Abstract
Abandoned objects on highways can cause serious traffic accidents. Abandoned objects detection algorithms are of great significance in reducing traffic accidents and improving the efficiency of highway management. Existing traditional image processing detection algorithms are difficult to detect small targets in the complex and changing highway environment. And the current deep learning methods are limited by the number of samples and the influence of vehicle occlusion resulting in lower detection accuracy. Aiming at the above problems, a abandoned object detection algorithm for highway is designed by combining the background modeling algorithm MOG2 and the YOLOv9 detector. Utilizing the difference of the two algorithms on the recognition mechanism of abandoned objects, the results of the YOLOv9 detector are used as a guide to make a comprehensive judgment on the low confidence targets combined with the iterative difference results of MOG2. The actual test results on highways show that the abandoned objects detection algorithm based on YOLOv9 and MOG2 has an improved precision and recall rate for abandoned objects detection compared to a single detection algorithm, with an average precision of 86.7\(\%\) and a recall rate of 89.6\(\%\). The algorithm effectively complements the existing abandoned objects detection algorithms and has engineering practical value.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig5_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03609-z/MediaObjects/11760_2024_3609_Fig6_HTML.png)
Similar content being viewed by others
Data availability
The data utilized in this study are not publicly available due to restrictions imposed by the third-party organization from which they were obtained.
References
Fu, H., Xiang, M., Ma, H., Ming, A., Liu, L.: Abandoned object detection in highway scene. In: 2011 6th International Conference on Pervasive Computing and Applications, pp. 117–121 (2011). https://doi.org/10.1109/ICPCA.2011.6106489
Wang, Y., Zhai, J.: Highway abandoned object detection based on foreground extraction. In: Chinese Intelligent Systems Conference, pp. 367–376 (2023). Springer
Park, H., Park, S., Joo, Y.: Detection of abandoned and stolen objects based on dual background model and mask r-cnn. IEEE Access 8, 80010–80019 (2020)
Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6569–6578 (2019)
Wang, Y., Wang, C., Zhang, H., Dong, Y., Wei, S.: Automatic ship detection based on retinanet using multi-resolution gaofen-3 imagery. Remote Sens. 11(5), 531 (2019)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pp. 21–37 (2016). Springer
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. Preprint arXiv:1804.02767 (2018)
Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464–7475 (2023)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)
Song, H., Zhang, X., Song, J., Zhao, J.: Detection and tracking of safety helmet based on deepsort and yolov5. Multimed. Tools Appl. 82(7), 10781–10794 (2023)
Cai, S., Meng, H., Yuan, M., Wu, J.: FS-YOLO: a multi-scale SAR ship detection network in complex scenes. Signal, Image and Video Processing, 1–11 (2024)
Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2, 28–31 (2004). IEEE
Zivkovic, Z., Van Der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognit. Lett. 27(7), 773–780 (2006)
Wang, C.-Y., Yeh, I.-H., Liao, H.-Y.M.: Yolov9: learning what you want to learn using programmable gradient information. Preprint at arXiv:2402.13616 (2024)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 2, 246–252 (1999). IEEE
Kudela, P., Koller, V.J., Lubitz, W.: Bacterial ghosts (bgs)–advanced antigen and drug delivery system. Vaccine 28(36), 5760–5767 (2010)
Zhang, H., Xu, C., Zhang, S.: Inner-iou: more effective intersection over union loss with auxiliary bounding box. Preprint at arXiv:2311.02877 (2023)
Siliang, M., Yong, X.: Mpdiou: a loss for efficient and accurate bounding box regression. Preprint at arXiv:2307.07662 (2023)
Funding
This thesis is supported by the GF Technology and Innovation Special Zone Program.
Author information
Authors and Affiliations
Contributions
Huajun Song Conceptualization, Methodology, Investigation, Writing-Original Draft Jinbo Wang Data Curation, Writing-Original Draft, Formal Analysis Yunze Zhang Resources, Formal Analysis,Writing-Original Draft
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest to declare that are relevant to the content of this article.
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
Song, H., Wang, J. & Zhang, Y. Detection of abandoned objects based on Yolov9 and background differencing. SIViP 19, 54 (2025). https://doi.org/10.1007/s11760-024-03609-z
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11760-024-03609-z