Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
This work provides a method to improve the robustness of visual odometry and SLAM systems for robots and autonomous vehicles by ensuring consistent image quality in dynamic lighting environments.
This paper addresses the challenge of maintaining image quality for visual navigation systems under varying lighting conditions. The authors developed a self-supervised deep convolutional neural network that predicts and adjusts camera gain and exposure to maximize matchable features between consecutive images, demonstrating a substantially higher number of inlier feature matches compared to other methods during dramatic lighting changes.
Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use in visual odometry (VO) or visual simultaneous localization and mapping (SLAM). We train a deep convolutional neural network model to predictively adjust camera gain and exposure time parameters such that consecutive images contain a maximal number of matchable features. The training process is fully self-supervised: our training signal is derived from an underlying VO or SLAM pipeline and, as a result, the model is optimized to perform well with that specific pipeline. We demonstrate through extensive real-world experiments that our network can anticipate and compensate for dramatic lighting changes (e.g., transitions into and out of road tunnels), maintaining a substantially higher number of inlier feature matches than competing camera parameter control algorithms.