Flying object recognition algorithm based on region CNN

LIU Congcong; YING Jie; YANG Haima; LIU Jin; LI Jun

doi:10.13873/J.1000-9787(2021)01-0110-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Flying object recognition algorithm based on region CNN

更新时间：2025-09-11

- Flying object recognition algorithm based on region CNN
- Vol. 40, Issue 1, Pages: 110-113+117(2021)
- 作者机构：
  
  1. 上海理工大学光电信息与计算机工程学院
  2. 上海工程技术大学电子电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2021)01-0110-04
  CLC： E926.4;TP183;V355.1;TP391.41
- Published：2021
- 稿件说明：
移动端阅览
[1]刘聪聪,应捷,杨海马,刘瑾,李筠.基于区域卷积神经网络的空中飞行物识别算法[J].传感器与微系统,2021,40(01):110-113+117.

LIU Congcong, YING Jie, YANG Haima, et al. Flying object recognition algorithm based on region CNN[J]. 2021, 40(1): 110-113+117.
[1]刘聪聪,应捷,杨海马,刘瑾,李筠.基于区域卷积神经网络的空中飞行物识别算法[J].传感器与微系统,2021,40(01):110-113+117. DOI： 10.13873/J.1000-9787(2021)01-0110-04.

LIU Congcong, YING Jie, YANG Haima, et al. Flying object recognition algorithm based on region CNN[J]. 2021, 40(1): 110-113+117. DOI： 10.13873/J.1000-9787(2021)01-0110-04.

摘要

针对飞行物检测中

由于目标背景复杂、姿态不一导致的识别准确率低的问题

提出改进的基于区域卷积神经网络Faster R-CNN的空中飞行物识别算法

使用消色差折射式望远镜ETX80和个人电脑（PC）构建空中飞行物识别系统。首先

构建包含无人机、飞机和飞鸟三种飞行物的数据集

对数据集进行标注和划分;然后

利用ResNet101深度残差网络提取图像特征

并输入构建的深度学习网络模型进行训练

网络模型包括区域建议网络、感兴趣区域池化层和分类层。测试结果证明:该方法能够在不同背景下的无人机、飞机、飞鸟三类空中飞行物的识别上达到良好的效果

检测平均准确率为96.7%

比FasterR-CNN算法提高3.1%。

Abstract

Aiming at the problem that in detection of flying objects

due to the complex background of target and low recognition accuracy caused by different postures

a flying object recognition algorithm based on improved Faster R-CNN is proposed.The recognition algorithm uses the achromatic refracting telescope ETX80 and PC to construct the flying object recognition system.A dataset containing three kinds of flying objects of UAV

airplanes and birds is constructed

and the dataset is marked and divided.ResNet101 deep residual network is used to extract the image features

and input constructed deep learning network model for training.The network model includes the regional proposal network

the ROI pooling layer and the classification layer.The test results show that the method can achieve good results in the identification of three types of airborne objects such as uavs

airplanes and birds in different backgrounds.The mean average precision is 96.7%

which is 3.1% higher than that of Faster R-CNN algorithm.

关键词

Keywords

references

基于RPCCA的无人机目标跟踪定位算法 [J]. 代淑娴,张玉金,彭冬生,吴飞,马文锦,徐旸. 传感器与微系统 . 2019(04)

基于卷积神经网络的实时跟踪算法 [J]. 程朋,刘鹏程,程诚,周祥东,石宇. 传感器与微系统 . 2018(05)

Views

129

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Human behavior recognition method based on fusion model

Classification and recognition of floating objects on water surface based on DCNN

Method of hand gesture recognition based on CNN

Weld defect detection and recognition based on DenseNet network

Research on X-ray weld defects detection by deep CNN

Related Author

CHEN Xinyao

ZHANG Tianrong

ZHU Xuefen

MO Lufeng

BAO Jiasong

HUANG Xixia

JI Ke

LU Zhanbiao

Related Institution

School of Information Engineering,Zhejiang A&F University

Information and Educational Technology Center of Zhejiang A&F University

Key Laboratory of Marine Technology and Control Engineering Ministry of Communications,Shanghai Maritime University

School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science

Wuxi Jiangnan Institute of Computing Technology

⁰