WSCA: A floating trash collector system applied deep neural network
##plugins.themes.academic_pro.article.main##
Author
-
Huynh Ngoc Thai AnhThe College of Information and Communication Technology, Can Tho University, VietnamTrang Thanh TriThe College of Information and Communication Technology, Can Tho University, Vietnam
Keywords:
Abstract
This article presents an automatic water surface garbage collector using a deep learning model with the YOLOv7 network architecture. First, the Thinking Design method was combined with 3D simulation in the design and evaluation process of the WSCA (Water Surface Cleaning Autobot). The authors then propose a data augmentation method to create the FloW+ dataset, which contains an additional 800 images compared to the FloW dataset (2000 images with 5271 floating plastic waste). Finally, the deep learning model is trained on the FloW and FloW+ datasets to identify trash on water surfaces. The accuracy on the test set in the FloW+ set is a precision of 80.5%, recall of 76.6%, mAP@0.5 of 78.8%, mAP@0.5...95 of 35.6% with an average FPS of 17.6. This method has the potential application for the construction of an autonomous floating trash-collecting robot, as well as scale it up to larger scales.
References
-
[1] Eriksen et al. "Plastic pollution in the world’s oceans: more than 5 trillion plastic pieces weighing over 250,000 tons afloat at sea”, PloS one, Vol. 9, No. 12, e111913, 2014.
[2] C. Li, H. F. Tse, and L. Fok "Plastic waste in the marine environment: A review of sources, occurrence and effects”, Science of the Total Environment, Vol. 566, pp. 333–349, 2016.
[3] C. M. Lebreton, J. Zwet, J.-W. Damsteeg, B. Slat, A. Andrady, and J. Reisser. "River plastic emissions to the world’s oceans”, Nature communications, Vol. 8, No. 1, pp. 1-10, 2017.
[4] Ruangpayoongsak, J. Sumroengrit, and M. Leanglum. "A floating waste scooper robot on water surface”, In: 2017 17th International Conference on Control, Automation and Systems (ICCAS). IEEE, 17430768, 2017, pp. 1543-1548. DOI: 10.23919/ICCAS.2017.8204234
[5] Y. Sanda and I. Ibrahim. "Causes, categories and control of water pollution”, International Journal of Scientific Engineering and Science, Vol. 4, No. 9, pp. 84-90, 2020.
[6] Helinski, C. Poor and J. Wolfand. "Ridding our rivers of plastic: A framework for plastic pollution capture device selection”, Marine pollution bulletin, Vol. 165, pp. 112095, 2021.
[7] -Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao. 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. 2023, pp. 7464-7475.
[8] Bai; Y. Zhang; M. Ding; and B. Ghanem. "Sod-mtgan: Small object detection via multitask generative adversarial network”, In Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 206–221.
[9] Li, X. Liang, Y. Wei, T. Xu, J. Feng, and S. Yan. "Perceptual generative adversarial networks for small object detection”, In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2017, pp. 1222–1230. https://doi.org/10.48550/arXiv.1706.05274
[10] Cheng et al., "FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters”, In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10953-10962.
[11] M. Patole; M. Torlak; D. Wang; and M. Ali "Automotive radarrs: A review of signal processing techniques”, IEEE Signal Processing Magazine. Vol. 34, No. 2, pp. 22 - 35, 2017.
[12] Ouaknine, A. Newson, J. Rebut, F. Tupin, and P. Pérez, "Carradar Dataset: Camera and Automotive Radarr with Range-Angle-Doppler Annotations”. arXiv preprint arXiv:2005.01456, 2021, DOI:10.1109/ICPR48806.2021.9413181.
[13] Visser, "The Cognitive Artifacts of Designing”. Lawrence Erlbaum Associates, 2006.
[14] Cross, "Design Cognition: Results from Protocol and Other Empirical Studies of Design Activity”. In: C. Eastman, M. McCracken, and W. Newstatter (eds.) Design Knowing and Learning: Cognition in Design Education, Elsevier, Oxford, 2001, pp. 79-103. ISBN 0 08 043868 7.
[15] Brown, "Design Thinking”. Harvard Business Review, June 2008.
[16] Dorst, "Frame Innovation: Create New Thinking by Design”. Cambridge, MA: MIT Press, 2012. ISBN 978-0-262-32431-1.
[17] McGinn, E. Bourke, A. Murtagh, C. Donovan, P. Lynch, M. F. Cullinan, and K. Kelly, "Meet Stevie: A Socially Assistive Robot Developed Through Application of a ‘Design-Thinking’ Approach”. Journal of Intelligent & Robotic Systems, Vol. 98, No. 1, pp. 39-58, 2020.
[18] Cross, "Design Thinking: Understanding How Designers Think and Work”. Berg, 2011. ISBN 9781847886361.
[19] Cross, "The Nature and Nurture of Design Ability”. Design Studies, Vol. 11, pp. 127–140, 1990.
[20] Hynes et al., “Infusing Engineering Design into High School STEM Courses”, National Center for Engineering and Technology Education, vol. 165, pp. 1-7, 2011.
[21] X. Longet al., "PP-YOLO: An Effective and Efficient Implementation of Object Detector”. arXiv preprint arXiv:2007.12099.
[22] -Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg, "DSSD: Deconvolutional Single Shot Detector”. arXiv preprint arXiv:1701.06659, 2017. https://doi.org/10.48550/arXiv.1701.06659
[23] -Y. Lin; P. Goyal; R. Girshick; K. He; and P.Dollár, "Focal Loss for Dense Object Detection”. In Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980–2988. DOI: 10.1109/ICCV.2017.324
[24] Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement”. arXiv preprint arXiv:1804.02767, 2018. https://doi.org/10.48550/arXiv.1804.02767
[25] Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”. In Advances in Neural Information Processing Systems, 2015, pp. 91–99. https://doi.org/10.48550/arXiv.1506.01497
[26] T.-Y. Lin, P. Dollar´, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature Pyramid Networks for Object Detection”. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125.
[27] Z. Cai and N. Vasconcelos, "Cascade R-CNN: Delving into High-Quality Object Detection”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6154–6162. https://doi.org/10.48550/arXiv.1712.00726