[1]SHENG Ziqi,HUO Guanying.Detection of underwater mine target in sidescan sonar image based on sample simulation and transfer learning[J].CAAI Transactions on Intelligent Systems,2021,16(2):385-392.[doi:10.11992/tis.202101030]
Copy
Detection of underwater mine target in sidescan sonar image based on sample simulation and transfer learning
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
16
Number of periods:
2021 2
Page number:
385-392
Column:
吴文俊人工智能科学技术奖论坛
Public date:
2021-03-05
- Title:
- Detection of underwater mine target in sidescan sonar image based on sample simulation and transfer learning
- Keywords:
- mine target detection; sidescan sonar image; deep learning; sample simulation; transfer learning; convolutional neural network; pretraining; fine tuning
- CLC:
- TP391.4
- DOI:
- 10.11992/tis.202101030
- Abstract:
- Mine detection is of great significance to national defense and security. However, because of the high cost of underwater target sonar imaging experiments, usually sufficient mine sonar image samples cannot be obtained. Thus, the detection accuracy of mines and other targets is difficult to improve using deep neural networks. To solve this problem, a mine target detection and recognition method based on image simulation and transfer learning is proposed in this paper. The simulation model of a mine target is established in this proposed method according to the imaging mechanism of sidescan sonar to obtain numerous mine target images. Further, the deep convolutional neural network (CNN) is pretrained by the ImagenetNet dataset and then the deep CNN is fine-tuned by real and simulated mine images to adapt to mine targets detection. Finally, the fine-tuned CNN is used as the benchmark of the target detection network, and the target detection training is performed; real mine sonar images are used to verify the effectiveness of the proposed method. Experimental results show that the proposed mine detection method based on sample simulation and transfer learning can detect mine targets more accurately than some traditional feature extraction and detection, and deep learning-based detection methods using only real samples for training, which is helpful for underwater target detection.
- References:
-
[1] KUMAR N, MITRA U, NARAYANAN S. Robust object classification in underwater sidescan sonar images by using reliability-aware fusion of shadow features[J]. IEEE journal of oceanic engineering, 2015, 40(3):592-606.
[2] BARNGROVER C, ALTHOFF A, DEGUZMAN P, et al. A brain-computer interface (BCI) for the detection of mine-like objects in sidescan sonar imagery[J]. IEEE journal of oceanic engineering, 2016, 41(1):123-138.
[3] ACOSTA G G, VILLAR S A. Accumulated CA-CFAR process in 2-D for online object detection from sidescan sonar data[J]. IEEE journal of oceanic engineering, 2015, 40(3):558-569.
[4] BARNGROVER C, KASTNER R, BELONGIE S. Semisynthetic versus real-world sonar training data for the classification of mine-like objects[J]. IEEE journal of oceanic engineering, 2015, 40(1):48-56.
[5] DANIEL S, Le LEANNEC F, ROUX C, et al. Side-scan sonar image matching[J]. IEEE journal of oceanic engineering, 1998, 23(3):254-259.
[6] BRYNER D, SRIVASTAVA A, HUYNH Q. Elastic shapes models for improving segmentation of object boundaries in synthetic aperture sonar images[J]. Computer vision and image understanding, 2013, 117(12):1695-1710.
[7] FANDOS R, ZOUBIR A M. Optimal feature set for automatic detection and classification of underwater objects in SAS images[J]. IEEE journal of selected topics in signal processing, 2011, 5(3):454-468.
[8] CHO H, GU J, YU S C. Robust sonar-based underwater object recognition against angle-of-view variation[J]. IEEE sensors journal, 2016, 16(4):1013-1025.
[9] SAWAS J, PETILLOT Y, PAILHAS Y. Cascade of boosted classifiers for rapid detection of underwater objects[C]//Proceedings of the European Conference on Underwater Acoustics.[S.l.]2010, 10:1-8.
[10] FEI Tai, KRAUS D, ZOUBIR A M. Contributions to automatic target recognition systems for underwater mine classification[J]. IEEE transactions on geoscience and remote sensing, 2015, 53(1):505-518.
[11] SUN Yi, WANG Xiaogang, TANG Xiaoou. Deep learning face representation from predicting 10, 000 classes[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014:1891-1898.
[12] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6):1137-1149.
[13] REDMON J, FARHADI A. YOLOv3:an incremental improvement[J]. arXiv e-prints arXiv:1804.02767, 2018.
[14] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[J]. arXiv preprint arXiv:1512.02325, 2016.
[15] YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks?[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada, 2014:3320-3328.
[16] PAN S J, YANG Qiang. A survey on transfer learning[J]. IEEE transactions on knowledge and data engineering, 2010, 22(10):1345-1359.
[17] WANG Yuanyuan, WANG Chao, ZHANG Hong, et al. A SAR dataset of ship detection for deep learning under complex backgrounds[J]. Remote sensing, 2019, 11(7):765.
[18] HUO Guanying, WU Ziyin, LI Jiabiao. Underwater object classification in sidescan sonar images using deep transfer learning and semisynthetic training data[J]. IEEE access, 2020, 8:47407-47418.
[19] OQUAB M, BOTTOU L, LAPTEV L, et al. Learning and transferring mid-Level image representations using convolutional neural networks[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014:1717-1724.
- Similar References:
Memo
-
Last Update:
2021-04-25