Abstract
By introducing a low-score detection box association stage, the full-detection association can effectively enhance the accuracy and robustness of online multi-object tracking. However, this association would lead to a decline in tracking precision, the key point of which is that the fixed noise setting of Kalman Filter is difficult to balance the system requirements for high-score and low-score detection boxes. A Power-Adaptive Kalman Filter (PAKF) was proposed in this article. Taking the motion matching cost and confidence score as process and observation noise scale parameters, respectively, and combined with the power transformation, two adaptive factors were constructed to adjust the process and observation covariance matrices, respectively. Sufficient ablation experiments were conducted on the full validation set of MOT17. After introducing the PAKF into the ByteTrack and SORT, the High-Order Tracking Accuracy, Multi-Object Tracking Precision (MOTP) and ID F1 score of them were improved by about 1%, and their improvements were more obvious in complex scenarios. On the challenging HiEve benchmark dataset, after introducing the PAKF, the Multi-Object Tracking Accuracy and MOTP of the ByteTrack were improved by 0.53% and 0.28%, respectively. It is more advantageous than other state-of-the-art online methods. The proposed PAKF can effectively improve the performances of the multi-object tracking algorithms based on the Kalman Filter and tracking-by-detection. The codes are available at https://github.com/LiYi199983/PAKF.
Similar content being viewed by others
Data availability
The authors confirm that the code, network weights and datasets supporting the results of this study can be found in the article.
References
Kishi, N., Shinkuma, R., Oka, M., et al.: Multi-object tracking for road surveillance without using features of image data. In: 2021 IEEE Global Communications Conference (GLOBECOM). pp. 1–6 (2021).
Yurtsever, M.M.E., Eken, S.: BabyPose: real-time decoding of baby’s non-verbal communication using 2D video-based pose estimation. IEEE Sens. J. 22(14), 13776–13784 (2022). https://doi.org/10.1109/jsen.2022.3183502
Chen, J., Wang, F., Li, C., et al.: Online multiple object tracking using a novel discriminative module for autonomous driving. Electronics 10(20), 2479 (2021). https://doi.org/10.3390/electronics10202479
Ge, Z., Liu, S., Wang, F., et al.: YOLOX: Exceeding YOLO Series in 2021. (2021). https://ui.adsabs.harvard.edu/abs/2021arXiv210708430G
Zhou, X., Wang, D., Krähenbühl, P. J. a. e.-p.: Objects as Points. (2019). https://ui.adsabs.harvard.edu/abs/2019arXiv190407850Z
Ahmed, I., Ahmad, M., Ahmad, A., et al.: Top view multiple people tracking by detection using deep SORT and YOLOv3 with transfer learning: within 5G infrastructure. Int. J. Mach. Learn. Cybern. 12(11), 3053–3067 (2021)
Guo, W., Jin, Y., Shan, B., et al.: Multi-cue multi-hypothesis tracking with re-identification for multi-object tracking. Multimed. Syst. 28(3), 925–937 (2022)
Sheng, H., Chen, J., Zhang, Y., et al.: Iterative multiple hypothesis tracking with tracklet-level association. IEEE Trans. Cir. Syst. Video Technol. 29(12), 3660–3672 (2018)
Song, Y.-m., Jeon, M.: Online multiple object tracking with the hierarchically adopted gm-phd filter using motion and appearance. In: 2016 IEEE International conference on consumer electronics-Asia (ICCE-Asia). pp. 1–4 (2016)
Wang, Z., Zheng, L., Liu, Y., et al.: Towards real-time multi-object tracking. In: European Conference on Computer Vision. pp. 107–122 (2020)
Zhang, Y., Wang, C., Wang, X., et al.: Fairmot: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vision 129(11), 3069–3087 (2021)
Pang, J., Qiu, L., Li, X., et al.: Quasi-dense similarity learning for multiple object tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 164–173 (2021).
Zhou, X., Koltun, V., Krähenbühl, P.: Tracking objects as points. In: European Conference on Computer Vision. pp. 474–490 (2020).
Hua, W., Mu, D., Zheng, Z., et al.: Online multi-person tracking assist by high-performance detection. J. Supercomput. 76(6), 4076–4094 (2017). https://doi.org/10.1007/s11227-017-2202-8
Chen, L., Ai, H., Zhuang, Z., et al.: Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In: 2018 IEEE International Conference on Multimedia and Expo (ICME). pp. 1–6 (2018).
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP). pp. 3645–3649 (2017).
Min, Y., Yuwei, W., Yunde, J.: A hybrid data association framework for robust online multi-object tracking. IEEE Trans. Image Process. 26(12), 5667–5679 (2017). https://doi.org/10.1109/TIP.2017.2745103
Bae, S.H., Yoon, K.J.: Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 595–610 (2018). https://doi.org/10.1109/TPAMI.2017.2691769
Zhang, Y., Sun, P., Jiang, Y., et al.: ByteTrack: Multi-Object Tracking by Associating Every Detection Box (2021). https://ui.adsabs.harvard.edu/abs/2021arXiv211006864Z
Kalman, R.E.: A new approach to linear filtering and prediction problems. J Fluids Eng. 82(1), 35–45 (1960)
Bewley, A., Ge, Z., Ott, L., et al.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP). pp. 3464–3468 (2016).
Hou, X., Wang, Y., Chau, L.-P.: Vehicle tracking using deep sort with low confidence track filtering. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). pp. 1–6 (2019).
He, J., Erfani, S., Ma, X., et al.: Alpha-IoU: a family of power intersection over union losses for bounding box regression. Adv. Neural. Inf. Process. Syst. 34, 20230–20242 (2021)
Du, Y., Wan, J., Zhao, Y., et al.: GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 2809–2819 (2021).
Sarkar, K., Halder, T.K., Mandal, A.: Adaptive power-law and cdf based geometric transformation for low contrast image enhancement. Multimed. Tools Appl. 80(4), 6329–6353 (2021)
Milan, A., Leal-Taixe, L., Reid, I., et al.: MOT16: A Benchmark for Multi-Object Tracking (2016). https://ui.adsabs.harvard.edu/abs/2016arXiv160300831M
Lin, W., Liu, H., Liu, S., et al.: Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events (2020). https://ui.adsabs.harvard.edu/abs/2020arXiv200504490L
Lu, Z., Rathod, V., Votel, R., et al.: Retinatrack: Online single stage joint detection and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14668–14678 (2020).
Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). (2018).
Zhang, J., Xing, M., Sun, G.-C., et al.: Multiple statistics contributing to few-sample deep learning for subtle trace detection in high-resolution SAR images. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2021)
Kim, T., Park, T.-H.: Extended Kalman filter (EKF) design for vehicle position tracking using reliability function of radar and lidar. Sensors. 20(15), 4126 (2020)
Wang, M., Wu, X.: Multi-object tracking strategy of autonomous vehicle using modified unscented Kalman Filter and reference point switching. J. Shanghai Jiaotong University (Science). 26(5), 607–614 (2021)
Cui, Y., Zhang, J., He, Z., et al.: Multiple pedestrian tracking by combining particle filter and network flow model. Neurocomputing 351, 217–227 (2019)
Guo, W., Zhao, Q., Gu, D.: Visual tracking using an insect vision embedded particle filter. Math. Prob. Eng. (2015). https://doi.org/10.1155/2015/573131
Khattak, A.S., Raja, G., Anjum, N.: Adaptive framework for multi-feature hybrid object tracking. Appl. Sci. 8(11), 2294 (2018)
Zhai, G., Wu, C., Wang, Y.: Millimeter wave radar target tracking based on adaptive Kalman filter. In: 2018 IEEE Intelligent Vehicles Symposium (IV). pp. 453–458 (2018).
Wang, Y., Mu, X.: Dynamic siamese network with adaptive Kalman filter for object tracking in complex scenes. IEEE Access. 8, 222918–222930 (2020)
Cao, J., Weng, X., Khirodkar, R., et al.: Observation-centric SORT: rethinking SORT for robust multi-object tracking. (2022). https://ui.adsabs.harvard.edu/abs/2022arXiv220314360C
Kumar, M., Singh, K.: Retrieval of head–neck medical images using Gabor filter based on power-law transformation method and rank BHMT. Signal Image Video Process. 12(5), 827–833 (2018)
Lin, T.-Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980–2988 (2017).
Dendorfer, P., Rezatofighi, H., Milan, A., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. (2020). https://ui.adsabs.harvard.edu/abs/2020arXiv200309003D
Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. EURASIP J. Image Video Process. 2008, 1–10 (2008)
Ristani, E., Solera, F., Zou, R., et al.: Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision. pp. 17–35 (2016).
Luiten, J., Os Ep, A.A., Dendorfer, P., et al.: HOTA: a higher order metric for evaluating multi-object tracking. Int. J. Comput. Vis. 129(2), 548–578 (2021). https://doi.org/10.1007/s11263-020-01375-2
Wu, B., Nevatia, R.: Tracking of multiple, partially occluded humans based on static body part detection. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06). pp. 951–958 (2006).
Shao, S., Zhao, Z., Li, B., et al.: Crowdhuman: a benchmark for detecting human in a crowd. (2018). https://doi.org/10.48550/arXiv.1805.00123
Zhang, S., Benenson, R., Schiele, B.: Citypersons: a diverse dataset for pedestrian detection. In: Proceedings of the IEEE Conference on Computer VISION and Pattern Recognition. pp. 3213–3221 (2017)
Ess, A., Leibe, B., Schindler, K., et al.: A mobile vision system for robust multi-person tracking. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition. pp. 1–8 (2008)
Shuai, B., Berneshawi, A., Wang, M., et al.: Application of multi-object tracking with Siamese track-RCNN to the human in events dataset. In: Proceedings of the 28th ACM International Conference on Multimedia. pp. 4625–4629 (2020)
Acknowledgements
This work was supported in part by Anhui Province Key Laboratory of Advanced Numerical Control & Servo Technology, Grant (No. XJSK202102), by the Special Fund for Collaborative Innovation of Anhui Polytechnic University & Jiujiang District under Grant (No. 2021CYXTB3), and by the Natural Science Research Project of Higher Education of Anhui Province of China under Grant (No. YJS20210446).
Author information
Authors and Affiliations
Contributions
Conceptualization and methodology, Youyu Liu and Yi Li; software, Yi Li; validation, Yi Li and Qingyan Yang; formal analysis, Dezhang Xu; writing—original draft preparation, Youyu Liu; writing—review and editing, Youyu Liu; visualization, Yi Li; project administration, Youyu Liu and Wanbao Tao; funding acquisition, Youyu Liu and Qingyan Yang. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
This paper does not contain any studies with human or animal subjects and all authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, Y., Li, Y., Xu, D. et al. Adaptive Kalman Filter with power transformation for online multi-object tracking. Multimedia Systems 29, 1231–1244 (2023). https://doi.org/10.1007/s00530-023-01052-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-023-01052-7