{"title":"基于图神经网络的多目标雷达数据关联","authors":"C. Wang, Yuhao Yang, Qian Zhang","doi":"10.1109/EEI59236.2023.10212706","DOIUrl":null,"url":null,"abstract":"In the complex target tracking scenarios, Bayesianbased method and the random finite set-based method cannot solve the data association problem. This paper introduces an end-to-end data association method based on graph neural networks. As far as we know, this is the first time in the field of radar that a graph neural network method is used to solve the data association problem. Different from the traditional data association method, our method can automatically learn the association criterion from the labeled samples, and the algorithm is more adaptable to complex scenarios. The simulation and experiments on real data can verify the effectiveness of our method.","PeriodicalId":363603,"journal":{"name":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data Association for Multiple Radar Targets Using Graph Neural Network\",\"authors\":\"C. Wang, Yuhao Yang, Qian Zhang\",\"doi\":\"10.1109/EEI59236.2023.10212706\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the complex target tracking scenarios, Bayesianbased method and the random finite set-based method cannot solve the data association problem. This paper introduces an end-to-end data association method based on graph neural networks. As far as we know, this is the first time in the field of radar that a graph neural network method is used to solve the data association problem. Different from the traditional data association method, our method can automatically learn the association criterion from the labeled samples, and the algorithm is more adaptable to complex scenarios. The simulation and experiments on real data can verify the effectiveness of our method.\",\"PeriodicalId\":363603,\"journal\":{\"name\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EEI59236.2023.10212706\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEI59236.2023.10212706","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Data Association for Multiple Radar Targets Using Graph Neural Network
In the complex target tracking scenarios, Bayesianbased method and the random finite set-based method cannot solve the data association problem. This paper introduces an end-to-end data association method based on graph neural networks. As far as we know, this is the first time in the field of radar that a graph neural network method is used to solve the data association problem. Different from the traditional data association method, our method can automatically learn the association criterion from the labeled samples, and the algorithm is more adaptable to complex scenarios. The simulation and experiments on real data can verify the effectiveness of our method.