典型文献
Ghost edge detection based on HED network
文献摘要：
In this paper,we present an edge detection scheme based on ghost imaging(GI)with a holistically-nested neural network.The so-called holistically-nested edge detection(HED)network is adopted to combine the fully convolutional neural network(CNN)with deep supervision to learn image edges effectively.Simulated data are used to train the HED network,and the unknown object's edge information is reconstructed from the experimental data.The experiment results show that,when the compression ratio(CR)is 12.5％,this scheme can obtain a high-quality edge information with a sub-Nyquist sampling ratio and has a better performance than those using speckle-shifting GI(SSGI),compressed ghost edge imaging(CGEI)and subpixel-shifted GI(SPSGI).Indeed,the proposed scheme can have a good signal-to-noise ratio performance even if the sub-Nyquist sampling ratio is greater than 5.45％.Since the HED network is trained by numerical simulations before the experiment,this proposed method provides a promising way for achieving edge detection with small measurement times and low time cost.
文献关键词：
中图分类号：
作者姓名：
Shengmei Zhao;Yifang Cui;Xing He;Le Wang
作者机构：
Institute of Signal Processing and Transmission,Nanjing University of Posts and Telecommunications(NUPT),Nanjing 210003,China;Key Lab of Broadband Wireless Communication and Sensor Network Technology(NUPT),Ministry of Education,Nanjing 210003,China
文献出处：
引用格式：
[1]Shengmei Zhao;Yifang Cui;Xing He;Le Wang-.Ghost edge detection based on HED network)[J].光电子前沿（英文版）,2022(03):24-32
A类：
SSGI,CGEI,SPSGI
B类：
Ghost,detection,HED,network,this,paper,we,present,scheme,ghost,imaging,holistically,nested,neural,so,called,adopted,combine,fully,convolutional,deep,supervision,learn,image,edges,effectively,Simulated,data,are,used,unknown,object,information,reconstructed,from,experimental,results,show,that,when,compression,ratio,CR,can,obtain,high,quality,Nyquist,sampling,has,better,performance,than,those,using,speckle,shifting,compressed,subpixel,shifted,Indeed,proposed,have,good,signal,noise,even,greater,Since,trained,by,numerical,simulations,before,method,provides,promising,way,achieving,small,measurement,times,low,cost
AB值：
0.531099
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
