咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Object detection of inland wat... 收藏

Object detection of inland waterway ships based on improved SSD model

作     者:Yang, Yang Chen, Pengyu Ding, Kaifa Chen, Zhuang Hu, Kaixuan 

作者机构:Dalian Univ Technol Sch Naval Architecture & Ocean Engn Dalian Peoples R China 

出 版 物:《SHIPS AND OFFSHORE STRUCTURES》 (船舶与海洋结构物)

年 卷 期:2023年第18卷第8期

页      面:1192-1200页

核心收录:

学科分类:08[工学] 0824[工学-船舶与海洋工程] 

基  金:Fundamental Research Funds for the Central Universities [DUT21GF302] 

主  题:Ship object detection loss function Soft-NMS feature pyramid up-sampling 

摘      要:To realise the rational utilisation of inland waterway resources, the intelligent identification method based on Convolutional Neural Network (CNN) is used to track and monitor the ships. Introducing the Repulsion Loss function and Soft-NMS algorithm to improve model, improve the detection precision of the partially occluded ships. The Feature Pyramid Networks (FPN) is used to realise the fusion of semantic information and spatial information of feature map to solve the problem of difficult detection of small object ships. Three up-sampling methods are used to extend and smooth the feature map. Through the above multiple algorithm improvements, the partial occlusion ships and small object ships in inland waterways are effectively detected.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分