Aiming at the problem of false target tracks resulting from cloud and rain clutter,as well as active and passive interference in multi-radar sensor systems,the autonomous learning a-bility of support vector machine(SVM)algorithm is used to construct a data-driven discriminant model for false track recognition.Based on the characteristics of data-driven and self-learning of artificial intelligence,the SVM model is designed for the target potential track obtained from the initial track.Through offline learning of the target track samples that have been marked as true or false,the SVM classifier for false track recognition is realized,a data-driven discrimination model is implemented to replace the fixed model constrained by the rules of prior knowledge.The false track is identified online by SVM classifier,and real-time elimination is completed.The result of the radar data measurement experiment shows that,the accuracy of the target false track of the al-gorithm is more than 95％,which fully meets the actual engineering application requirements.Compared with the traditional false track recognition methods which make hard judgments based on threshold or rules,the proposed algorithm not only improves the accuracy,but also has high real-time performance and can adapt to the complex clutter environment,which makes the method more adaptable and practical in practical applications.Therefore,the false track identification method based on SVM algorithm proposed has significant practical application value for the false track elimination problem in dense clutter scenes.
维普
万方数据
