{"title":"利用时域测量数据积累,使用 CNN 在杂乱环境中检测缓慢移动的点目标","authors":"Wonmin Cho, N. Kwak","doi":"10.26866/jees.2023.6.r.194","DOIUrl":null,"url":null,"abstract":"In modern radars, the target detection probability is increased by lowering the detection threshold via signal processing to detect a point target with a small radar cross-section value. However, a lower threshold increases the number of false targets. In the conventional tracking method, which uses a general tracking filter, the measurement data between scans should be compared. Therefore, for a large amount of acquired measurement data, the computational complexity can be reduced by accumulating the acquired measurement data over time, recognizing the target movement as a pattern, and training a convolutional neural network (CNN) model. Here, we propose a method to create a desired target scenario by transfer learning and estimate the target position using the activation map of a binary detector CNN model. The model can detect a target using the actual acquired radar data, and the processing time remains constant, regardless of the number of false alarms.","PeriodicalId":15662,"journal":{"name":"Journal of electromagnetic engineering and science","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Time-Domain Measurement Data Accumulation for Slow Moving Point Target Detection in Heavily Cluttered Environments Using CNN\",\"authors\":\"Wonmin Cho, N. Kwak\",\"doi\":\"10.26866/jees.2023.6.r.194\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In modern radars, the target detection probability is increased by lowering the detection threshold via signal processing to detect a point target with a small radar cross-section value. However, a lower threshold increases the number of false targets. In the conventional tracking method, which uses a general tracking filter, the measurement data between scans should be compared. Therefore, for a large amount of acquired measurement data, the computational complexity can be reduced by accumulating the acquired measurement data over time, recognizing the target movement as a pattern, and training a convolutional neural network (CNN) model. Here, we propose a method to create a desired target scenario by transfer learning and estimate the target position using the activation map of a binary detector CNN model. The model can detect a target using the actual acquired radar data, and the processing time remains constant, regardless of the number of false alarms.\",\"PeriodicalId\":15662,\"journal\":{\"name\":\"Journal of electromagnetic engineering and science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2023-11-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of electromagnetic engineering and science\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.26866/jees.2023.6.r.194\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of electromagnetic engineering and science","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.26866/jees.2023.6.r.194","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Time-Domain Measurement Data Accumulation for Slow Moving Point Target Detection in Heavily Cluttered Environments Using CNN
In modern radars, the target detection probability is increased by lowering the detection threshold via signal processing to detect a point target with a small radar cross-section value. However, a lower threshold increases the number of false targets. In the conventional tracking method, which uses a general tracking filter, the measurement data between scans should be compared. Therefore, for a large amount of acquired measurement data, the computational complexity can be reduced by accumulating the acquired measurement data over time, recognizing the target movement as a pattern, and training a convolutional neural network (CNN) model. Here, we propose a method to create a desired target scenario by transfer learning and estimate the target position using the activation map of a binary detector CNN model. The model can detect a target using the actual acquired radar data, and the processing time remains constant, regardless of the number of false alarms.
期刊介绍:
The Journal of Electromagnetic Engineering and Science (JEES) is an official English-language journal of the Korean Institute of Electromagnetic and Science (KIEES). This journal was launched in 2001 and has been published quarterly since 2003. It is currently registered with the National Research Foundation of Korea and also indexed in Scopus, CrossRef and EBSCO, DOI/Crossref, Google Scholar and Web of Science Core Collection as Emerging Sources Citation Index(ESCI) Journal. The objective of JEES is to publish academic as well as industrial research results and discoveries in electromagnetic engineering and science. The particular scope of the journal includes electromagnetic field theory and its applications: High frequency components, circuits, and systems, Antennas, smart phones, and radars, Electromagnetic wave environments, Relevant industrial developments.