Recently, our work “Automated Camera-Exposure Control for Robust Localization in Varying Illumination Environments” has been accepted by the top robotics journal Autonomous Robots.
The vision-based localization of robots operating in complex environments is challenging due to the varying dynamic illumination. This study aims to develop a novel automated camera-exposure control algorithm for illumination robust localization. The main contributions of this paper are three-fold:
- First, a lightweight camera photometric calibration approach based on specific sampling is proposed to model optical imaging.
- Second, a novel automated exposure control algorithm, based on the coarse-to-fine optimization strategy, is proposed to respond to the illumination variation rapidly and adjust the camera exposure to capture the best-exposed images.
- Third, considering that exposure change breaks the brightness constancy assumption, which may lead to data association error, a full photometric compensation algorithm is proposed based on the photometric model to improve the robustness of data association.
Paper: Automated Camera-Exposure Control for Robust Localization in Varying Illumination Environments, Yu Wang, Haoyao Chen*, Shiwu Zhang, Wencan Lu, Autonomous Robots, 2022.