Shengsen Pan, Qinglong Bao, Weibing Hou, Zengping Che
{"title":"An improved track segment association algorithm using MM-GNN method","authors":"Shengsen Pan, Qinglong Bao, Weibing Hou, Zengping Che","doi":"10.1109/PIERS.2017.8261827","DOIUrl":null,"url":null,"abstract":"Track breakages are common due to target maneuver, Doppler radar blind spot, long sampling interval and low detection probabilities. Note that the existed classic association algorithms have low correlation accuracy and poor practicability in dense environment or in track crossing situation. In this paper, we aim to present a new track segment association (TSA) technique to improve track continuity. An improved Multiple Model (MM) method with Global Nearest Neighbor (GNN) algorithm for track segment association is put forward, that is MM-GNN method. Simulation experiments show that proposed algorithm enhances the track maintenance performance and the track life of tracking result while ensuring the accuracy of tracking. Verified by real measured data, it confirms that the algorithm is suitable for multiple target tracking in practical radar system with the improvement of track continuity.","PeriodicalId":387984,"journal":{"name":"2017 Progress In Electromagnetics Research Symposium - Spring (PIERS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Progress In Electromagnetics Research Symposium - Spring (PIERS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PIERS.2017.8261827","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Track breakages are common due to target maneuver, Doppler radar blind spot, long sampling interval and low detection probabilities. Note that the existed classic association algorithms have low correlation accuracy and poor practicability in dense environment or in track crossing situation. In this paper, we aim to present a new track segment association (TSA) technique to improve track continuity. An improved Multiple Model (MM) method with Global Nearest Neighbor (GNN) algorithm for track segment association is put forward, that is MM-GNN method. Simulation experiments show that proposed algorithm enhances the track maintenance performance and the track life of tracking result while ensuring the accuracy of tracking. Verified by real measured data, it confirms that the algorithm is suitable for multiple target tracking in practical radar system with the improvement of track continuity.