Abstract：To solve the problems of large changes in target scale and serious environmental interference during nearshore ship detection, an improved anchorless frame detection algorithm of YOLOX is proposed. Firstly, the contextual transformer (CoT) module is introduced in the backbone network to enhance the expression capability and improve the problem of severe environmental interference by dynamically using contextual information. Secondly, SimAM attention is embedded between the feature pyramid and detection head to enrich semantic information and improve small target detection accuracy. Furtherly, CIOU is used to replace the original loss function to improve the convergence speed. Finally, the depth-separable convolution is used to replace the ordinary convolution in the feature pyramid to reduce the number of parameters and improve the detection speed. The experimental results show that on the SeaShips dataset, the improved model improves the accuracy by 6.73%, mAP reaches 96.63%, and detection speed reaches 48.6 frames per second while reducing the number of parameters, which can detect near-shore ships in real time and with high accuracy.
GUO L, YU H Y, ZHOU S Q. Inshore Ship Detection Method Based on SimAM Attention Mechanism［J］. Journal of Harbin Institute of Technology, 2023, 55(5):14-21.
［4］
SHAO Z F, WANG L G, WANG Z Y, et al. Saliency-aware convolution neural network for ship detection in surveillance video［J］. IEEE Transactions on Cricuits and Systems for Video Technology, 2019, 30(3): 781-794.
［6］
REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks［C］// IEEE Transactions on Pattern Analysis and Machine Intelligence.IEEE, 2017.
［8］
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector［C］//European Conference on Computer Vision. Amsterdam Netherland, 2016.
［10］
DUAN K, BAI S, XIE L, et al. CenterNet: Keypoint triplets for object detection［C］//in Proc. IEEE/CVF Int. Conf. Comput. Vis,(ICCV). Seoul, Korea, 2019, 6569-6578.
［11］
TIAN Z, SHEN C H, CHEN H, et al. FCOS: Fully convolutional one-stage object detection［C］// The 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 2019, 9626-9635.
GE Z, LIU S, WANG F, et al. ［C］// IEEE Conference on Computer Vision and Pattern Recognition. IEEE,2021,2107.08430.
［18］
LI Y, YAO T, PAN Y, et al. Contextual Transformer Networks for Visual Recognition［C］//IEEE Trans Pattern Anal Mach Intell, IEEE. 2023,45(2): 1489-1500.
CHENG S H, YANG Z H, WANG C. Research on Gesture Recognition Algorithm under Multi-channel Fusion and Design of Ship Virtual Interaction Platform. Acta Metrologica Sinica, 2022, 43(7): 856-862.
［9］
LAW H, DENG J. CornerNet: Detecting objects as paired key points［C］//in Proc. Eur Conf Comput Vis, ECCV. Munich, Germany, 2018, 734-750.
［17］
YI C C, XU B, CHEN J, et al. An Improved YOLOX Model for Detecting Strip Surface Defects［J］. Steel Research International, 2022, 93: 2200505.
CAI H, YANG G W, WANG D D. Intelligent supervision system solution of electronic bayonet in inland waterways［J］. China Water Transport, 2020(4): 61-64.
［7］
BOCHKOVSKIY A, WANG C Y, LIAO H Y M, et al. YOLOv4: optimal speed and accuracy of object detection［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2020.
［13］
PENG H, TIAN X D. Improved YOLOXs Anchor-Free SAR Image Ship Target Detection［J］. IEEE Access, 2022(10):70001-70015.
CHENG S H, XIE W R, ZHANG D F, et al. Fall Behavior Recognition Based on Multi-algorithm Fusion ［J］. Acta Metrologica Sinica, 2022. 43(1): 107-113.
［20］
YANG L X, ZHANG R Y, LI L D, et al. SimAM: A simple parameter-free attention module for convolutional neural networks［C］//Proceedings of the 38th Internarional Conference on Machine Learning. New York,USA, 2021,11863-11874.
ZHANG L G, JIANG Y X, TIAN G J. Research on Unmanned Aerial Vehicle to Ground Vehicle Target Detection Algorithm Based on Multiscale Fusion Method［J］. Acta Metrologica Sinica, 2021, 42(11): 1436-1442.
［5］
GIRSHICK R. Fast R-CNN［C］// 2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile, 2015, 1440-1448.
YAO T T, ZHANG B, LIU X M. Ship Detection under Feature Enhanced Fully Convolutional Network［J］. Journal of Computer Aided Design and Computer Graphics, 2022. 34(7): 1028-1036.
LIN Y, CHEN L, WANG G P, et al. Improved YOLOv3 traffic sign recognition algorithm［J］. Science Technology and Engineering, 2022, 22(27): 12030-12037.
［12］
ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios［C］//2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal, Canada, 2021,2778-2788.
AN H N, YANG J Z, DENG W C, et al. Improved detection network based on YOLOx residual block fusion CoA module［J］. Computer system applications, 2022, 31(8): 245-251.
2024, Vol. 45 
