Multi-sensor data fusion method and system

Abstract

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.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a multi-sensor data fusion method and system. Background technique [0002] In the prior art, multi-sensor data fusion methods generally include the following methods: first, by continuously expanding or shrinking the first object data interval of the first sensor within a certain threshold, to find the only object associated with the second sensor, Until a unique object is found or it is determined that there is no associated object; secondly, by installing corresponding sensing devices at different positions of the vehicle, obstacle detection is performed on the respective detection areas, and data fusion is achieved by adopting multiple sensor classification confirmation methods for overlapping areas; Third, by comparing the data type, data time and data content of the two sensor data elements, perform different actions according to the comparison results, including deleting, me...

AI Technical Summary

Problems solved by technology

The first solution cannot deal with the situation where a sensor detects multiple objects for the same larger target, and this situation often occurs in millimeter-wave radar sensors, and there are also problems such as difficulty in determining the sensor level and missed detection of targets.

The latter two schemes realize data fusion through logical judgment of different sensor data, and the effective utilization rate of collected redundant data is low.

Images