Monocular vision SLAM for indoor aerial vehicles

  title={Monocular vision SLAM for indoor aerial vehicles},
  author={Koray Çelik and Arun Kumar Somani},
  journal={2009 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  • K. Çelik, Arun Kumar Somani
  • Published 15 December 2009
  • Engineering
  • 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
This paper presents a novel indoor navigation and ranging strategy by using a monocular camera. The proposed algorithms are integrated with simultaneous localization and mapping (SLAM) with a focus on indoor aerial vehicle applications. We experimentally validate the proposed algorithms by using a fully self-contained micro aerial vehicle (MAV) with on-board image processing and SLAM capabilities. The range measurement strategy is inspired by the key adaptive mechanisms for depth perception and… 

Indoor navigation for aerial vehicle using monocular visual SLAM

Improvements are demonstrated on implementing a fast monocular visual slam system (MonoSLAM) to navigate indoor aerial vehicle by designing for the framework of the navigation system, redesigning of landmark patch matching method and giving new rules updating the image patch to overcome some particularly bad situation when landmarks are insufficient.

Monocular Vision based Navigation in GPS-Denied Riverine Environments

This paper presents a new method to estimate the range and bearing of landmarks and solve the simultaneous localization and mapping (SLAM) problem. The proposed ranging and SLAM algorithms have

Monocular visual SLAM for small UAVs in GPS-denied environments

This paper presents a monocular visual simultaneous localization and mapping system for a small unmanned aerial vehicle (UAV) in GPS-denied environments that estimates the positions of the UAV and the features by an extended Kalman filter (EKF).

Monocular Vision Based Navigation and Localisation in Indoor Environments

Abstract This paper describes a set of tools and algorithms to enable vision based navigation for a Micro Aerial Vehicle (MAV) flying in an indoor environment. An optical flow balancing strategy is

Vision-based SLAM system for MAVs in GPS-denied environments

This work proposes a novel monocular simultaneous localization and mapping system with application to MAVs based on the theoretical findings obtained from an observability analysis, and experimental results show that the proposed method is capable of providing good results with low-cost hardware.

Vision Only Autonomous Indoor Exploration Method for Unmanned Aerial Vehicles (UAVs)

Through exploiting the straight architectural lines of corridors and doors, a method was introduced for gathering useful landmarks to estimate UAVs’ three degrees of freedom (DoF) attitudes as well as the horizontal displacement from the wall in a corridor environment.

Monocular Visual SLAM Based on a Cooperative UAV–Target System

This work presents a monocular-based SLAM approach for cooperative UAV–Target systems that addresses the state estimation problem of the UAV position and velocity, and a novel technique to estimate the approximate depth of the new visual landmarks is proposed, which takes advantage of the cooperative target.

Autonomous MAV flight in indoor environments using single image perspective cues

This work considers the problem of autonomously flying Miniature Aerial Vehicles in indoor environments such as home and office buildings, and uses vision algorithms based on perspective cues to estimate the desired direction to fly.

Integrated indoor navigation system for aerial vehicle using visual odometry and artificial landmark matching

The feasibility of combination of navigation from optical flow and artificial landmarks which will complement mutually is explored, and the integrated navigation system is experimented on the aerial vehicle exploring the laboratory, comparing with the optical flow method and landmarks method separately.

Monocular SLAM System for MAVs Aided with Altitude and Range Measurements: a GPS-free Approach

In this work, a monocular SLAM system for MAVs is presented and a novel technique for inferring the approximate depth of visual features from an ultrasonic range-finder is developed, which is able to work with low-cost sensors.



MVCSLAM: Mono-Vision Corner SLAM for Autonomous Micro-Helicopters in GPS Denied Environments

A real-time vision navigation and ranging method (VINAR) for the purpose of Simultaneous Localization and Mapping (SLAM) using monocular vision and makes use of the corners by exploiting the architectural features of the manmade indoors.

Biologically Inspired Monocular Vision Based Navigation and Mapping in GPS-Denied Environments

This paper introduces a method for gathering useful landmarks from a monocular camera for SLAM use, with absolute range information without using active ranging sensors, and incorporates the key functions of developed visual cortex in several advanced species, including humans, for depth perception and pattern recognition.

Mono-vision corner SLAM for indoor navigation

We present a real-time monocular vision based range measurement method for Simultaneous Localization and Mapping (SLAM) for an Autonomous Micro Aerial Vehicle (MAV) with significantly constrained

A Minimalistic Approach to Appearance-Based Visual SLAM

This paper presents a vision-based approach to simultaneous localization and mapping (SLAM) in indoor/outdoor environments with minimalistic sensing and computational requirements. The approach is

MonoSLAM: Real-Time Single Camera SLAM

The first successful application of the SLAM methodology from mobile robotics to the "pure vision" domain of a single uncontrolled camera, achieving real time but drift-free performance inaccessible to structure from motion approaches is presented.

Mapping Large Loops with a Single Hand-Held Camera

This paper presents a method for Simultaneous Localization and Mapping (SLAM) relying on a monocular camera as the only sensor which is able to build outdoor, closedloop maps much larger than

Large-Scale 6-DOF SLAM With Stereo-in-Hand

A system that can carry out simultaneous localization and mapping (SLAM) in large indoor and outdoor environments using a stereo pair moving with 6 DOF as the only sensor, which accommodates both monocular and stereo.

Vision-based localization algorithm based on landmark matching, triangulation, reconstruction, and comparison

This paper presents the landmark matching, triangulation, reconstruction, and comparison (LTRQ global localization algorithm), which is reasonably immune to ambiguous landmark matches, and is also robust against inaccurate map data.

High speed obstacle avoidance using monocular vision and reinforcement learning

An approach in which supervised learning is first used to estimate depths from single monocular images, which is able to learn monocular vision cues that accurately estimate the relative depths of obstacles in a scene is presented.

An Efficient Direct Approach to Visual SLAM

This paper proposes a new approach for simultaneously obtaining the correspondences, the camera pose, the scene structure, and the illumination changes, all directly using image intensities as observations, and formulate the visual SLAM problem as a nonlinear image alignment task.