Underwater Waste Recognition and Localization Based on Improved YOLOv5
Source abstract
Abstract
With the continuous development of the economy and society, plastic pollution in rivers, lakes, oceans, and other bodies of water is increasingly severe, posing a serious challenge to underwater ecosystems. Effective cleaning up of underwater litter by robots relies on accurately identifying and locating the plastic waste. However, it often causes significant challenges such as noise interference, low contrast, and blurred textures in underwater optical images. A weighted fusion-based algorithm for enhancing the quality of underwater images is proposed, which combines weighted logarithmic transformations, adaptive gamma correction, improved multi-scale Retinex (MSR) algorithm, and the contrast limited adaptive histogram equalization (CLAHE) algorithm. The proposed algorithm improves brightness, contrast, and color recovery and enhances detail features resulting in better overall image quality. A network framework is proposed in this article based on the YOLOv5 model. MobileViT is used as the backbone of the network framework, detection layer is added to improve the detection capability for small targets, self-attention and mixed-attention modules are introduced to enhance the recognition capability of important features. The cross stage partial (CSP) structure is employed in the spatial pyramid pooling (SPP) section to enrich feature information, and the complete intersection over union (CIOU) loss is replaced with the focal efficient intersection over union (EIOU) loss to accelerate convergence while improving regression accuracy. Experimental results proved that the target recognition algorithm achieved a recognition accuracy of 0.913 and ensured a recognition speed of 45.56 fps/s. Subsequently, Using red, green, blue and depth (RGB-D) camera to construct a system for identifying and locating underwater plastic waste. Experiments were conducted underwater for recognition, localization, and error analysis. The experimental results demonstrate the effectiveness of the proposed method for identifying and locating underwater plastic waste, and it has good localization accuracy.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Microplastics and Plastic Pollution · Advanced Neural Network Applications · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Marine microplastic debris: An emerging issue for food security, food safety and human health
2. River plastic emissions to the world’s oceans
3. Enhancing underwater imagery using generative adversarial networks
4. Underwater image descattering and quality assessment
5. A methodology to characterize riverine macroplastic emission into the ocean10.3389/fmars.2018.00372 ↗
6. Toward a harmonized approach for monitoring of riverine floating macro litter inputs to the marine environment
7. Rivers as a source of marine litter-a study from the SE Pacific
8. Macroplastic and microplastic contamination assessment of a tropical river (Saigon River, Vietnam) transversed by a developing megacity
9. Semi-automatic recognition of marine debris on beaches
10. SMACC: A system for microplastics automatic counting and classification10.1109/ACCESS.2020.2970498 ↗
11. Plastic debris in rivers
12. Detection of underwater plastic waste based on improved yolov5n
13. Identifying floating plastic marine debris using a deep learning approach
14. H. Liu, P. H. Song and R. W. Ding, “WQT and DG-YOLO: Towards domain generalization in underwater object detection,” 2020. [Online]. Available: https://arxiv.org/abs/2004.0633310.1109/ICIP40778.2020.9191364 ↗
15. Robust RGB-D camera and IMU fusion-based cooperative and relative close-range localization for multiple turtle-inspired amphibious spherical robots10.1007/s42235-019-0036-1 ↗
16. An underwater positioning system for uuvs based on lidar camera and inertial measurement unit
17. Multiscale retinex infrared image enhancement based on the fusion of guided filtering and logarithmic transformation algorithm
18. Underground pedestrian detection model based on Dense-YOLO network
19. Contrast enhancement of brightness-distorted images by improved adaptive gamma correction10.1016/j.compeleceng.2017.09.012 ↗
20. Image contrast and color enhancement using adaptive gamma correction and histogram equalization10.1016/j.ijleo.2019.02.054 ↗
21. Properties and performance of a center/surround retinex
22. Multi-scale retinex for color image enhancement
23. Zuiderveld · Contrast limited adaptive histogram equalization · 1994 · 474
24. Image enhancement algorithm for underwater vision based on weighted fusion10.13700/j.bh.1001-5965.2022.0540 ↗
25. Z. L. Peng, W. Huang, S. Z. Gu, L. X. Xie, Y. W. Wang et al., “Conformer: Local features coupling global representations for visual recognition,” 2021. [Online]. Available: https://arxiv.org/abs/2105.0388910.1109/ICCV48922.2021.00042 ↗
26. Y. P. Chen, X. Y. Dai, D. D. Chen, M. C. Liu, X. Y. Dong et al., “Mobile-Former: Bridging MobileNet and transformer,” 2021. [Online]. Available: https://arxiv.org/abs/2108.05895
27. Y. H. Li, T. Yao, Y. W. Pan and T. Mei, “Contextual transformer networks for visual recognition,” 2021. [Online]. Available: https://arxiv.org/abs/2107.12292
28. S. Mehta and M. Rastegari, “MobileViT: Light-weight, general-purpose, and mobile-friendly vision Transformer,” 2021. [Online]. Available: https://arxiv.org/abs/2110.02178
29. Spatial pyramid pooling in deep convolutional networks for visual recognition
30. C. 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,” 2022. [Online]. Available: https://arxiv.org/abs/2207.0269610.1109/CVPR52729.2023.00721 ↗
31. A new backbone that can enhance learning capability of CNN
32. Cbam: Convolutional block attention module
33. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios
34. Focal and efficient IOU loss for accurate bounding box regression10.1016/j.neucom.2022.07.042 ↗
35. A multiscale retinex for bridging the gap between color images and the human observation of scenes
36. T. Gautam, R. S. Jeanne, P. Olivier and L. Jay, “A robotic approach towards quantifying epipelagic bound plastic using deep visual models,” 2021. [Online]. Available: https://arxiv.org/abs/2105.01882
37. G. Zheng, S. T. Liu, F. Wang, Z. M. Li and J. Sun, “Yolox: Exceeding yolo series in 2021,” 2021. [Online]. Available: https://arxiv.org/abs/2107.08430
38. B. Alexey, C. Y. Wang and H. Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” 2021. [Online]. Available: https://arxiv.org/abs/2004.10934
39. R. Joseph and A. Farhadi, “Yolov3: An incremental improvement,” 2018. [Online]. Available: https://arxiv.org/abs/1804.02767
40. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗