Data fusion method and device for vehicle sensors

Abstract

Embodiments of the invention provide a data fusion method and device for vehicle sensors, and belong to the field of data fusion. The method comprises the steps of reading a parameter attribute set ofeach target detected by each sensor disposed on the vehicle, wherein the parameter attribute set at least comprises one or more of a longitudinal speed, a longitudinal distance and a transverse distance; generating an attribute combination according to the read parameter attribute set of each target detected by each sensor; and determining the overlapping degree of the parameter attribute sets inthe attribute combinations, and performing data fusion on the basis of the overlapping degree to obtain a first data fusion list, wherein the first data fusion list comprises the overlapping degree of the attribute combinations and the parameter attribute sets corresponding to the overlapping degree of the attribute combinations. According to the data fusion method and device, the judgment logicof a subsequent decision-making system is simplified, and the security and the operation efficiency of the whole system are improved.

Description

technical field [0001] The present invention relates to the field of data fusion, in particular to a data fusion method and device for vehicle sensors. Background technique [0002] Due to the performance defects of a single sensor itself, object detection for obstacles cannot be achieved in some cases, for example, the camera cannot detect objects under poor lighting conditions. Therefore, self-driving cars need a variety of sensors to detect targets in order to achieve a comprehensive perception of the surrounding environment. [0003] If the target data detected by multiple sensors is directly output, the amount of data transmission will be huge, and there will be the following problems: target false detection, such as outputting obstacles without obstacles; target missing detection, such as obstacles but no output ; The attributes of the same target are inconsistent; the optimal attributes of the target cannot be obtained, etc. These problems will bring great inconveni...

AI Technical Summary

Problems solved by technology

[0003] If the target data detected by multiple sensors is directly output, the amount of data transmission will be huge, and there will be the following problems: target false detection, such as outputting obstacles without obstacles; target missing detection, such as obstacles but no output ;The attributes of the same target are inconsistent; the optimal attributes of the target cannot be obtained, etc.

These problems will bring great inconvenience to the judgment logic of the subsequent decision-making system and reduce the safety and operating efficiency of the entire system.

Images