Visual SLAM algorithms: a survey from 2010 to 2016

Simultaneous Localization and Mapping (SLAM) is a technique for obtaining the 3D structure of an unknown environment and sensor motion in the environment. This technique was originally proposed to achieve autonomous control of robots in robotics [1]. Then, SLAM-based applications have widely become broadened such as computer vision-based online 3D modeling, augmented reality (AR)-based visualization, and self-driving cars. In early SLAM algorithms, many different types of sensors were integrated such as laser range sensors, rotary encoders, inertial sensors, GPS, and cameras. Such algorithms are well summarized in the following papers [2, 3, 4, 5].