Vehicle front barrier contour detection method based on recursive superposition algorithm

Abstract

The invention discloses a vehicle front barrier contour detection method based on a recursive superposition algorithm. The method comprises steps that barrier contour height is calculated according tothe radar and ground geometric relationship; coordinate matching of historical scanning data and present scanning data is carried out; normal distribution characteristics of radar light beams are considered and are introduced to a probability density function; quasi-continuous estimation of the barrier contour is realized; the accurate barrier contour height can be solved in a continuous recursive superposition mode according to the historical scanning data and the present scanning data; regression calculation of height deviation and pitch angle deviation is carried out; fusion of historicalscanning and present scanning is carried out. The method is advantaged in that the employed measurement method is simple and feasible, the approximate contour height of a barrier in front of the roadcan be accurately and efficiently detected, recursive superposition of overlapped areas generated by historical and present scanning is continuously carried out, influence caused by certain interference can be eliminated, information density is greatly enhanced, and the vehicle front barrier contour height can be accurately acquired.

Description

technical field [0001] The invention belongs to the field of automobile intelligent driving and radar technology, and relates to a method for identifying targets by radar, in particular to a method for detecting the contours of obstacles in front of a vehicle based on a recursive superposition algorithm, which is used to solve the problem that existing radars cannot quickly and accurately identify road obstacles Contour problem. Background technique [0002] LiDAR is a commonly used ranging sensor. It is widely used in various fields due to its advantages of high resolution and low interference from environmental factors. Lidar is divided into three types: single-line lidar, multi-line lidar and area array radar. Single-line lidar generates one scan line per scan. It has fast ranging speed, less data volume, small size, light weight, and is suitable for fast processing. Because of its high cost performance, single-line lidar is currently the most widely used. [0003] LiDA...

AI Technical Summary

Problems solved by technology

This method has a high recognition rate, but the effective execution of the algorithm must rely on the neural network training of a large number of image model libraries. Once the obstacle information is missing in the model library, it will greatly affect the recognition results.

Images