Automatic driving 3D modeling method, device and system

Abstract

The invention discloses an automatic driving 3D modeling method, device and system. The invention relates to the technical field of automatic driving, and solves the problems that data modeling is incomplete due to single data sampling, or the relevance between data is poor, and an accurate 3D environment model cannot be created. According to the invention, the method comprises the steps of: obtaining and fusing data collected by the multi-element sensor to form a composite view, extracting inter-frame target parameters of the same detection target in a plurality of adjacent frames acquired bydifferent sensors in the comprehensive view; comparing and analyzing data acquired by different sensors; adopting a stepped threshold method to eliminate singular values and redundancy of data in different sensors, achieving accurate judgment of target parameters, and when the inter-frame target parameters of the same detection target in a plurality of continuous adjacent frames are within a preset threshold, determining the inter-frame target parameters to be inter-frame correlation dynamic data so as to construct a 3D environment model. According to the method, more and more accurate associated dynamic data can be extracted, and the establishment of an accurate 3D environment model is facilitated.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a 3D modeling method, device and system for automatic driving. Background technique [0002] In the autonomous driving technology, the recognition of the target existing in the driving environment of the autonomous driving vehicle is one of the important core technologies of the autonomous driving. At present, the industry usually uses neural network machine learning technology to collect and analyze a large amount of actual road driving data, and extract the feature quantities of common targets on various road surfaces for machine recognition training. In the actual driving, the target matching analysis is carried out through the trained feature quantity, so as to identify the target. As the number of collected samples increases and the training period increases, the content of the feature library becomes more and more abundant, so more and more actual road ta...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a 3D modeling method, device and system for automatic driving to solve the problem of incomplete data modeling caused by single data sampling in the current automatic driving field, or even if multiple sampling is used, the correlation between data is poor, and an accurate 3D environment cannot be created model problem

Images