A deep learning approach to state estimation from videos

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.

Bibliographic Details
Main Author: Doshi, Chandani
Other Authors: Rebecca L. Russell and Leslie P. Kaelbling.
Format: Thesis
Language:eng
Published: Massachusetts Institute of Technology 2018
Subjects:
Online Access:http://hdl.handle.net/1721.1/119761
_version_ 1826196953893961728
author Doshi, Chandani
author2 Rebecca L. Russell and Leslie P. Kaelbling.
author_facet Rebecca L. Russell and Leslie P. Kaelbling.
Doshi, Chandani
author_sort Doshi, Chandani
collection MIT
description Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.
first_indexed 2024-09-23T10:40:12Z
format Thesis
id mit-1721.1/119761
institution Massachusetts Institute of Technology
language eng
last_indexed 2024-09-23T10:40:12Z
publishDate 2018
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/1197612019-04-12T22:52:27Z A deep learning approach to state estimation from videos Doshi, Chandani Rebecca L. Russell and Leslie P. Kaelbling. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 45-47). Kalman lters have been commonly used for estimating the state of a vehicle from a video. Multi-State Constraint Kalman Filter (MSCKF) is an EKF-based state estimator that uses feature measurements for pose estimation of a vehicle. These models require a lot of hands-on engineering time to dene the measurement functions. We propose a data-driven approach by training deep neural networks on high-dimensional navigation image data generated from a simulation. We describe a CNN model that robustly learns reliable features from the input and gives promising results to model temporal data. We show that a deep learning approach can be a replacement for the MSCKF model for estimating the velocity of a moving vehicle. by Chandani Doshi. M. Eng. 2018-12-18T19:48:55Z 2018-12-18T19:48:55Z 2018 2018 Thesis http://hdl.handle.net/1721.1/119761 1078782966 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 47 pages application/pdf Massachusetts Institute of Technology
spellingShingle Electrical Engineering and Computer Science.
Doshi, Chandani
A deep learning approach to state estimation from videos
title A deep learning approach to state estimation from videos
title_full A deep learning approach to state estimation from videos
title_fullStr A deep learning approach to state estimation from videos
title_full_unstemmed A deep learning approach to state estimation from videos
title_short A deep learning approach to state estimation from videos
title_sort deep learning approach to state estimation from videos
topic Electrical Engineering and Computer Science.
url http://hdl.handle.net/1721.1/119761
work_keys_str_mv AT doshichandani adeeplearningapproachtostateestimationfromvideos
AT doshichandani deeplearningapproachtostateestimationfromvideos