ISETAuto: Detecting vehicles with depth and radiance information

TL;DR

This paper compares vehicle detection performance using depth and radiance sensors in autonomous driving, showing that combining both improves accuracy by leveraging their complementary strengths.

Contribution

It demonstrates that a hybrid approach using both depth and radiance data enhances vehicle detection accuracy over single-sensor methods in complex driving scenes.

Findings

Depth-based detection outperforms radiance at typical resolutions.

Radiance outperforms depth at lower resolutions.

Combining both data types yields higher accuracy than either alone.

Abstract

Autonomous driving applications use two types of sensor systems to identify vehicles - depth sensing LiDAR and radiance sensing cameras. We compare the performance (average precision) of a ResNet for vehicle detection in complex, daytime, driving scenes when the input is a depth map (D = d(x,y)), a radiance image (L = r(x,y)), or both [D,L]. (1) When the spatial sampling resolution of the depth map and radiance image are equal to typical camera resolutions, a ResNet detects vehicles at higher average precision from depth than radiance. (2) As the spatial sampling of the depth map declines to the range of current LiDAR devices, the ResNet average precision is higher for radiance than depth. (3) For a hybrid system that combines a depth map and radiance image, the average precision is higher than using depth or radiance alone. We established these observations in simulation and then confirmed them using realworld data. The advantage of combining depth and radiance can be explained by noting that the two type of information have complementary weaknesses. The radiance data are limited by dynamic range and motion blur. The LiDAR data have relatively low spatial resolution. The ResNet combines the two data sources effectively to improve overall vehicle detection.