Vehicular radar data processing algorithm verification system

Abstract

The invention provides a vehicular radar data processing algorithm verification system which comprises a radar sensor, a camera shooting device, a car body information acquisition device, a main-control computer and a display device. The main-control computer comprises a frame synchronizer, a data storage module, a data playback module, a data processing algorithm module and a data display module, the frame synchronizer acquires original intermediate-frequency echo data, target tracking data, video data and car body data and synchronously stores the acquired data into the data storage module; the data playback module synchronously reads the stored data and transmits the read data to the data processing algorithm module and the data display module; the data processing algorithm module verifies a radar data processing algorithm in non-real time after synchronous data are received and outputs verification results and intermediate process data of the algorithm to the data display module. According to the verification system, the radar data processing algorithm can be repeatedly verified in non-real time in a laboratory by the aid of data acquired on an external field.

Description

technical field [0001] The invention relates to the field of radar sensor testing of intelligent driving vehicles, in particular to a vehicle radar data processing algorithm verification system. Background technique [0002] Advanced Driver Assistant System (ADAS) can greatly reduce traffic accidents, casualties and economic losses, and the market has grown rapidly in recent years. The current mainstream advanced driver assistance technologies include BSD (Blind Spot Detection, Blind Spot Detection), LCA (Lane ChangeAssist, Line Assist) and FCW (Front Collision Warning, Front Collision Warning). As one of the key components of these technologies, the vehicle-mounted radar sensor often needs to conduct multiple field road tests in the development stage to realize the performance assessment and verification of the radar data processing algorithm. However, field tests are not only expensive, but also limited by weather conditions, and test data are very valuable. How to reuse...

AI Technical Summary

Problems solved by technology

However, the existing methods cannot display the intermediate process data when the algorithm is running, such as FFT (Fast Fourier Transform) data, DOA (Data Oriented Architecture, Data Oriented Architecture) angle data and I / Q (In-phase / Quadrature , in-phase quadrature) angle quadrature information, inconvenient to find the problem

At the same time, during data storage, the existing method of using timers for data synchronization is not efficient, which reduces the degree of correlation between various data, and cannot accurately correspond to a single data frame during data playback.

In addition, the existing methods can only verify the algorithm integrated by the radar itself, so it is impossible to repeatedly verify the performance of the radar algorithm in the laboratory in non-real time

Images