ORB-SLAM: A Versatile and Accurate Monocular SLAM System

Abstract

This paper presents ORB-SLAM, a feature-based monocular SLAM system that operates in real time, in small and large, indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

Modified Indoor Navigation Mapping based on VSLAM

“…We define 11 EF 、 as the last occupied state, 22 EF 、 as the current occupied state. If the robot detects the same grid at next time, the occupied state of the grid is updated based on Bayesian formula:…”

“…The computer's configuration is Intel I7 CPU running at 2.5GHz, no GPU acceleration, and the system is Ubuntu14.04. Based on VSLAM [11], we generate 3D map. The result of 3D map building is shown in Fig.7.…”

Superimposing Thermal-Infrared Data on 3D Structure Reconstructed by RGB Visual Odometry

“…Since our goal is to generate a large thermal map with real-time performance, possibly on outdoor scenes, the best candidates are direct sparse odometry (DSO) [25], large-scale direct monocular simultaneous localization and mapping (LSD-SLAM) [26] and ORB-SLAM [27]. In these three 3D reconstruction systems, DSO and ORB-SLAM are more accurate [25] direct sparse small large LSD-SLAM [26] direct semi-dense small large PTAM [24] feature sparse small small ORB-SLAM [27] feature sparse small large SfM [11] feature sparse large large KinectFusion [5] RGB-D dense small small Lidar 3D scanner dense -large than LSD-SLAM [25], [27]. Moreover, the 3D structures generated from DSO have a better density than those generated from ORB-SLAM.…”

A brain-inspired SLAM system based on ORB features

“…ORB uses FAST algorithm to detect key points in images, filters the key features using Harris corner measure [36] and computes binary descriptors using oriented BRIEF. ORB can provide good performance with low cost computation, it is suitable to construct a semi-dense map in real-time [37] .…”

“…Experimental results showed that for the same number of features, the processing time of ORB is faster than speeded up robust features (SURF) by an order of magnitude and over two orders faster than SIFT. ORB was used to achieve the good performance for place recognition [37,38] . Comparing with the other feature descriptions such as SIFT, SURF and FAST, major advantages of ORB include: 1) It provides a fast calculation and matching algorithm.…”