Sonar image object detection is an important part of underwater exploration,submarine rescue, hostile object reconnaissance and other tasks. The breakthrough of deep learning related technologies has brought new opportunities for the development of sonar image object detection. The performance of sonar image object detection algorithm based on deep learning is better than traditional methods,but the relevant systematic research and application are still insufficient. Therefore,a sonar image object detection system is designed to meet the requirements of accuracy,speed,portability,extensibility,and deployment environment of the system in practical applications by using the data driven advantages of the deep learning model. The system consists of three subsystems,which are data set generation,algorithm model training and testing,and model deployment. It is applied to underwater suspicious object detection task. The experimental results show that the object detection system can obtain good test data and has excellent application performance.
[1] LOU G T,ZHENG R H,LIU M Q,et al.Automatic target recognition in forward-looking sonar images using transfer learning[C]//Global Oceans 2020.Bilox:IEEE,2020.
[2] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[3] FAN Z M,XIA W J,LIU X,et al.Detection and segmentation of underwater objects from forwardlooking sonar based on a modified Mask RCNN[J].Signal,Image and Video Processing,2021,15(6):1135-1143.
[4] WANG Y M,LIU J X,YU S Q,et al.Underwater object detection based on YOLOv3 network[C]//IEEE International Conference on Unmanned Systems.Beijing:IEEE,2021.
[9] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016.
[10] ZHANG H C,WANG J Y.Towards adversarially robust object detection[C]//IEEE International Conference on Computer Vision.Seoul:IEEE,2019.
[11] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[EB/OL].[2020-04-23].https://arxiv.org/pdf/20 04.10934.pdf.
[12] WANG M,DENG W H.Deep visual domain adaptation:a survey[J].Neurocomputing,2018,312:135-153.
[13] PASZKE A,GROSS S,MASSA F,et al.PyTorch:an imperative style,high-performance deep learning library[C]//33rd Conference on Neural Information Processing Systems.Vancouver:Curran Associates Inc,2019.
[16] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016.
[17] XIE S N,GIRSHICK R,DOLLáR P,et al.Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017.
[18] GAO S H,CHENG M M,ZHAO K,et al.Res2Net:a new multi-scale backbone architecture[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(2):652-662.
[19] LIN T Y,DOLLáR P,GIRSHICK R B,et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017.
[20] LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:common objects in context[C]//13th European Conference on Computer Vision.Zurich:Springer,2014.