Please use this identifier to cite or link to this item:
Title: From local understanding to global regression in monocular visual odometry
Authors: Esfahani, Mahdi Abolfazli
Wu, Keyu
Yuan, Shenghai
Wang, Han
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Esfahani, M. A., Wu, K., Yuan, S. & Wang, H. (2020). From local understanding to global regression in monocular visual odometry. International Journal of Pattern Recognition and Artificial Intelligence, 34(1), 2055002-.
Journal: International Journal of Pattern Recognition and Artificial Intelligence
Abstract: The most significant part of any autonomous intelligent robot is the localization module that gives the robot knowledge about its position and orientation. This knowledge assists the robot to move to the location of its desired goal and complete its task. Visual Odometry (VO) measures the displacement of the robots' camera in consecutive frames which results in the estimation of the robot position and orientation. Deep Learning, nowadays, helps to learn rich and informative features for the problem of VO to estimate frame-by-frame camera movement. Recent Deep Learning-based VO methods train an end-by-end network to solve VO as a regression problem directly without visualizing and sensing the label of training data in the training procedure. In this paper, a new approach to train Convolutional Neural Networks (CNNs) for the regression problems, such as VO, is proposed. The proposed method first changes the problem to a classification problem to learn different subspaces with similar observations. After solving the classification problem, the problem converts to the original regression problem to solve using the knowledge achieved by solving the classification problem. This approach helps CNN to solve regression problem globally in a local domain learned in the classification step, and improves the performance of the regression module for approximately 10%.
ISSN: 0218-0014
DOI: 10.1142/S0218001420550022
Rights: © 2020 World Scientic Publishing Company. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Page view(s)

Updated on May 17, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.