Abstract
Computer vision-aided small target detection in moving streams, such as rivers/ roads, requires a fast-converging outcome as the frame requirements are high. The bounding box varies for the multiple frames generated, resulting in low object detection precision. To address the problem of floating object detection, this article introduces a Region-Overlap Detection (ROD) method using the Minimum Convoluted YOLOv7 (MCY) architecture. First, the typical YOLO classifier identifies the largest overlap area from multiple overlapping regions. The second method extracts the largest bounding box in an area with minimal convolution in the neural network’s final training layer. Both techniques accurately identify small objects in flowing streams with high mean accuracy. The YOLO architecture trains its convolutional layers using the largest overlap area, shared by many bounding box regions. The intersecting areas are removed from convolutional layers to expedite convergence and increase mAP. The proposed method achieves a high mean Average Precision (mAP) of 73.1% and a recall of 70.2% for small floating object detection in dynamic river environments.
Similar content being viewed by others
Data availability
The data will be made available by the corresponding author on request.
References
Xian, R., Tang, L. & Liu, S. Development of a Lightweight Floating Object Detection Algorithm. Water 16 (11), 1633 (2024).
Codes-Alcaraz, A. M., Puerto, H. & Rocamora, C. Image Recognition for Floating Waste Monitoring in a Traditional Surface Irrigation System. Water 16 (18), 2680 (2024).
Renfei, C., Yong, P., Zhongwen, L. & Hua, S. Floating object detection using double-labelled domain generalization. Eng. Appl. Artif. Intell. 133, 108500 (2024).
Park, J. J., Park, K. A., Kim, T. S., Oh, S. & Lee, M. Aerial hyperspectral remote sensing detection for maritime search and surveillance of floating small objects. Adv. Space Res. 72 (6), 2118–2136 (2023).
Huangfu, Z., Li, S., & Yan, L. Ghost-YOLO v8: An attention-guided enhanced small target detection algorithm for floating litter on water surfaces. Computers, Materials & Continua. 80(3), 3713–3731 (2024)http://www.techscience.com/cmc/v80n3/57888
Santos, S. P., Rodrigues, F. L., de Alcântara Santos, A. C. & Moraes, L. E. Spatial and temporal patterns of floating litter in shallow habitats: Insights from high-tourism tropical areas in Northeastern Brazil. Reg. Stud. Mar. Sci. 78, 103782 (2024).
Mahmoud, H., Kurniawan, I. F., Aneiba, A. & Asyhari, A. T. Enhancing detection of remotely-sensed floating objects via Data Augmentation for Maritime SAR. J. Indian Soc. Remote Sens. 52 (6), 1285–1295 (2024).
Aliha, A., Liu, Y., Zhou, G. & Hu, Y. High-Speed Spatial–Temporal Saliency Model: A Novel Detection Method for Infrared Small Moving Targets Based on a Vectorized Guided Filter. Remote Sens. 16 (10), 1685 (2024).
Li, X., Wang, Y., Zhao, y and Chen, G. "UW-DETR: Feature Fusion Enhanced RT-DETR for Improving Underwater Object Detection," in IEEE Access, vol. 12, pp. 191967-191979, (2024), https://doi.org/10.1109/ACCESS.2024.3515960 doi: 10.1109/ACCESS.2024.3515960
Deng, L., Liu, Z., Wang, J. & Yang, B. ATT-YOLOv5-Ghost: water surface object detection in complex scenes. J. Real-Time Image Proc. 20 (5), 97 (2023).
Yang, M. & Wang, H. Real-time water surface target detection based on improved YOLOv7 for Chengdu Sand River. J. Real-Time Image Proc. 21 (4), 127 (2024).
Wang, C., Zhu, G., Mao, Y. & Yin, J. A Bayesian framework-based method for suppressing reverberation in moving target detection. Appl. Acoust. 224, 110141 (2024).
Xiang, W. et al. Reverberation suppression for detecting underwater moving target based on robust autoencoder. Appl. Acoust. 206, 109301 (2023).
Chen, L. & Zhu, J. Water surface garbage detection based on lightweight YOLOv5. Sci. Rep. 14 (1), 6133 (2024).
Du, Y. et al. Improving Unsupervised Object-Based Change Detection via Hierarchical Multi-Scale Binary Partition Tree Segmentation: A Case Study in the Yellow River Source Region. Remote Sens. 16 (4), 629 (2024).
He, J. et al. Ec-yolox: A deep-learning algorithm for floating objects detection in ground images of complex water environments. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 17, 7359–7370 (2024).
García-Pimentel, M. M. et al. Floating plastics as integrative samplers of organic contaminants of legacy and emerging concern from Western Mediterranean coastal areas. Sci. Total Environ. 905, 166828 (2023).
Fu, B. Floating waste discovery by request via object-centric learning. Computers, Materials & Continua. 80(1), 1407–1424 (2024). https://doi.org/10.32604/cmc.2024.052656
Yang, J., Li, Z., Gu, Z. & Li, W. Research on floating object classification algorithm based on convolutional neural network. Sci. Rep. 14 (1), 32086 (2024).
Nair, S. & Kumar, A. Zero-Shot Learning Algorithms for Object Recognition in Medical and Navigation Applications. PatternIQ Min. 1 (4), 24–37. https://doi.org/10.70023/sahd/241103 (Nov. 2024).
Yu, H. Cao, Z. Wang, G. Ding, H.Liu, N and Dong, Y. "A Classification Method for Marine Surface Floating Small Targets and Ship Targets," in IEEE Journal on Miniaturization for Air and Space Systems., vol. 5, no. 2, pp. 94-99, June 2024, https://doi.org/10.1109/JMASS.2024.3372116..
Wu, X., Liu, T., Liu, Y and Liu, L. "An Autonomous Feature Detection Method for Slow-Moving Small Target on Sea Surface Based on Kernelized Contextual Bandit," in IEEE Sensors Journal, vol. 24, no. 19, pp. 30541-30559, 1 Oct.1, 2024, https://doi.org/10.1109/JSEN.2024.3442865.
Wang, H. et al. Attention and prediction-guided motion detection for low-contrast small moving targets. IEEE Trans. Cybernetics. 53 (10), 6340–6352 (2022).
Bai, X., Xu, S., Zhu, J., Guo, Z. & Shui, P. Floating small target detection in sea clutter based on multifeature angle variance. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 16, 9422–9436 (2023).
Shao, Z. et al. An efficient model for small object detection in the maritime environment. Appl. Ocean Res. 152, 104194 (2024).
Jia, T., de Vries, R., Kapelan, Z., Van Emmerik, T. H. & Taormina, R. Detecting floating litter in freshwater bodies with semi-supervised deep learning. Water Res. 266, 122405 (2024).
Renfei, C., Jian, W., Yong, P., Zhongwen, L. & Hua, S. Detection and tracking of floating objects based on spatial-temporal information fusion. Expert Syst. Appl. 225, 120185 (2023).
Chen, R., Wu, J., Peng, Y., Li, Z. & Shang, H. Solving floating pollution with deep learning: A novel SSD for floating objects based on continual unsupervised domain adaptation. Eng. Appl. Artif. Intell. 120, 105857 (2023).
Li, N. et al. DENS-YOLOv6: A small object detection model for garbage detection on water surface. Multimedia Tools Appl. 83 (18), 55751–55771 (2024).
Wang, H., Cheng, H., & Zhang, J. Faster-PGYOLO: An efficient framework for floating debris detection in inland waters. The Visual Computer. 41, 5087–5104 (2025). https://doi.org/10.1007/s00371-024-03709-4.
Zhang, D., Wang, P., Dong, Y., Li, L. & Li, X. Joint fuzzy background and adaptive foreground model for moving target detection. Front. Comput. Sci. 18 (2), 182306 (2024).
Li, N., Zhang, T., Li, B., Yuan, B. & Xu, S. RS-UNet: lightweight network with reflection suppression for floating objects segmentation. Signal. Image Video Process. 17 (8), 4319–4326 (2023).
Aliha, A. et al. A spatial–temporal block-matching patch-tensor model for infrared small moving target detection in complex scenes. Remote Sens. 15 (17), 4316 (2023).
Zhang, X., Min, C., Luo, J. & Li, Z. YOLOv5-FF: detecting floating objects on the surface of fresh water environments. Appl. Sci. 13 (13), 7367 (2023).
Li, H. et al. Detection of floating objects on water surface using YOLOv5s in an edge computing environment. Water 16 (1), 86 (2023).
Zhang, L., Xie, Z., Xu, M., Zhang, Y. & Wang, G. EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River. Appl. Sci. 13 (4), 2303 (2023).
Li, K. et al. Feature augmentation and scale penalty for tiny floating detection. Int. J. Mach. Learn. Cybernet. 15 (3), 853–862 (2024).
Selvaraj, R., Kuthadi, V. M., Duraisamy, A., Selvaraj, B. & Pethuraj, M. S. Learning optimizer-based visual analytics method to detect targets in autonomous unmanned aerial vehicles (IEEE Intelligent Transportation Systems Magazine, 2023).
Sheron, P. F., Sridhar, K. P., Baskar, S. & Shakeel, P. M. Projection-dependent input processing for 3D object recognition in human robot interaction systems. Image Vis. Comput. 106, 104089 (2021).
Li, C., Jiang, S. & Cao, X. Small-Target Detection Algorithm Based on STDA-YOLOv8. Sensors 25 (9), 2861 (2025).
Zhang, C., Yue, J., Fu, J. & Wu, S. River floating object detection with transformer model in real time. Sci. Rep. 15 (1), 9026 (2025).
Wang, S. et al. PHSI-RTDETR: A lightweight infrared small target detection algorithm based on UAV aerial photography. Drones 8 (6), 240 (2024).
Gao, P. & Li, Z. YOLO-S3DT: A Small Target Detection Model for UAV Images Based on YOLOv8. Computers Mater. Continua. 82 (3), 4555–4572 (2025).
Ni, J., Zhu, S., Tang, G., Ke, C. & Wang, T. A Small-Object Detection Model Based on Improved YOLOv8s for UAV Image Scenarios. Remote Sens. 16 (13), 2465 (2024).
Yue, M., Zhang, L., Huang, J. & Zhang, H. Lightweight and Efficient Tiny-Object Detection Based on Improved YOLOv8n for UAV Aerial Images. Drones 8 (7), 276 (2024).
AFO dataset. URL: https://www.kaggle.com/datasets/jangsienicajzkowy/afo-aerial-dataset-of-floating-objects
Funding
Zhejiang Province “spearhead” “leading wild goose” research and development plan (No. 2023C03193).
Author information
Authors and Affiliations
Contributions
Conceptualization, Weifeng Yang, Bing Zhang, and Wenjie Wang; Methodology, Weifeng Yang, Su Guo, and Kebin Gao; Software, Jianwei Ying, Jun Zheng, and Chao Li; Validation, Jun Li, Weigang Xu, and Qi Chen; Formal analysis, Jun Cao and Youxiang Zuo; Investigation, Yu Chen, Weifeng Yang, Qi Chen, and Jun Cao; Resources, Kebin Gao, Jianwei Ying, and Su Guo; Data curation, Yu Chen, Weifeng Yang, and Su Guo; Writing—original draft preparation, Weifeng Yang, Bing Zhang, Su Guo, and Jun Zheng; Writing—review and editing, Kebin Gao, Jianwei Ying, Chao Li, and Jun Li; Visualization, Jun Cao, Youxiang Zuo, and Yu Chen; Supervision, Wenjie Wang, Kebin Gao, and Jianwei Ying; Project administration, Wenjie Wang and Kebin Gao; Funding acquisition, Wenjie Wang, Kebin Gao, and Jianwei Ying.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yang, W., Zhang, B., Guo, S. et al. Small target detection of floating objects in river channels based on improved YOLOv7. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40688-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40688-z
