计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 176-180.doi: 10.11896/JsJkx.191100206

• 计算机图形学 & 多媒体 • 上一篇    下一篇

基于改进YOLO-V2算法的遥感图像目标检测技术研究

张曼, 李杰, 丁荣莉, 成昊天, 沈霁   

  1. 上海航天电子技术研究所 上海 201109
  • 发布日期:2020-07-07
  • 通讯作者: 张曼(manzhang_sh@163.com)

Remote Sensing Image ObJect Detection Technology Based on Improved YOLO-V2 Algorithm

ZHANG Man, LI Jie, DING Rong-li, CHENG Hao-tian and SHEN Ji   

  1. Shanghai Aerospace Electronics Technology Research Institute,Shanghai 201109,China
  • Published:2020-07-07
  • About author:ZHANG Man, born in 1993, master’s degree.Her main research interests include image processing and remote sensing application.

摘要: 传统遥感图像目标检测方法的时间复杂度高且精准率低,如何快速准确地检测遥感图像中的特定目标成为当前的研究热点。为解决这一问题,文中在YOLO-V2目标检测算法的基础上进行改进,减少了卷积层数与维度,并结合特征金字塔思想,增加了检测尺度,达到了提高检测精度的目的。同时给出了一种基于深度学习的遥感图像目标检测算法的通用处理框架,解决了无法直接处理大幅遥感图像的问题。在DOTA数据集上进行对比实验,结果表明改进YOLO-V2算法在15个类别上的精准率和召回率均优于YOLO-V2算法,mAP值提高了0.12。在时间复杂度方面,所提方法略低于YOLO-V2算法;在大小为416×416的图像小块上,改进YOLO-V2算法相比YOLO-V2检测时间缩短了0.1ms。

关键词: YOLO-V2, 多尺度, 目标检测, 深度学习, 特征金字塔, 遥感图像

Abstract: Traditional method of remote sensing image obJect detection has the disadvantages of high time complexity and low precision.How to detect specific targets in remote sensing images quickly and accurately has become a hot research topic.In order to solve this problem,this paper improves the YOLO-V2 obJect detection algorithm,reduces the convolution layers and dimension,and combined with the ideal of feature pyramid to increase the detection features’ scale,so as to achieve the purpose of improving detection accuracy.At the same time,a general processing framework of remote sensing image obJect detection algorithm based on deep learning is presented to solve the problem that large remote sensing images cannot be directly processed.Comparison experiments on the DOTA dataset show that the improved YOLO-V2 algorithm has better accuracy and recall rate in 15 categories than the YOLO-V2 algorithm,and the mAP value is increased by 0.12.In terms of time complexity,it is slightly lower than the YOLO-V2 algorithm.Specifically,on 416×416 image patches,the detection time of the improved YOLO-V2 algorithm is reduced by 0.1 ms compared to the YOLO-V2 algorithm.

Key words: Deep learning, Feature pyramid, Multiscale, ObJect detection, Remote sensing image, YOLO-V2

中图分类号: 

  • TP751
[1] CAO Q,ZHENG H,LI X S.A Cloud Detection Method for Sate-llite Remote Sensing Image Based on Texture Features.Journal of Aeronautics,2007,28(3):661-666.
[2] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate obJect detection and semantic segmentation//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:580-587.
[3] UIJLINGS J R R,VAN DE SANDE K E A,GEVERS T,et al.Selective search for obJect recognition.International Journal of Computer Vision,2013,104(2):154-171.
[4] GIRSHICK R.Fast r-cnn.arXiv:1504.08083,2015.
[5] REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time obJect detection with region proposal networks//Advances In Neural Information Processing Systems.2015:91-99.
[6] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time obJect detect//Las Vegas:Proceeding of the IEEE Conference on Computer Vision and Pattern Recogniton.IEEE,2016.
[7] REDMOD J,FARHADI A.YOLO9000:Better,Faster,Stronger//2017 IEEE Conference on Computer Vision and Pattern Recognition,Honolulu.IEEE,2017:6517-6525.
[8] SEFERBEKOV S S,LGLOVIKOV V I,et al.Feature Pyramid Network for Multi-Class land Segmentation//IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.IEEE,2018.
[9] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition.arXiv:1409.1556,2014.
[10] LIN M,CHEN Q,YAN S.Network in network.arXiv:1312.4400,2013.
[11] LOFE S,SZEGEDY C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift//International Conference on Machine Learning.2015.
[12] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[13] ZHANG S J,ZHAO H C.Algorithm research of optimal cluster number and initial cluster center.Application Research of Computers,2017,34(6):1617-1620.
[14] ROTHE R,GUILLAUMIN M,VAN GOOL L.Non-maximum suppression for obJect detection by passing messages between windows//Asian Conference on Computer Vision.Springer,Cham,2014:290-306.
[15] VAN ETTEN A.You Only Look Twice:Rapid Multi-Scale ObJect Detection in Satellite Imagery//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[16] XIA G S,BAI X,et al.DOTA:A Large-scale Dataset for ObJect Detection in Aerial Images//IEEE Conference on Computer Vision and Pattern Recogniton.2018.
[17] QIAN N.On the momentum term in gradient descent learning algorithms.Neural Networks,1999,12(1):145-151.
[1] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 魏恺轩, 付莹.
基于重参数化多尺度融合网络的高效极暗光原始图像降噪
Re-parameterized Multi-scale Fusion Network for Efficient Extreme Low-light Raw Denoising
计算机科学, 2022, 49(8): 120-126. https://doi.org/10.11896/jsjkx.220200179
[5] 王坤姝, 张泽辉, 高铁杠.
基于Hachimoji DNA和QR分解的遥感图像可逆隐藏算法
Reversible Hidden Algorithm for Remote Sensing Images Based on Hachimoji DNA and QR Decomposition
计算机科学, 2022, 49(8): 127-135. https://doi.org/10.11896/jsjkx.210700216
[6] 刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉.
基于边框距离度量的增量目标检测方法
Incremental Object Detection Method Based on Border Distance Measurement
计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132
[7] 王灿, 刘永坚, 解庆, 马艳春.
基于软标签和样本权重优化的Anchor Free目标检测算法
Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization
计算机科学, 2022, 49(8): 157-164. https://doi.org/10.11896/jsjkx.210600240
[8] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[9] 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩.
基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究
Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network
计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094
[10] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[11] 王馨彤, 王璇, 孙知信.
基于多尺度记忆残差网络的网络流量异常检测模型
Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network
计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[12] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[13] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[14] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[15] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!