The invention discloses a pedestrian identification method based on multi-domain spatial attribute correlation analysis. The method comprises the following steps: firstly, converting similarity measurement into difference distribution calculation of objects, performing statistics on visual similarity probability difference distribution of real and false objects, and determining two distribution maximum separable thresholds by utilizing the separability of the distribution; calculating the joint probability of the object under the known mobile phone signal track according to the separable threshold of the real/false object, and measuring the relevance between the object attributes by utilizing the joint probability; and determining a strong association mapping relationship between the identity attribute and the object and the identity according to the joint probability sorting. Test results of the method disclosed by the invention on two data sets prove that the effectiveness of the method is greatly improved compared with a pedestrian identification technology under an unsupervised condition.