Generic Camera Attribute Control using Bayesian Optimization

TL;DR

This paper introduces an active camera attribute control method using Bayesian optimization, which jointly manages gain and exposure time, and employs image synthesis to accelerate the process, validated in dynamic lighting conditions.

Contribution

It presents a novel joint control scheme for gain and exposure time with image synthesis to speed up Bayesian optimization in camera parameter tuning.

Findings

Improved control performance in rapidly changing light conditions

Reduced image acquisition time during optimization

Validated in indoor and outdoor environments

Abstract

Cameras are the most widely exploited sensor in both robotics and computer vision communities. Despite their popularity, two dominant attributes (i.e., gain and exposure time) have been determined empirically and images are captured in very passive manner. In this paper, we present an active and generic camera attribute control scheme using Bayesian optimization. We extend from our previous work [1] in two aspects. First, we propose a method that jointly controls camera gain and exposure time. Secondly, to speed up the Bayesian optimization process, we introduce image synthesis using the camera response function (CRF). These synthesized images allowed us to diminish the image acquisition time during the Bayesian optimization phase, substantially improving overall control performance. The proposed method is validated both in an indoor and an outdoor environment where light condition rapidly changes. Supplementary material is available at https://youtu.be/XTYR_Mih3OU .