Robust and Accurate Object Velocity Detection by Stereo Camera for Autonomous Driving

TL;DR

This paper presents a novel camera-based method for accurate object velocity detection in autonomous driving, utilizing HDR disparity fusion, monocular-stereo recognition fusion, and a new velocity calculation, validated on a large-scale Subaru dataset.

Contribution

It introduces a comprehensive approach combining HDR disparity fusion, recognition fusion, and a new velocity calculation method for improved accuracy.

Findings

High dynamic range disparity fusion improves robustness.

Fusion of monocular and stereo recognition enhances accuracy.

Validated on real vehicle with severe environment conditions.

Abstract

Although the number of camera-based sensors mounted on vehicles has recently increased dramatically, robust and accurate object velocity detection is difficult. Additionally, it is still common to use radar as a fusion system. We have developed a method to accurately detect the velocity of object using a camera, based on a large-scale dataset collected over 20 years by the automotive manufacturer, SUBARU. The proposed method consists of three methods: an High Dynamic Range (HDR) detection method that fuses multiple stereo disparity images, a fusion method that combines the results of monocular and stereo recognitions, and a new velocity calculation method. The evaluation was carried out using measurement devices and a test course that can quantitatively reproduce severe environment by mounting the developed stereo camera on an actual vehicle.