A remote sensing target detection model based on lightweight feature enhancement and feature refinement extraction

Author:

Guo Dongen1ORCID,Zhou Zhuoke1,Guo Fengshuo2,Jia Chaoxin1,Huang xiaohong1,Feng Jiangfan3,Shen zhen1

Affiliation:

1. Nanyang Institute of Technology

2. Henan University School of Computer and Information Engineering

3. Chongqing University of Posts and Telecommunications

Abstract

Abstract

Remote sensing image (RSI) target detection methods based on traditional multi scale feature fusion (MSFF) have achieved great success. However, the traditional MSFF method significantly increases the computational cost during model training and inference, and the simple fusion operation may lead to the semantic confusion of the feature map, which cannot realize the refined extraction of features by the model. In order to reduce the computational effort associated with the MSFF operation and to enable the features in the feature map to present an accurate, fine-grained distribution, we propose a single-stage detection model(RS-YOLO). Our main additions to RS-YOLO are a computationally smaller and faster QS-E-ELEN (Quick and Small E-ELEN) module and a feature refinement extraction (FRE) module. In the QS-E-ELEN module We utilize QSBlock,jump-join, and convolution operations to fuse features on different scales and reduce the computational effort of the model by exploiting the similarity of the RSI feature map channels. In order for the model to better utilize the enhanced features, FRE makes the feature mapping of the target to be detected in the RSI accurate and refined. By conducting experiments on the popular NWPU-VHR- 10 and SSDD datasets, we derive results that show that RS-YOLO outperforms most mainstream models in terms of the trade-off between accuracy and speed. Specifically, in terms of accuracy, it improves 1.6% and 1.7% compared to the current state-of-the-art models, respectively. At the same time, RS-YOLO reduces the number of parameters and computational effort.

Publisher

Research Square Platform LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3