Abstract
With the rise of augmented reality and autonomous driving, visual SLAM (simultaneous localization and mapping) has become the focus of research again. Visual odometry is an important part of visual SLAM. Too dark or too strong light will reduce the image quality, resulting in a large deviation in the visual odometry trajectory. Therefore, this paper proposes a visual odometry with image enhancement. Identify the lighting state of the image by estimating the brightness value of the input image. Gamma correction based on truncated cumulative distribution function modulation is used to enhance images that are too dark. For too strong images, negative image strategy is used. An improved algorithm can boost the detailed texture of the image in a poor lighting environment accurately, thereby improving the accuracy of feature point matching and the precision of the pose estimation. Tests on the public EuRoC dataset demonstrate that the presented algorithm has better localization precision and robustness.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have