RoboticsLab-URJC, Universidad Rey Juan Carlos, Fuenlabrada, 28943 Madrid, Spain.
Sensors (Basel). 2019 Jan 14;19(2):302. doi: 10.3390/s19020302.
Visual Simultaneous Localization and Mapping (SLAM) approaches have achieved a major breakthrough in recent years. This paper presents a new monocular visual odometry algorithm able to localize in 3D a robot or a camera inside an unknown environment in real time, even on slow processors such as those used in unmanned aerial vehicles (UAVs) or cell phones. The so-called semi-direct visual localization (SDVL) approach is focused on localization accuracy and uses semi-direct methods to increase feature-matching efficiency. It uses inverse-depth 3D point parameterization. The tracking thread includes a motion model, direct image alignment, and optimized feature matching. Additionally, an outlier rejection mechanism (ORM) has been implemented to rule out misplaced features, improving accuracy especially in partially dynamic environments. A relocalization module is also included but keeping the real-time operation. The mapping thread performs an automatic map initialization with homography, a sampled integration of new points and a selective map optimization. The proposed algorithm was experimentally tested with international datasets and compared to state-of-the-art algorithms.
近年来，视觉同时定位与地图构建（SLAM）方法取得了重大突破。本文提出了一种新的单目视觉里程计算法，能够实时在未知环境中对机器人或相机进行 3D 定位，即使在处理器速度较慢的情况下也能实现，例如在无人机（UAV）或手机中。所提出的半直接视觉定位（SDVL）方法侧重于定位精度，并使用半直接方法来提高特征匹配效率。它使用逆深度 3D 点参数化。跟踪线程包括运动模型、直接图像对准和优化的特征匹配。此外，还实现了异常值拒绝机制（ORM），以排除错位特征，从而提高了特别是在部分动态环境中的准确性。还包括重定位模块，但保持实时操作。映射线程通过单应性、新点的抽样积分和选择性地图优化执行自动地图初始化。所提出的算法在国际数据集上进行了实验测试，并与最先进的算法进行了比较。
