Fast visual inertial odometry with point–line features using adaptive EDLines algorithm

Abstract

In mainstream visual inertial odometry systems, the method of positional solution by feature point extraction and matching in the image is widely used. But the tracking accuracy of point features is dependent on texture richness in the environment. Although many existing algorithms introduce line features in the front-end to improve the system's environmental adaptability, most of them sacrifice system real-time in exchange for higher positioning accuracy. The extraction and matching of line features often require more time, thus failing to meet the real-time requirements of the system for localization. In this paper, therefore, we propose a fast visual inertial odometry fused with point and line features, which enables the system to maintain a high level of positioning robustness in dim and changing light environments with low time cost. The point-line features visual inertial odometry algorithm is based on adaptive thresholding of EDLines. By adding an adaptive thresholding component to the EDLines algorithm, the robustness of line feature extraction is enhanced to better adapt to changes in ambient lighting. And the time for line feature extraction is significantly reduced. And a line feature matching algorithm based on geometric information and structural similarity is proposed, which enables fast and accurate line features matching. The algorithm is compared with PL-VIO and VINS-MONO algorithms on the EuRoc dataset and real world secens. Many experiments prove that the algorithm has improved in both real-time and accuracy.

Tightly coupled visual-inertial fusion with image enhancement for robust positioning

“…However, VIO faces limitations when it utilizes visible light cameras as visual input, as external light sources, ambient lighting, material occlusion, and other factors impair its performance. In dark or low-light environments, visible light cameras cannot capture clear images, which makes it difficult to extract effective feature points and causes loss or discontinuity of visual trajectories [4,5]. Moreover, substances such as smoke, dust, water vapor, blur the images captured by visible light cameras, interfere with the transmission of visual information, and affect the stability and accuracy of the VIO system.…”

A PTV-based feature-point matching algorithm for binocular stereo photogrammetry

“…In general, there are two classes of feature-matching algorithms, depending on the different primitives to be matched. One is to match the object texture (or coherent optical pattern) that is both discernible by the optical system and quasi-invariant to the viewing perspectives [11,12], while the other is to match feature points by optical geometry constraint (or spatial relationship) being imposed by the optical system [13][14][15]. Actually, the boundary between these two classes is vague.…”