融合混合域注意力的YOLOv4在船舶检测中的应用

计算机与现代化 ›› 2021, Vol. 0 ›› Issue (09): 75-82.

融合混合域注意力的YOLOv4在船舶检测中的应用

(1.中国航天科工集团第二研究院,北京100039;2.北京航天长峰股份有限公司,北京100039)

出版日期:2021-09-14 发布日期:2021-09-14
作者简介:赵玉蓉(1996—),女,陕西榆林人,硕士研究生,研究方向:计算机视觉,深度学习,E-mail: zyr_xx@126.com; 郭会明(1966—),男,研究员,硕士生导师,研究方向:计算机信息系统集成与应用,E-mail: 13901314693@139.com; 焦函(1981—),男,研究员,博士后,研究方向:大数据,人工智能,E-mail: xiaojiaomail@163.com; 章俊伟,男,工程师,硕士,研究方向:边境管控智能应用,E-mail: zjw_jenry@foxmail.com
基金资助:
国家重点研发计划项目(2020YFC0833406)

Application of YOLOv4 with Mixed-domain Attention in Ship Detection

(1. The Second Research Institute of China Aerospace Science and Industry Corporation, Beijing 100039, China;

2. Beijing Aerospace Changfeng Co. Ltd., Beijing 100039, China)

Online:2021-09-14 Published:2021-09-14

摘要/Abstract

摘要： 海上船舶检测在海事监管领域发挥着重要的作用，然而由于海上的复杂环境以及船型的多样性，现有的基于卷积神经网络的方法在船舶检测领域难以同时满足高精度和实时的要求。针对复杂环境下海上船舶实时检测困难的问题，提出一种基于YOLOv4的YOLO-Marine模型，该模型将混合注意力机制引入检测网络的backbone部分，首先使用Mosaic方法对船舶数据进行预处理，然后通过K-Means+〖KG-*3〗+聚类得到初始anchor，并在Darknet上实现模型，用真实船舶数据集对模型进行训练和评估。实验结果表明YOLO-marine与YOLOv4相比，将船舶检测任务的mAP提升了2.1个百分点，在保证实时性的同时有效提高了船舶检测的精度，且在小目标和遮挡目标检测方面效果突出。

关键词: 船舶检测, 数据增强, YOLO, K-means++, 注意力机制

Abstract: Marine ship detection plays an important role in the maritime field. Due to the complicated environment and the diversity of ships, existing methods based on convolutional neural network cannot achieve both high accuracy and real-time performance. To solve the problem of ship’s real-time detection in complicated environment, a YOLO-marine model based on YOLOv4 is proposed in which the domain attention mechanism is introduced into backbone. Firstly, the Mosaic method is used to preprocess the ship data. Then the K-Means++ algorithm is used to get initial anchors. The model is implemented on Darknet for training and evaluation with the real ship dataset. The experimental result show that compared with YOLOv4, YOLO-marine improves the mAP of ship detection task by 2.1 percentage points. The model can effectively improve the accuracy of ship detection while ensuring real-time performance. It also gives outstanding results in small and occluded target.

Key words: ship detection, data enhancement, YOLO, K-means+〖KG-*3〗+, attention mechanism

赵玉蓉, 郭会明, 焦函, 章俊伟. 融合混合域注意力的YOLOv4在船舶检测中的应用[J]. 计算机与现代化, 2021, 0(09): 75-82.

ZHAO Yu-rong, GUO Hui-ming, JIAO Han, ZHANG Jun-wei. Application of YOLOv4 with Mixed-domain Attention in Ship Detection[J]. Computer and Modernization, 2021, 0(09): 75-82.

参考文献

［1］黄洲,齐向阳. 合成孔径雷达图像船舶检测分析系统［J］. 微计算机信息, 2009(6):298-300.
［2］ HUANG J, JIANG Z G, ZHANG H P, et al. Region proposal for ship detection based on structured forests edge method［C］// 2017 IEEE International Geoscience and Remote Sensing Symposium. 2017:1856-1859.
［3］ 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 Circuits and Systems for Video Technology, 2020,30(3):781-794.
［4］ MOHANTY N C. Image enhancement and recognition of moving ship in cluttered background［J］. IEEE Transaction on PAMI, 1981,3(5):606-610.
［5］胡耀辉,张科,邢超. 基于海天线的舰船弱小目标检测［J］. 西北工业大学学报, 2019,37(1):35-40.
［6］ LIN H N, SHI Z W, ZOU Z X. Fully convolutional network with task partitioning for inshore ship detection in optical remote sensing images［J］. IEEE Geoscience Remote Sensing Letters, 2017,14(10):1665-1669.
［7］ 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. 2016:779-788.
［8］ REDMON J, FARHADI A. YOLO9000: Better, faster, stronger［C］// IEEE Conference on Computer Vision & Pattern Recognition. 2017:6517-6525.
［9］ REDMON J, FARHADI A. YOLOv3: An incremental improvement［J］. Computer Vision and Pattern Recognition, 2018， arXiv:1804.02767.
［10］BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection［J］. Computer Vision and Pattern Recognition, 2020，arXiv:2004.10934.
［11］段敬雅,李彬,董超,等. 基于YOLOv2的船舶目标检测分类算法［J］. 计算机工程与设计, 2020,41(6):209-215.
［12］CHEN L K, LI B Y, QI L. Improved YOLOv3 algorithm for ship target detection［C］// 2020 39th Chinese Control Conference. 2020:7288-7293.〖HJ1.85mm〗
［13］WANG Y, WANG L, JIANG Y, et al. Detection of self-build data set based on YOLOv4 network［C］// 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education. 2020:640-642.
［14］HU J, SHEN L, SUN G. Squeeze-and-excitation networks［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:7132-7141.
［15］XIAO T J, XU Y C, YANG K Y, et al. The application of two-level attention models in deep convolutional neural network for fine-grained image classification［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:842-850.
［16］WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module［C］// Proceedings of the European Conference on Computer Vision. 2018:3-19.
［17］BI F K, ZHU B C, GAO L, et al. A visual search inspired computational model for ship detection in optical satellite images［J］. IEEE Geoscience Remote Sensing Letters, 2012,9(4):749-753.
［18］SONG Z, SUI H G, WANG Y J. Automatic ship detection for optical satellite images based on visual attention model and LBP［C］// 2014 IEEE Workshop on Electronics, Computer and Applications. 2014:722-725.
［19］CUI H Y, YANG Y, LIU M Y, et al. Ship detection: An improved YOLOv3 method［C］// OCEANS 2019-Marseille. 2019:1-4.
［20］DENG J, DONG W, SOCHER R, et al. Imagenet: A large-scale hierarchical image database［C］// 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009:248-255.
［21］EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes (VOC) challenge［J］. International Journal of Computer Vision, 2009,88(2):303-338.
［22］SHAO Z F, WU W J, WANG Z Y, et al. SeaShips: A large-scale precisely annotated dataset for ship detection［J］. IEEE Transactions on Multimedia, 2018,20(10):2593-2604.
［23］ZHENG Y T, ZHANG S. Mcships: A large-scale ship dataset for detection and fine-grained categorization in the wild［C］// 2020 IEEE International Conference on Multimedia and Expo. 2020:1-6.
［24］ARTHUR D, VASSILVITSKII S. K-Means+〖KG-*3〗+: The advantages of careful seeding［C］// Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms. 2007:7-9.
［25］ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box regression［C］// Proceedings of the AAAI Conference on Artificial Intelligence. 2020:12993-13000.

[1]	何思达, 陈平华. 基于意图的轻量级自注意力序列推荐模型[J]. 计算机与现代化, 2024, 0(12): 1-9.
[2]	赵晨阳, 薛涛, 刘俊华. 基于改进Stable Diffusion的时尚服饰图案生成[J]. 计算机与现代化, 2024, 0(12): 15-23.
[3]	黄庭培1, 马禄彪1, 李世宝2, 刘建航1. 基于WiFi和原型网络的手势识别方法[J]. 计算机与现代化, 2024, 0(12): 34-39.
[4]	张思敏, 刘新妹, 殷俊龄, 李宝玲. 基于YOLOv7改进的PCB缺陷检测方法[J]. 计算机与现代化, 2024, 0(12): 45-52.
[5]	张晓东1, 白广芝1, 李敏1, 李昊洋2. 基于经验小波变换的油气井产量预测模型 [J]. 计算机与现代化, 2024, 0(12): 53-58.
[6]	刘云海1, 冯广1, 吴晓婷2, 杨群2. 复杂施工场景下的安全帽佩戴检测算法[J]. 计算机与现代化, 2024, 0(12): 66-71.
[7]	谷岳, 邓松峰, 沈霁, 穆文涛, 赵恩棋. 基于改进YOLOv8的SAR舰船目标检测算法[J]. 计算机与现代化, 2024, 0(12): 78-83.
[8]	王艳媛, 茅正冲. 中英文场景文本图像的检测和识别算法[J]. 计算机与现代化, 2024, 0(12): 84-90.
[9]	李钧超1, 尤菲1, 张超2, 苏乐乐2, 龚龑2. 基于新型多目标浣熊优化算法的BiLSTM-Attention#br# 预测模型及误差分析[J]. 计算机与现代化, 2024, 0(11): 70-76.
[10]	张宇1, 2, 黎靖1, 2, 马铭1, 2, 王众祥1, 2, 孙妍1, 2. YOLOLW:一个新的轻量级目标检测模型[J]. 计算机与现代化, 2024, 0(11): 91-98.
[11]	董玉玟. 基于改进YOLOv7-tiny的多尺度运动目标检测算法[J]. 计算机与现代化, 2024, 0(11): 99-105.
[12]	祁贤, 刘大铭, 常佳鑫. 基于改进自注意力机制的多视图三维重建[J]. 计算机与现代化, 2024, 0(11): 106-112.
[13]	陈凯1, 李宜汀1, 2, 全华凤1 . 基于改进YOLOv8的河道废弃瓶检测方法[J]. 计算机与现代化, 2024, 0(11): 113-120.
[14]	杨骏1, 胡为1, 朱文福2. 基于改进MobileNetV3的视觉SLAM回环检测算法[J]. 计算机与现代化, 2024, 0(10): 21-26.
[15]	魏学诚1, 江凌云1, 李研2, 何非2. 改进YOLOv5的路侧单目视角小目标检测算法[J]. 计算机与现代化, 2024, 0(10): 27-34.