Learning Whole-Image Descriptors for Real-time Loop Detection andKidnap Recovery under Large Viewpoint Difference

04/15/2019
by   Manohar Kuse, et al.
0

We present a real-time stereo visual-inertial-SLAM system which is able to recover from complicatedkidnap scenarios and failures online in realtime. We propose to learn the whole-image-descriptorin a weakly supervised manner based on NetVLAD and decoupled convolutions. We analyse thetraining difficulties in using standard loss formulations and propose an allpairloss and show itseffect through extensive experiments. Compared to standard NetVLAD, our network takes an orderof magnitude fewer computations and model parameters, as a result runs about three times faster.We evaluate the representation power of our descriptor on standard datasets with precision-recall.Unlike previous loop detection methods which have been evaluated only on fronto-parallel revisits,we evaluate the performace of our method with competing methods on scenarios involving largeviewpoint difference. Finally, we present the fully functional system with relative computation andhandling of multiple world co-ordinate system which is able to reduce odometry drift, recover fromcomplicated kidnap scenarios and random odometry failures. We open source our fully functional system as an add-on for the popular VINS-Fusion.

READ FULL TEXT
research
07/23/2020

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

This paper presents ORB-SLAM3, the first system able to perform visual, ...
research
08/26/2017

Robust Stereo Feature Descriptor for Visual Odometry

In this paper, we propose a simple way to utilize stereo camera data to ...
research
03/06/2018

PI-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines

In this paper, we present the PerceptIn Visual Inertial Odometry (PI-VIO...
research
03/14/2021

GVINS: Tightly Coupled GNSS-Visual-Inertial for Smooth and Consistent State Estimation

Visual-Inertial odometry is known to suffer from drifting especially ove...
research
10/20/2016

ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras

We present ORB-SLAM2 a complete SLAM system for monocular, stereo and RG...
research
04/01/2022

Bi-directional Loop Closure for Visual SLAM

A key functional block of visual navigation system for intelligent auton...

Please sign up or login with your details

Forgot password? Click here to reset