The invention provides a method for initiating a track of a radar target based on a support vector machine, and relates to a method for initiating a track of a radar target based on a support vector machine, which aims at overcoming the defects of rough rule, setting of an empirical threshold, sudden degrading of property under strong clutter background and the like in the existing sequential processing method, and solving the problems of huge calculation amount and multiple batches of data measuring in a batch processing method. The method specifically comprises the following steps: 1, extracting motion information of a radar detection target as training sample features; 2, utilizing the training sample features to train the support vector machine, so as to obtain a decision function of an optimal hyperplane for classifying of the radar target; 3, utilizing a traditional enlightening type rule method to pre-select to-be-classified measuring data of a radar, so as to form pre-selected tracks; 4, by using the trained support vector machine as a classifier, classifying the pre-selected tracks, and distinguishing a real target from a virtual target, so as to obtain a track initiating result. The method belongs to the fields of radar target data processing and machine learning.