Borui Xu
ABSTRACT
Addressing the challenges of small individual volume, difficulty in cleaning, and high cost of removing floating debris on water surfaces, A small-scale intelligent water surface cleaning vessel based on the YOLOv5 algorithm is designed in this paper, with the STM32 selected as the microcontroller for this system, The Raspberry Pi 4B is selected as the carrier for the vision recognition module. Is capable of intelligently identifying and automatically clearing debris and floating oil spills on water surfaces. Additionally, it employs a camera to analyze the water color index, enabling real-time monitoring of regional water quality. When the system detects garbage in its path, a cylindrical roller brush at the front automatically activates, sweeping floating debris into an integrated garbage bin. Experimental results demonstrate that this system achieves an overall recognition accuracy greater than 81.4% in complex environments. Capable of cleaning tasks in small to medium-sized water bodies like lakes and rivers, it concurrently performs water quality assessments, thereby enhancing the effectiveness of pollution control in aquatic environments.
- Duarte, M.M. & Azevedo, L. 2023. Automatic Detection and Identification of Floating Marine Debris Using Multispectral Satellite Imagery. IEEE Transactions on Geoscience and Remote Sensing, 61(1): 1–15. DOI:10.1109/TGRS.2023.3283607.Google Scholar
Cross Ref
- Becker, N., Greenfeld, A. & Shamir, S.Z. 2019. Cost–benefit analysis of full and partial river restoration: the Kishon River in Israel. International Journal of Water Resources Development, 35: 871–890. DOI: 10.1080/07900627.2018.1501349.Google ScholarCross Ref
- Li, X., Tian, M., Kong, S., Wu, L., & Yu, J. 2020. A modified YOLOv3 detection method for vision-based water surface garbage capture robot. International Journal of Advanced Robotic Systems, 17(3). DOI:10.1177/1729881420932715.Google ScholarCross Ref
- Paige, M. & Painho, M., 2014. Exogenous floating marine debris: Filling search and detection gaps using remote sensing. In: 2014 9th Iberian Conference on Information Systems and Technologies (CISTI). DOI: 10.1109/CISTI.2014.6876887.Google ScholarCross Ref
- Shirakura, N., Kiyokawa, T., Kumamoto, H., Takamatsu, J., & Takamatsu, J., 2020. Semi-automatic Collection of Marine Debris by Collaborating UAV and UUV. In: 2020 Fourth IEEE International Conference on Robotic Computing (IRC). IEEE. DOI: 10.1109/IRC.2020.00072.Google ScholarCross Ref
- Nong, J., Fan, W., Yang, Q., 2019. Design and Implementation of a Small Unmanned Water Surface Garbage Cleaning Device. Shanxi Electronics Technology, 2019(05): 18-20. https://kns.cnki.net/kcms/detail/detail.aspx?filename=SXDS201905007&dbname=cjfdtotal&dbcode=cjfd&v=Google Scholar
- Ma, H., Ye, Y., Dong, J. & Bo, Y., 2022. An Intelligent Garbage Classification System Using a Lightweight Network MobileNetV2. In: 2022 7th International Conference on Signal and Image Processing (ICSIP). Suzhou, China. pp. 531-535. DOI: 10.1109/ICSIP55141.2022.9886985.Google ScholarCross Ref
- Junzhe Zhang A water surface garbage recognition method based on transfer learning and image enhancement[J]. Results in Engineering, 2023, 19. https://wrdvpn.dlnu.edu.cn/https/77726476706e69737468656265737421f4f848d228226f/10.1016/j.rineng.2023.101340.Google ScholarCross Ref
- Wu, X., Tan, L., & Xu, X. 2023. A YOLOv5s-based Defect Detection Method for Nitrile Gloves. Manufacturing Automation, 45(09): 1-4+10. https://kns.cnki.net/kcms/detail/detail.aspx?filename=JXGY202309001&dbname=cjfdtotal&dbcode=cjfd&v=.Google Scholar
- Li, S. 2023. TC-YOLOv5: rapid detection of floating debris on raspberry Pi 4B. Journal of Real-Time Image Processing, 20(2). DOI: 10.1007/S11554-023-01265-Z.Google ScholarDigital Library
Index Terms
- Intelligent Small-Scale Surface Cleaning Boat Based on the YOLOv5 Algorithm
Recommendations
Hillslope and catchment scale landform evolution – Predicting catchment form and surface properties
AbstractComputer-based coupled soilscape-landform evolution models provide an avenue for estimating the erosion potential of a landform over geological timescales. They also provide tools to understand soil-landform relationships in the ...
Graphical abstractDisplay Omitted
Highlights- SSSPAM and CAESAR-Lisflood models were used to simulate the evolution of a natural catchment.
Characteristics and Evaluation for Nitrogen Pollution in Water and Surface Sediments of Xixi Wetland
ISDEA '13: Proceedings of the 2013 Third International Conference on Intelligent System Design and Engineering ApplicationsIn this paper, it was investigated and evaluated about characteristics of nitrogen pollution for 11 sampling water or surface sediments (0~10cm) in Hang Zhou Xixi Wetland, and correlation analysis was conducted amongst nitrogen indexes for water and ...
Comments