Search Results for author: Larry Matthies

Found 9 papers, 2 papers with code

ShadowNav: Crater-Based Localization for Nighttime and Permanently Shadowed Region Lunar Navigation

no code implementations11 Jan 2023 Abhishek Cauligi, R. Michael Swan, Hiro Ono, Shreyansh Daftry, John Elliott, Larry Matthies, Deegan Atha

This GITL operation limits the distance that can be driven in a day to a few hundred meters, which is the distance that the rover can maintain acceptable localization error via relative methods.

Autonomous Driving Edge Detection

Lunar Rover Localization Using Craters as Landmarks

no code implementations18 Mar 2022 Larry Matthies, Shreyansh Daftry, Scott Tepsuporn, Yang Cheng, Deegan Atha, R. Michael Swan, Sanjna Ravichandar, Masahiro Ono

At the end of each drive, a ground-in-the-loop (GITL) interaction is used to get a position update from human operators in a more global reference frame, by matching images or local maps from onboard the rover to orbital reconnaissance images or maps of a large region around the rover's current position.

Position Visual Odometry

Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras

1 code implementation7 Dec 2020 Manash Pratim Das, Larry Matthies, Shreyansh Daftry

Thermal infrared cameras are increasingly being used in various applications such as robot vision, industrial inspection and medical imaging, thanks to their improved resolution and portability.

Camera Auto-Calibration Thermal Image Denoising +2

Online Self-supervised Scene Segmentation for Micro Aerial Vehicles

no code implementations13 Jun 2018 Shreyansh Daftry, Yashasvi Agrawal, Larry Matthies

Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles (MAVs).

Scene Segmentation Scene Understanding

Early Recognition of Human Activities from First-Person Videos Using Onset Representations

no code implementations20 Jun 2014 M. S. Ryoo, Thomas J. Fuchs, Lu Xia, J. K. Aggarwal, Larry Matthies

In this paper, we propose a methodology for early recognition of human activities from videos taken with a first-person viewpoint.

Activity Prediction Person Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.