Optimization of ship target detection algorithm based on random forest and regional convolutional network

Zhong Han, Long Ma, He Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Target detection can assist in detecting the position of the target ship, which is an important part of the intelligent ship visual aid system. With the development and perfection of deep learning, the convolutional neural network technology has been continuously optimized. And it can automatically learn and extract features of objects in images, providing stronger distinguishing power and representation ability. In this paper, various optimization algorithms of convolutional neural networks are compared. Aiming at the problem of unbalanced ship targets in remote sensing images of near-port areas, a ship target detection algorithm based on random forest and Faster-RCNN is proposed. The random forest algorithm is used for model optimization due to its insensitivity to multi-collinearity. The positive effect of the optimized algorithm on accuracy is verified through experiments.

源语言英语
主期刊名Proceedings - 2019 International Conference on Electronic Engineering and Informatics, EEI 2019
出版商Institute of Electrical and Electronics Engineers Inc.
375-382
页数8
ISBN(电子版)9781728140766
DOI
出版状态已出版 - 11月 2019
活动2019 International Conference on Electronic Engineering and Informatics, EEI 2019 - Nanjing, 中国
期限: 8 11月 201910 11月 2019

出版系列

姓名Proceedings - 2019 International Conference on Electronic Engineering and Informatics, EEI 2019

会议

会议2019 International Conference on Electronic Engineering and Informatics, EEI 2019
国家/地区中国
Nanjing
时期8/11/1910/11/19

指纹

探究 'Optimization of ship target detection algorithm based on random forest and regional convolutional network' 的科研主题。它们共同构成独一无二的指纹。

引用此