Stereo Relative Pose from Line and Point Feature Triplets (2018-09-08T00:00:00.000000Z)

TL;DR

This work presents two minimal solvers for the stereo relative pose problem, specifically the case when a minimal set consists of three point or line features and each of them has three known projections on two stereo cameras.

Abstract

Stereo relative pose problem lies at the core of stereo visual odometry systems that are used in many applications. In this work we present two minimal solvers for the stereo relative pose. We specifically consider the case when a minimal set consists of three point or line features and each of them has three known projections on two stereo cameras. We validate the importance of this formulation for practical purposes in our experiments with motion estimation. We then present a complete classification of minimal cases with three point or line correspondences each having three projections, and present two new solvers that can handle all such cases. We demonstrate a considerable effect from the integration of the new solvers into a visual SLAM system.

Authors

V. Lempitsky

14 papers

Yinqiang Zheng

5 papers

Alexander Vakhitov

2 papers

TL;DR

Abstract

Authors

References31 items

Pose Estimation from Line Correspondences: A Complete Analysis and a Series of Solutions

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

Accurate and Linear Time Pose Estimation from Points and Lines

Efficient Intersection of Three Quadrics and Applications in Computer Vision

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age

An Efficient Minimal Solution for Multi-camera Motion

Object scene flow for autonomous vehicles

Direct Solution to the Minimal Generalized Pose

Structure from Motion with Line Segments Under Relaxed Endpoint Constraints

A simple solution for the non perspective three point pose problem

Efficient Computation of Relative Pose for Multi-camera Systems

An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency

Are we ready for autonomous driving? The KITTI vision benchmark suite

Egomotion Estimation Using Assorted Features

A geometric solver for calibrated stereo egomotion

ORB: An efficient alternative to SIFT or SURF

EDLines: A real-time line segment detector with a false detection control

A new minimal solution to the relative pose of a calibrated stereo camera with small field of view overlap

Moving in stereo: Efficient structure and motion using lines

Building Rome in a day

A generic structure-from-motion framework

A Minimal Solution to the Generalised 3-Point Pose Problem

An efficient solution to the five-point relative pose problem

Complete Solution Classification for the Perspective-Three-Point Problem

Complete solution classification for the perspective-three-point problem

Maple V Library Reference Manual

Using Algebraic Geometry

Solutions to Minimal Generalized Relative Pose Problems

Visual odometry

Multiple View Geometry in Computer Vision

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Field of Study

Venue Information

Name

Type

URL

Alternate Names