An Underwater Target Detection Algorithm Based on Attention Mechanism and Improved YOLOv7
Source abstract
Abstract
For underwater robots in the process of performing target detection tasks, the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model, which is prone to issues like error detection, omission detection, and poor accuracy. Therefore, this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7) underwater target detection algorithm. To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase, we have added a Convolutional Block Attention Module (CBAM) to the backbone network. The Reparameterization Visual Geometry Group (RepVGG) module is inserted into the backbone to improve the training and inference capabilities. The Efficient Intersection over Union (EIoU) loss is also used as the localization loss function, which reduces the error detection rate and missed detection rate of the algorithm. The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition) dataset show that the mAP(mean Average Precision) score of the algorithm is 86.1%, which is a 2.2% improvement compared to the YOLOv7. The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments, and it is more suitable for underwater target detection.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Water Quality Monitoring Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. High-value components and bioactives from sea cucumbers for functional foods—A review10.3390/md9101761 ↗
2. Bioactive compounds from various types of sea urchin and their therapeutic effects—A review
3. Vision-based object detection and tracking for autonomous navigation of underwater robots10.1016/j.oceaneng.2012.04.006 ↗
4. A review on underwater autonomous environmental perception and target grasp, the challenge of robotic organism capture10.1016/j.oceaneng.2019.106644 ↗
5. Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: A review10.3390/s23041990 ↗
6. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
7. Cbam: Convolutional block attention module
8. RepVGG: Making VGG-style convnets great again
9. Focal and efficient iou loss for accurate bounding box regression10.1016/j.neucom.2022.07.042 ↗
10. Enhancing geometric factors in model learning and inference for object detection and instance segmentation10.1109/TCYB.2021.3095305 ↗
11. Real-time underwater onboard vision sensing system for robotic gripping10.1109/TIM.2020.3044719 ↗
12. Underwater image processing and object detection based on deep CNN method
13. All-in-one underwater image enhancement using domain-adversarial learning
14. Deep learning10.1038/nature14539 ↗
15. Faster R-CNN: Towards real-time object detection with region proposal networks
16. You only look once: Unified, real-time object detection
17. YOLO9000: Better, faster, stronger
18. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018.
19. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020.
20. G. Zheng, S. T. Liu, F. Wang, Z. M. Li and J. Sun, “YOLOX: Exceeding YOLO series in 2021,” arXiv:2107.08430, 2021.
21. SSD: Single shot multibox detector
22. SWIPENET: Object detection in noisy underwater scenes10.1016/j.patcog.2022.108926 ↗
23. Boosting R-CNN: Reweighting R-CNN samples by RPN’s error for underwater object detection10.1016/j.neucom.2023.01.088 ↗
24. Lightweight underwater object detection based on YOLO v4 and multi-scale attentional feature fusion10.3390/rs13224706 ↗
25. A deep learning approach incorporating YOLO v5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings10.1016/j.compag.2022.107194 ↗
26. Improved YOLO network for free-angle remote sensing target detection10.3390/rs13112171 ↗
27. Detection method of timber defects based on target detection algorithm10.1016/j.measurement.2022.111937 ↗
28. A lightweight border patrol object detection network for edge devices10.3390/electronics11223828 ↗
29. CME-YOLOv5: An efficient object detection network for densely spaced fish and small targets10.3390/w14152412 ↗
30. Feature pyramid networks for object detection
31. Path aggregation network for instance segmentation
32. W. Zaremba, I. Sutskever, and O. Vinyals, “Recurrent neural network regularization,” arXiv:1409.2329, 2014.
33. Squeeze-and-excitation networks
34. Coordinate attention for efficient mobile network design
35. ECA-Net: Efficient channel attention for deep convolutional neural networks
36. SimAM: A simple, parameter-free attention module for convolutional neural networks
37. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv:1409.1556, 2014.
38. Deep residual learning for image recognition
39. Batch normalization: Accelerating deep network training by reducing internal covariate shift