How to deal with glare for improved perception of Autonomous Vehicles
Muhammad Z. Alam, Zeeshan Kaleem, Sousso Kelouwani
TL;DR
The paper addresses glare as a critical hindrance to vision-based autonomous vehicle perception across OD, OR, OT, LD, and DE tasks. It introduces a joint glare spread function (GSF) framework and saturated-pixel aware deconvolution that recover true radiance in saturated regions; glare is modeled in the linear domain as $l_s(x,y) = l_{in}(x,y) \circledast g(x,y)$ and deconvolved with a learned $GSF$. Offline calibration estimates a parametric radially symmetric GSF $g(r) = p_1 \delta(r) + p_2 \exp(-p_3 r^{p_4})$, optimized via a logged-error objective with $\lambda$-regularization. Experiments on a tunnel dataset and a real AV dataset show the method outperforms baselines on OD, OR, and LD, with average improvements around 8.11%, and gamma-encoded processing providing notable gains.
Abstract
Vision sensors are versatile and can capture a wide range of visual cues, such as color, texture, shape, and depth. This versatility, along with the relatively inexpensive availability of machine vision cameras, played an important role in adopting vision-based environment perception systems in autonomous vehicles (AVs). However, vision-based perception systems can be easily affected by glare in the presence of a bright source of light, such as the sun or the headlights of the oncoming vehicle at night or simply by light reflecting off snow or ice-covered surfaces; scenarios encountered frequently during driving. In this paper, we investigate various glare reduction techniques, including the proposed saturated pixel-aware glare reduction technique for improved performance of the computer vision (CV) tasks employed by the perception layer of AVs. We evaluate these glare reduction methods based on various performance metrics of the CV algorithms used by the perception layer. Specifically, we considered object detection, object recognition, object tracking, depth estimation, and lane detection which are crucial for autonomous driving. The experimental findings validate the efficacy of the proposed glare reduction approach, showcasing enhanced performance across diverse perception tasks and remarkable resilience against varying levels of glare.