Issue
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
LITE-BoostTrack: A Hybrid Real-Time Multi-Object Tracking Architecture for Resource-Constrained Environments
Corresponding Author(s) : Adhitya Nugraha
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control,
Vol. 11, No. 2, May 2026
Abstract
Multi-object tracking (MOT) is a fundamental task in computer vision that underpins applications such as intelligent surveillance, autonomous driving, and crowd analysis. The primary challenge in MOT lies in maintaining identity consistency under frequent occlusions while ensuring real-time performance on resource-constrained devices. This study proposes LITE-BoostTrack, a hybrid tracking framework that combines the confidence-based association mechanism of BoostTrack with the lightweight embedding strategy of the Lightweight Integrated Tracking and Embedding (LITE) architecture. The proposed model extracts appearance descriptors directly from the internal feature maps of the YOLOv8 detector, thereby eliminating the need for an external re-identification network. This design significantly reduces computational complexity while preserving reliable identity association. Experiments were conducted on the MOT20 benchmark using standard MOT evaluation metrics, including HOTA, MOTA, IDF1, IDSW, and FPS, to assess both tracking accuracy and runtime efficiency. The results show that LITE-BoostTrack achieves a HOTA of 27.31 and IDF1 of 37.48, outperforming LITE-BoT-SORT (HOTA 25.73, IDF1 33.88), while reducing identity switches by 37% (2,939 vs. 4,674) and maintaining real-time performance at 13.22 FPS. These outcomes demonstrate that substantial efficiency gains can be achieved through detector-level feature integration without introducing additional deep embedding modules. Although occasional failures still occur under severe occlusion, LITE-BoostTrack provides a balanced and practical solution that effectively combines accuracy and efficiency for real-time multi-object tracking in edge-computing and embedded vision systems.
Keywords
Download Citation
Endnote/Zotero/Mendeley (RIS)BibTeX
- M. A. Altaf and M. Y. Kim, “Multiple object detection and tracking in autonomous vehicles: A survey on enhanced affinity computation and its multimodal applications,” Aug. 01, 2025, Korean Institute of Communications and Information Sciences. https://doi.org/10.1016/j.icte.2025.06.005
- H. Wang, L. Jin, Y. He, Z. Huo, G. Wang, and X. Sun, “Detector–Tracker Integration Framework for Autonomous Vehicles Pedestrian Tracking,” Remote Sens. (Basel)., vol. 15, no. 8, Apr. 2023. https://doi.org/10.3390/rs15082088
- X. Zhou, Y. Jia, C. Bai, H. Zhu, and S. Chan, “Multi-object tracking based on attention networks for Smart City system,” Sustainable Energy Technologies and Assessments, vol. 52, Aug. 2022. https://doi.org/10.1016/j.seta.2022.102216
- M. Elshahawy, A. O. Aseeri, S. El-Sappagh, H. Soliman, M. Elmogy, and M. Abu-Elkheir, “Identification and Classification of Crowd Activities,” Computers, Materials and Continua, vol. 72, no. 1, pp. 815–832, 2022. https://doi.org/10.32604/cmc.2022.023852
- J. Yan, S. Du, and Y. Wang, “Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter,” IEEE Access, vol. 10, pp. 118512–118521, 2022. https://doi.org/10.1109/ACCESS.2022.3220635
- J. Alikhanov, D. Obidov, M. Abdurasulov, and H. Kim, “Practical Evaluation Framework for Real-Time Multi-Object Tracking: Achieving Optimal and Realistic Performance,” IEEE Access, vol. 13, pp. 34768–34788, 2025. https://doi.org/10.1109/ACCESS.2025.3541177
- P. Zhang, D. Wang, and H. Lu, “Multi-modal visual tracking: Review and experimental comparison,” Apr. 01, 2024, Tsinghua University. https://doi.org/10.1007/s41095-023-0345-5
- S. Honarparvar, Z. B. Ashena, S. Saeedi, and S. Liang, “A Systematic Review of Event-Matching Methods for Complex Event Detection in Video Streams,” Nov. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/s24227238
- Y. Li, Y. Liu, C. Zhou, D. Xu, and W. Tao, “A lightweight scheme of deep appearance extraction for robust online multi-object tracking,” Visual Computer, vol. 40, no. 3, pp. 2049–2065, Mar. 2024. https://doi.org/10.1007/s00371-023-02901-2
- L. Ye, W. Li, L. Zheng, and Y. Zeng, “Lightweight and Deep Appearance Embedding for Multiple Object Tracking,” IET Computer Vision, vol. 16, no. 6, pp. 489–503, Sep. 2022. https://doi.org/10.1049/cvi2.12106
- Z. Wan and W. Wu, “A robust approach to deformed pedestrian tracking with multi-trajectory prediction,” Cluster Comput., vol. 28, no. 5, Oct. 2025. https://doi.org/10.1007/s10586-024-05059-1
- V. M. Scarrica, C. Panariello, A. Ferone, and A. Staiano, “A hybrid approach to real-time multi-target tracking,” Jun. 01, 2024, Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/s00521-024-09799-4
- H. Li et al., “Multi-object tracking via deep feature fusion and association analysis,” Eng. Appl. Artif. Intell., vol. 124, Sep. 2023. https://doi.org/10.1016/j.engappai.2023.106527
- K. Sriram and K. Purushotham, “Multiple object tracking using space-time adaptive correlation tracking,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 32, no. 3, pp. 1805–1815, 2023. https://doi.org/10.11591/ijeecs.v32.i3.pp1805-1815
- P. Dendorfer et al., “MOT20: A benchmark for multi object tracking in crowded scenes,” Mar. 2020. https://doi.org/10.48550/arXiv.2003.09003
- N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tracking with a deep association metric,” in 2017 IEEE International Conference on Image Processing (ICIP), IEEE, Sep. 2017, pp. 3645–3649. https://doi.org/10.1109/ICIP.2017.8296962
- Y. Du et al., “StrongSORT: Make DeepSORT Great Again,” IEEE Trans. Multimedia, vol. 25, pp. 8725–8737, Feb. 2023. https://doi.org/10.1109/TMM.2023.3240881
- J. Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani, “Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2023, pp. 9686–9696. https://doi.org/10.1109/CVPR52729.2023.00934
- G. Maggiolino, A. Ahmad, J. Cao, and K. Kitani, “Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification,” in Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, 2023, pp. 3025–3029. https://doi.org/10.1109/ICIP49359.2023.10222576
- N. Aharon, R. Orfaig, and B.-Z. Bobrovsky, “BoT-SORT: Robust Associations Multi-Pedestrian Tracking,” Jul. 2022. http://arxiv.org/abs/2206.14651
- V. D. Stanojevic and B. T. Todorovic, “BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking,” Mach. Vis. Appl., vol. 35, no. 3, May 2024. https://doi.org/10.1007/s00138-024-01531-5
- Q. Wan et al., “A transformer-based lightweight method for multiple-object tracking,” IET Image Process., vol. 18, no. 9, pp. 2329–2345, Jul. 2024. https://doi.org/10.1049/ipr2.13099
- S. Li, H. Ren, X. Xie, and Y. Cao, “A Review of Multi-Object Tracking in Recent Times,” Jan. 01, 2025, John Wiley and Sons Inc. https://doi.org/10.1049/cvi2.70010
- P. Karthikeyan, Y. H. Liu, and P. A. Hsiung, “LightMOT: Lightweight and anchor-free solution for tracking multiple objects in dense populations,” Future Generation Computer Systems, vol. 166, May 2025. https://doi.org/10.1016/j.future.2024.107690
- J. Alikhanov, D. Obidov, and H. Kim, “LITE: A Paradigm Shift in Multi-object Tracking with Efficient ReID Feature Integration,” vol. 15293, M. Mahmud, M. Doborjeh, K. Wong, A. C. S. Leung, Z. Doborjeh, and M. Tanveer, Eds., in Lecture Notes in Computer Science, vol. 15293., Singapore: Springer Nature Singapore, 2025, pp. 92–106. https://doi.org/10.1007/978-981-96-6596-9_7
References
M. A. Altaf and M. Y. Kim, “Multiple object detection and tracking in autonomous vehicles: A survey on enhanced affinity computation and its multimodal applications,” Aug. 01, 2025, Korean Institute of Communications and Information Sciences. https://doi.org/10.1016/j.icte.2025.06.005
H. Wang, L. Jin, Y. He, Z. Huo, G. Wang, and X. Sun, “Detector–Tracker Integration Framework for Autonomous Vehicles Pedestrian Tracking,” Remote Sens. (Basel)., vol. 15, no. 8, Apr. 2023. https://doi.org/10.3390/rs15082088
X. Zhou, Y. Jia, C. Bai, H. Zhu, and S. Chan, “Multi-object tracking based on attention networks for Smart City system,” Sustainable Energy Technologies and Assessments, vol. 52, Aug. 2022. https://doi.org/10.1016/j.seta.2022.102216
M. Elshahawy, A. O. Aseeri, S. El-Sappagh, H. Soliman, M. Elmogy, and M. Abu-Elkheir, “Identification and Classification of Crowd Activities,” Computers, Materials and Continua, vol. 72, no. 1, pp. 815–832, 2022. https://doi.org/10.32604/cmc.2022.023852
J. Yan, S. Du, and Y. Wang, “Multi-Pedestrian Tracking in Crowded Scenes by Modeling Movement Behavior and Optimizing Kalman Filter,” IEEE Access, vol. 10, pp. 118512–118521, 2022. https://doi.org/10.1109/ACCESS.2022.3220635
J. Alikhanov, D. Obidov, M. Abdurasulov, and H. Kim, “Practical Evaluation Framework for Real-Time Multi-Object Tracking: Achieving Optimal and Realistic Performance,” IEEE Access, vol. 13, pp. 34768–34788, 2025. https://doi.org/10.1109/ACCESS.2025.3541177
P. Zhang, D. Wang, and H. Lu, “Multi-modal visual tracking: Review and experimental comparison,” Apr. 01, 2024, Tsinghua University. https://doi.org/10.1007/s41095-023-0345-5
S. Honarparvar, Z. B. Ashena, S. Saeedi, and S. Liang, “A Systematic Review of Event-Matching Methods for Complex Event Detection in Video Streams,” Nov. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/s24227238
Y. Li, Y. Liu, C. Zhou, D. Xu, and W. Tao, “A lightweight scheme of deep appearance extraction for robust online multi-object tracking,” Visual Computer, vol. 40, no. 3, pp. 2049–2065, Mar. 2024. https://doi.org/10.1007/s00371-023-02901-2
L. Ye, W. Li, L. Zheng, and Y. Zeng, “Lightweight and Deep Appearance Embedding for Multiple Object Tracking,” IET Computer Vision, vol. 16, no. 6, pp. 489–503, Sep. 2022. https://doi.org/10.1049/cvi2.12106
Z. Wan and W. Wu, “A robust approach to deformed pedestrian tracking with multi-trajectory prediction,” Cluster Comput., vol. 28, no. 5, Oct. 2025. https://doi.org/10.1007/s10586-024-05059-1
V. M. Scarrica, C. Panariello, A. Ferone, and A. Staiano, “A hybrid approach to real-time multi-target tracking,” Jun. 01, 2024, Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/s00521-024-09799-4
H. Li et al., “Multi-object tracking via deep feature fusion and association analysis,” Eng. Appl. Artif. Intell., vol. 124, Sep. 2023. https://doi.org/10.1016/j.engappai.2023.106527
K. Sriram and K. Purushotham, “Multiple object tracking using space-time adaptive correlation tracking,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 32, no. 3, pp. 1805–1815, 2023. https://doi.org/10.11591/ijeecs.v32.i3.pp1805-1815
P. Dendorfer et al., “MOT20: A benchmark for multi object tracking in crowded scenes,” Mar. 2020. https://doi.org/10.48550/arXiv.2003.09003
N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tracking with a deep association metric,” in 2017 IEEE International Conference on Image Processing (ICIP), IEEE, Sep. 2017, pp. 3645–3649. https://doi.org/10.1109/ICIP.2017.8296962
Y. Du et al., “StrongSORT: Make DeepSORT Great Again,” IEEE Trans. Multimedia, vol. 25, pp. 8725–8737, Feb. 2023. https://doi.org/10.1109/TMM.2023.3240881
J. Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani, “Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2023, pp. 9686–9696. https://doi.org/10.1109/CVPR52729.2023.00934
G. Maggiolino, A. Ahmad, J. Cao, and K. Kitani, “Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification,” in Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, 2023, pp. 3025–3029. https://doi.org/10.1109/ICIP49359.2023.10222576
N. Aharon, R. Orfaig, and B.-Z. Bobrovsky, “BoT-SORT: Robust Associations Multi-Pedestrian Tracking,” Jul. 2022. http://arxiv.org/abs/2206.14651
V. D. Stanojevic and B. T. Todorovic, “BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking,” Mach. Vis. Appl., vol. 35, no. 3, May 2024. https://doi.org/10.1007/s00138-024-01531-5
Q. Wan et al., “A transformer-based lightweight method for multiple-object tracking,” IET Image Process., vol. 18, no. 9, pp. 2329–2345, Jul. 2024. https://doi.org/10.1049/ipr2.13099
S. Li, H. Ren, X. Xie, and Y. Cao, “A Review of Multi-Object Tracking in Recent Times,” Jan. 01, 2025, John Wiley and Sons Inc. https://doi.org/10.1049/cvi2.70010
P. Karthikeyan, Y. H. Liu, and P. A. Hsiung, “LightMOT: Lightweight and anchor-free solution for tracking multiple objects in dense populations,” Future Generation Computer Systems, vol. 166, May 2025. https://doi.org/10.1016/j.future.2024.107690
J. Alikhanov, D. Obidov, and H. Kim, “LITE: A Paradigm Shift in Multi-object Tracking with Efficient ReID Feature Integration,” vol. 15293, M. Mahmud, M. Doborjeh, K. Wong, A. C. S. Leung, Z. Doborjeh, and M. Tanveer, Eds., in Lecture Notes in Computer Science, vol. 15293., Singapore: Springer Nature Singapore, 2025, pp. 92–106. https://doi.org/10.1007/978-981-96-6596-9_7