[HTML][HTML] Towards explainable artificial intelligence in deep vision-based odometry
A Ghasemieh, R Kashef - Computers and Electrical Engineering, 2024 - Elsevier
Visual Odometry (VO) is a crucial process for estimating camera motion in real-time based
on visual information captured. The emergence of deep learning has significantly …
on visual information captured. The emergence of deep learning has significantly …
islam: Imperative slam
Simultaneous Localization and Mapping (SLAM) stands as one of the critical challenges in
robot navigation. A SLAM system often consists of a front-end component for motion …
robot navigation. A SLAM system often consists of a front-end component for motion …
Pseudo-lidar for visual odometry
Y Miao, H Deng, C Jiang, Z Feng, X Wu… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
As one of the important tasks in the field of robotics and machine vision, visual odometry
provides tremendous help for various applications such as navigation, location, and so on …
provides tremendous help for various applications such as navigation, location, and so on …
Unsupervised visual odometry and action integration for pointgoal navigation in indoor environment
PointGoal navigation in indoor environment is a fundamental task for personal robots to
navigate to a specified point. Recent studies solved this PointGoal navigation task with near …
navigate to a specified point. Recent studies solved this PointGoal navigation task with near …
Online indoor visual odometry with semantic assistance under implicit epipolar constraints
Among solutions to the tasks of indoor localization and reconstruction, compared with
traditional SLAM (Simultaneous Localization And Mapping), learning-based VO (Visual …
traditional SLAM (Simultaneous Localization And Mapping), learning-based VO (Visual …
Vector-Symbolic Architecture for Event-Based Optical Flow
From a perspective of feature matching, optical flow estimation for event cameras involves
identifying event correspondences by comparing feature similarity across accompanying …
identifying event correspondences by comparing feature similarity across accompanying …
DE-RGBD SLAM: enhancing static feature point selection in RGB-D visual SLAM using depth information
M Wu, Q Zheng, W Ma, P Zhu… - … Science and Technology, 2024 - iopscience.iop.org
Feature point extraction plays a key role in visual simultaneous localization and mapping
(SLAM) systems. And it remains a major challenge to accurately select static feature points …
(SLAM) systems. And it remains a major challenge to accurately select static feature points …
Enhancing Conventional Geometry-Based Visual Odometry Pipeline Through Integration of Deep Descriptors
Geometry-based Visual Odometry (VO) techniques are renowned in the fields of computer
vision and robotics. They use methods from multi-view geometry to estimate camera motion …
vision and robotics. They use methods from multi-view geometry to estimate camera motion …
Unsupervised monocular depth learning using self-teaching and contrast-enhanced SSIM loss
C Feng, Y Wang, Y Lai, Q Liu… - Journal of Electronic …, 2024 - spiedigitallibrary.org
In recent years, unsupervised learning has gained significant attention as a promising
approach for monocular depth estimation. We propose an unsupervised monocular depth …
approach for monocular depth estimation. We propose an unsupervised monocular depth …
Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
Unsupervised monocular depth learning generally relies on the photometric relation among
temporally adjacent images. Most of previous works use both mean absolute error (MAE) …
temporally adjacent images. Most of previous works use both mean absolute error (MAE) …