DOE-SLAM: Dynamic Object Enhanced Visual SLAM

Towards Visual SLAM in Dynamic Environments

To build autonomous robots capable of operating wherever humans do, we must develop local­ ization and mapping strategies that can handle changing environments. Recent work by Se, Lowe and Little has shown that current machine vision technology makes visual SLAM feasible in a potentially wide range of static environments. However, their system treats vision system errors in a manner which impos...

The case for visual-inertial SLAM over visual SLAM

Object-based Visual SLAM: How Object Identity Informs Geometry

Objects are rich information sources about the environment. A 3D model of the objects, together with their semantic labels, can be used for camera localization as well as for cognitive reasoning about the environment. However, traditional frameworks for scene reconstruction usually map a cloud of points using structure-from-motion techniques, but do not provide objects representation. On the ot...

Visual Trajectory Based SLAM

Dense visual SLAM

Visual SLAM systems aim to estimate the motion of a moving camera together with the geometric structure and appearance of the world being observed. To the extent that this is possible using only an image stream, the core problem that must be solved by any practical visual SLAM system is that of obtaining correspondence throughout the images captured. Modern visual SLAM pipelines commonly obtain...