The invention provides a multi-sensor multi-target joint detection, tracking and classification method, which is characterized in that it includes the following steps: S1: given the initial value of the multi-target state, defining a new Bayesian risk; S2: in the Under the conditions of the category assumptions in the above category hypothesis set, predict the multi-target state to obtain the prior state distribution of multiple targets; S3: under the condition of the category decision set, calculate the multi-target posterior density at time k, and obtain the posterior Check the state distribution of multiple targets; S4: Calculate the multi-target detection loss, state estimation loss and classification loss under different decision-making conditions; S5: According to the detection loss, state estimation loss and classification loss, the multi-target Estimation and Classification Optimal Solutions of Objectives. The method is easy to implement and provides important technical support for multi-sensor network environment perception system.