SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection

doi:10.3969/j.issn.0372-2112.2020.01.010

您当前的位置：

首页 >

文章列表页 >

SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection

更新时间：2025-07-08

- SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection
- Acta Electronica Sinica Vol. 48, Issue 1, Pages: 84-91(2020)
- 作者机构：
  
  西北工业大学航海学院,陕西,西安,710072
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61271143)
- DOI：10.3969/j.issn.0372-2112.2020.01.010
  CLC： TP183
- Published Online：25 January 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection[J]. Acta Electronica Sinica, 2020, 48(1): 84-91.
DOI：

SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection[J]. Acta Electronica Sinica, 2020, 48(1): 84-91. DOI： 10.3969/j.issn.0372-2112.2020.01.010.

摘要

针对SSD原始附加特征提取网络（Original Additional Feature Extraction Network，OAFEN）中stride操作造成图像小目标信息丢失和串联结构产生的多尺度特征之间冗余度较大的问题，提出了一种计算量小、感受野大的深度可分离空洞卷积（Depthwise Separable Dilated Convolution，DSDC），并利用DSDC设计了一个包含三个独立子网络的并行附加特征提取网络（Parallel Additional Feature Extraction Network，PAFEN）.PAFEN上路用两个DSDC提取尺寸为19*19和3*3的特征图；中路用一个DSDC提取尺寸为10*10的特征图；下路用两个DSDC提取尺寸为5*5和1*1的特征图.实验结果表明，在SSD框架内，PAFEN在mAP和检测时间等方面均优于OAFEN，适用于地面小目标的检测任务.

Abstract

Aiming at the problems of small target information loss caused by stride operation and large redundancy among multi-scale feature maps generated by serial structure in original additional feature extraction network (OAFEN) of SSD

a depthwise separable dilated convolution (DSDC) with small computation and large field of receptivity is proposed; then a parallel additional feature extraction network (PAFEN) with three independent subnetworks is designed by using five DSDCs. In upper subnetwork of PAFEN

two DSDCs are used to extract 19*19 and 3*3 feature maps. In intermediate subnetwork of PAFEN

one DSDC is used to extract 10*10 feature maps.In lower subnetwork of PAFEN

two DSDCs are used to extract 5*5 and 1*1 feature maps. The experimental results show that within the framework of SSD

PAFEN is superior to OAFEN in terms of mAP and detection time

and is suitable for ground small target detection tasks.

关键词

Keywords

references

Views

172

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cross-Modal SAR Target Detection via Progressive Knowledge Transfer

Cross-Layer Attention Feature Interaction and Multi-Scale Channel Attention Network for Single Image Dehazing

A Lightweight Music Recognition Method Based on Improved CRNN

Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection

Cascaded Inverse Residual Network for Lightweight Object Detection Model in Remote Sensing Image

Related Author

ZHAO Guo-wei

JIANG Jia-qing

DONG Gang-gang

SUN Hang

FU Qiu-yue

LI Bo-hui

DAN Zhi-ping

YU Mei

Related Institution

National Key Laboratory of Radar Signal Processing, Xidian University

College of Computer and Information Technology, China Three Gorges University

Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University

School of Information and Safety Engineering, Zhongnan University of Economics and Law

School of Computer Science， Nanjing University of Posts and Telecommunications

⁰