016). MARS: A Video Benchmark for Large-Scale Person Re-Identification. European Conference on Computer Vision, Springer.10.1007/978-3-319-46466-4_52 ↗
45. Li, M., Zhu, X., and Gong, S. (2018, January 8). Unsupervised Person Re-identification by Deep Learning Tracklet Association. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01225-0_45 ↗
46. Ferryman, J., and Shahrokni, A. (2009, January 7–9). PETS2009: Dataset and challenge. Proceedings of the 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Snowbird, UT, USA.10.1109/PETS-WINTER.2009.5399556 ↗
47. Mykhaylo, A., Stefan, R., and Bernt, S. (2008, January 23–28). People-Tracking-by-Detection and People-Detection-by-Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.
48. Le, Q.C., Conte, D., and Hidane, M. (2018, January 6). Online Multiple View Tracking: Targets Association Across Cameras. Proceedings of the 6th Workshop on Activity Monitoring by Multiple Distributed Sensing, Newcastle, UK.
49. Dynamic target tracking based on corner enhancement with Markov decision process
50. Online Multi-Object Tracking Using Hierarchical Constraints for Complex Scenarios10.1109/TITS.2017.2750058 ↗