Underwater Garbage Detection Remotely-Operated Vehicle (ROV) Based on Arduino and YOLO V7

Xuanye Dai

doi:10.54097/jvhwtm45

Authors

Xuanye Dai

DOI:

https://doi.org/10.54097/jvhwtm45

Keywords:

Underwater robot; linear thrust allocation; YOLO image recognition.

Abstract

In response to solid waste pollution in water bodies, people generally use surface vessels with salvage nets for artificial purification, but are powerless to deal with areas that have sunk to the bottom of the water or are inaccessible to ships. Therefore, this project has designed a robot that can identify and even salvage solid waste pollution underwater. In order to solve the problem of multi thruster control for underwater robots, this project maps multi-channel joystick signals to multiple thrusters based on the principle of linear superposition. In order to have the ability to identify underwater garbage, real-time video data from underwater cameras is transmitted wirelessly, allowing laptops to use their self trained YOLO V7 weight model to statistically analyze the types and quantities of underwater garbage. In the future, this project can also design an independent garbage collection device to more conveniently solve the problem of underwater solid waste pollution.

Downloads

Download data is not yet available.

References

[1] Zhang C, Guo L, Luo Q, et al. Research on marine plastic garbage governance in Northwest Pacific Region from the perspective of cooperative game[J]. Journal of Cleaner Production, 2022, 354: 131636.

[2] Lebreton L. The status and fate of oceanic garbage patches[J]. Nature Reviews Earth & Environment, 2022, 3(11): 730-732.

[3] Christ R D, Wernli Sr R L. The ROV manual: a user guide for remotely operated vehicles[M]. Butterworth-Heinemann, 2013.

[4] Shahrubudin N, Lee T C, Ramlan R. An overview on 3D printing technology: Technological, materials, and applications[J]. Procedia manufacturing, 2019, 35: 1286-1296.

[5] Teague J, Allen M J, Scott T B. The potential of low-cost ROV for use in deep-sea mineral, ore prospecting and monitoring[J]. Ocean Engineering, 2018, 147: 333-339.

[6] Kabanov A, Kramar V, Ermakov I. Design and modeling of an experimental rov with six degrees of freedom[J]. Drones, 2021, 5(4): 113.

[7] Aguirre-Castro O A, Inzunza-González E, García-Guerrero E E, et al. Design and Construction of an ROV for Underwater Exploration[J]. Sensors, 2019, 19(24): 5387.

[8] Fairman F W. Linear control theory: the state space approach[M]. John Wiley & Sons, 1998.

[9] 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[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023: 7464-7475.

[10] Faisal M, Chaudhury S, Sankaran K S, et al. Faster R‐CNN Algorithm for Detection of Plastic Garbage in the Ocean: A Case for Turtle Preservation[J]. Mathematical Problems in Engineering, 2022, 2022(1): 3639222.

[11] Deng H, Ergu D, Liu F, et al. An embeddable algorithm for automatic garbage detection based on complex marine environment[J]. Sensors, 2021, 21(19): 6391.