A multi-sensor data fusion method and system, the method comprising: normalizing the detection data of M cycles adjacent to each sensor and the current moment, obtaining M groups of object data of objects sensed by each sensor, and calculating Add a time stamp to the data; based on the time stamp, associate the object data of one of the sensors with the object data of all other sensors, and record the association result data; for the object data that is successfully associated in the association result data, according to the object data in the same sensor For the association relationship of different time stamps, use the object data corresponding to the latest time stamp corresponding to the sensing object corresponding to the object data to update the object data; integrate the object data of different sensors to supplement and calculate the updated data. Based on the association of time marks, the method realizes the data correspondence of different sensors to the same target, effectively utilizes the spatiotemporal characteristics of the sensing target, and increases the accuracy of the association.