Underwater Object Detection Method Based on Improved Faster RCNN
Source abstract
Abstract
In order to better utilize and protect marine organisms, reliable underwater object detection methods need to be developed. Due to various influencing factors from complex and changeable underwater environments, the underwater object detection is full of challenges. Therefore, this paper improves a two-stage algorithm of Faster RCNN (Regions with Convolutional Neural Network Feature) to detect holothurian, echinus, scallop, starfish and waterweeds. The improved algorithm has better performance in underwater object detection. Firstly, we improved the backbone network of the Faster RCNN, replacing the VGG16 (Visual Geometry Group Network 16) structure in the original feature extraction module with the Res2Net101 network to enhance the expressive ability of the receptive field of each network layer. Secondly, the OHEM (Online Hard Example Mining) algorithm is introduced to solve the imbalance problem of positive and negative samples of the bounding box. Thirdly, GIOU (Generalized Intersection Over Union) and Soft-NMS (Soft Non-Maximum Suppression) are used to optimize the regression mechanism of the bounding box. Finally, the improved Faster RCNN model is trained using a multi-scale training strategy to enhance the robustness of the model. Through ablation experiments based on the improved Faster RCNN model, each improved part is disassembled and then the experiments are carried out one by one, which can be known from the experimental results that, based on the improved Faster RCNN model, mAP@0.5 reaches 71.7%, which is 3.3% higher than the original Faster RCNN model, and the average accuracy reaches 43%, and the F1-score reaches 55.3%, a 2.5% improvement over the original Faster RCNN model, which shows that the proposed method in this paper is effective in underwater object detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Water Quality Monitoring Technologies · Maritime Navigation and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
References (45)
Show source-provided references
1. Xu, X., Zou, S., and Liu, J. (2021, January 24–26). Research on the promotion path of scientific and technological innovation ability of marine industry based on big data under the background of marine power strategy. Proceedings of the 2021 International Conference on E-Commerce and E-Management (ICECEM), Dalian, China.10.1109/ICECEM54757.2021.00077 ↗
2. Res2net: A new multi-scale backbone architecture10.1109/TPAMI.2019.2938758 ↗
3. Shrivastava, A., Gupta, A., and Girshick, R. (2016, January 27–30). Training region-based object detectors with online hard example mining. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.89 ↗
4. Rott, P., Bailey, R.A., Comstock, J.C., and Croft, B.J. (2000). A Guide to Sugarcane Diseases, La Librairie du Cirad.10.19182/agritrop/00220 ↗
5. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
6. Bodla, N., Singh, B., Chellappa, R., and Davis, L.S. (2005, January 17–20). Soft-NMS--improving object detection with one line of code. Proceedings of the IEEE International Conference on Computer Vision, Beijing, China.
7. SNIPER: Efficient multi-scale training
8. A novel smart energy theft system (SETS) for IoT-based smart home10.1109/JIOT.2019.2903281 ↗
9. Multi-View Deep Learning Framework for Predicting Patient Expenditure in Healthcare10.1109/OJCS.2021.3052518 ↗
10. Towards Precision Agriculture: IoT-enabled Intelligent Irrigation Systems Using Deep Learning Neural Network10.1109/JSEN.2021.3069266 ↗
11. Zhang, X., Chen, M., and Zhan, X. (2018, January 23–26). Behavioral cloning for driverless cars using transfer learning. Proceedings of the 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, USA.10.1109/PLANS.2018.8373488 ↗
12. Lin, Y.-Y., Yang, J.-Y., Kuo, C.-Y., Huang, C.-Y., Hsu, C.-Y., and Liu, C.-C.C. (2020, January 3–4). Use Empirical Mode Decomposition and Ensemble Deep Learning to Improve the Performance of Emotional Voice Recognition. Proceedings of the 2020 IEEE 2nd International Workshop on System Biology and Biomedical Systems (SBBS), Taichung, Taiwan.10.1109/SBBS50483.2020.9314946 ↗
13. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
14. Mittal, S., Srivastava, S., and Phani, .J.J. (2022). A Survey of Deep Learning Techniques for Underwater Image Classification. IEEE Trans. Neural Netw. Learn. Syst.10.1109/TNNLS.2022.3143887 ↗
15. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
16. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of theEuropean Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
17. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
18. A review of research on object detection based on deep learning10.1088/1742-6596/1684/1/012028 ↗
19. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
20. Purkait, P., Zhao, C., and Zach, C. (2017). SPP-Net: Deep absolute pose regression with synthetic views. arXiv.
21. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
22. Roh, M.C., and Lee, J. (2017, January 8–12). Refining faster-RCNN for accurate object detection. Proceedings of the 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), Nagoya, Japan.10.23919/MVA.2017.7986913 ↗
23. Detection of K-complexes in EEG waveform images using faster R-CNN and deep transfer learning10.1186/s12911-022-02042-x ↗
24. Iqbal, K., Odetayo, M., James, A., Salam, R.A., and Talib, A.Z.H. (2010, January 10–13). Enhancing the low quality images using Unsupervised Colour Correction Method. Proceedings of the 2010 IEEE International Conference on Systems, Man and Cybernetics, Istanbul, Turkey.10.1109/ICSMC.2010.5642311 ↗
25. Zhang, D., Kopanas, G., Desai, C., Chai, S., and Piacentino, M. (2016, January 10). Unsupervised underwater fish detection fusing flow and objectiveness. Proceedings of the 2016 IEEE Winter Applications of Computer Vision Workshops (WACVW), New York, NY, USA.10.1109/WACVW.2016.7470121 ↗
26. A Biological Sensor System Using Computer Vision for Water Quality Monitoring10.1109/ACCESS.2018.2876336 ↗
27. Anomalous Behaviors Detection for Underwater Fish Using AI Techniques
28. ROI: The search for best practices
29. Jang, E., Gu, S., and Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arXiv.
30. Occlusion Problem-Oriented Adversarial Faster-RCNN Scheme10.1109/ACCESS.2019.2955685 ↗
31. Hahn, G., Lutz, S.M., Laha, N., and Lange, C. (2020). A framework to efficiently smooth L1 penalties for linear regression. bioRxiv, 1–35.10.1101/2020.09.17.301788 ↗
32. Qassim, H., Verma, A., and Feinzimer, D. (2018, January 8–10). Compressed residual-VGG16 CNN model for big data places image recognition. Proceedings of the 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.10.1109/CCWC.2018.8301729 ↗
33. Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks10.1007/s42979-020-0114-9 ↗
34. Lin, S.L. (2021). Application Combining VMD and ResNet101 in Intelligent Diagnosis of Motor Faults. Sensors, 21.10.3390/s21186065 ↗
35. Fully convolutional attention network for biomedical image segmentation10.1016/j.artmed.2020.101899 ↗
36. Arthur, D., and Vassilvitskii, S. (2007, January 77–9). K-means++: The advantages of careful seeding. Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, New Orleans, LA, USA.
37. Genetic K-means algorithm10.1109/3477.764879 ↗
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. GFNet: Gate Fusion Network with Res2Net for Detecting Salient Objects in RGB-D Images10.1109/LSP.2020.2993471 ↗
40. Kaiyan, Z., Xiang, L., and Weibo, S. (2020, January 16–18). Underwater object detection using transfer learning with deep learning. Proceedings of the CIPAE 2020: 2020 International Conference on Computers, Information Processing and Advanced Education, Ottawa, ON, Canada.10.1145/3419635.3419678 ↗
41. Melanoma Lesion Detection and Segmentation Using YOLOv4-DarkNet and Active Contour10.1109/ACCESS.2020.3035345 ↗
42. A robust method for wheatear detection using UAV in natural scenes10.1109/ACCESS.2020.3031896 ↗
43. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
44. Wang, Y., Liu, J., Yu, S., Wang, K., Han, Z., and Tang, Y. (2021, January 22–24). Underwater Object Detection based on YOLO-v3 network. Proceedings of the 2021 IEEE International Conference on Unmanned Systems (ICUS), Beijing, China.10.1109/ICUS52573.2021.9641489 ↗
45. Occlusion aware underwater object tracking using hybrid adaptive deep SORT-YOLOv3 approach10.1007/s11042-022-13281-5 ↗