Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization

08/03/2019
by   Yafei Song, et al.
1

In recent years, camera-based localization has been widely used for robotic applications, and most proposed algorithms rely on local features extracted from recorded images. For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static. Therefore, the motion attribute of a local feature point could be exploited to improve localization performance, e.g., the feature points extracted from moving persons or vehicles can be excluded from these systems due to their unsteadiness. In this paper, we design a fully convolutional network (FCN), named MD-Net, to perform motion attribute estimation and feature description simultaneously. MD-Net has a shared backbone network to extract features from the input image and two network branches to complete each sub-task. With MD-Net, we can obtain the motion attribute while avoiding increasing much more computation. Experimental results demonstrate that the proposed method can learn distinct local feature descriptor along with motion attribute only using an FCN, by outperforming competing methods by a wide margin. We also show that the proposed algorithm can be integrated into a vision-based localization algorithm to improve estimation accuracy significantly.

READ FULL TEXT

page 1

page 3

page 6

page 7

research
06/08/2018

3D FCN Feature Driven Regression Forest-Based Pancreas Localization and Segmentation

This paper presents a fully automated atlas-based pancreas segmentation ...
research
09/06/2017

Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)

In this work, we propose a technique that utilizes a fully convolutional...
research
08/28/2018

Localization Guided Learning for Pedestrian Attribute Recognition

Pedestrian attribute recognition has attracted many attentions due to it...
research
11/15/2017

A Novel SDASS Descriptor for Fully Encoding the Information of 3D Local Surface

Local feature description is a fundamental yet challenging task in 3D co...
research
01/21/2018

Low-level Active Visual Navigation: Increasing robustness of vision-based localization using potential fields

This paper proposes a low-level visual navigation algorithm to improve v...
research
06/19/2019

PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning

While many visual ego-motion algorithm variants have been proposed in th...
research
06/09/2016

Feature-based Recursive Observer Design for Homography Estimation

This paper presents a new algorithm for online estimation of a sequence ...

Please sign up or login with your details

Forgot password? Click here to reset