Method and device for realizing multi-sensor target information fusion and multi-sensor sensing synchronization, computer device and recording medium

Abstract

The invention relates to a method and a device for realizing multi-sensor target information fusion and multi-sensor sensing synchronization, a computer device and a recording medium. The method for realizing multi-sensor target information fusion and multi-sensor sensing synchronization comprises the following steps of acquiring the actual measurement result of each sensor with respect to a target state and recording moments at which each set of actual measurement results is obtained, and recording a first time stamp for each set of actual measurement results; recording the moment at which target information fusion processing is started to execute as a second time stamp; calculating a time difference between each first moment represented by each first time stamp and a second moment represented by the second time stamp respectively; updating the corresponding actual measurement result obtained at the first moment based on each calculated time difference to obtain a corresponding estimated measurement result at the second moment; acquiring the fusion prediction results of all sensors with respect to the target state at the second moment; and for each set of estimated measurement results, acquiring the optimal estimation result of the corresponding sensor with respect to the target state at the second moment based on the fusion prediction results and the set of estimated measurement results.

Description

technical field [0001] The present invention relates to the vehicle field, and more particularly relates to a method and device, a computer device, and a recording medium for synchronizing multi-sensor target information fusion and multi-sensor sensing. Background technique [0002] In the field of automobiles, the world is striving towards the development direction of "smart driving". "Intelligent driving" can be divided into assisted driving, conditional unmanned automatic driving and fully automatic driving according to different functions. The results of object-aware sensors are fused to reduce overlapping objects and compensate for the shortcomings of different sensor results. [0003] However, in actual processing, due to the differences in algorithms of various sensor suppliers, the strength of sensor hardware performance, etc., the update speed of the sensor on the target will be affected to varying degrees, and the update speed of different sensors is not always th...

AI Technical Summary

Problems solved by technology

[0005] However, when the sensor's recognition results about the target are updated slowly or not updated, it will lead to the problem that the optimal estimation of the fusion result is not accurate enough

Images