SHIPT: Simultaneous Humanoid Identification, Prediction, and Tracking

Date
2016
Journal Title
Journal ISSN
Volume Title
Publisher
Producer
Director
Performer
Choreographer
Costume Designer
Music
Videographer
Lighting Designer
Set Designer
Crew Member
Funder
Rehearsal Director
Concert Coordinator
Moderator
Panelist
Alternative Title
Department
Swarthmore College. Dept. of Engineering
Type
Thesis (B.A.)
Original Format
Running Time
File Format
Place of Publication
Date Span
Copyright Date
Award
Language
en_US
Note
Table of Contents
Terms of Use
Full copyright to this work is retained by the student author. It may only be used for non-commercial, research, and educational purposes. All other uses are restricted.
Rights Holder
Access Restrictions
Terms of Use
Tripod URL
Identifier
Abstract
The problem of automatically identifying humans in a space, tracking their motions, and predicting future locations in real time has not been attempted in the current literature. We propose a system to do this, by establishing a network of cameras, using depth subtraction with noise reduction to obtain person floor coordinates, tracking those coordinates across multiple cameras and frames, and then using LSTMs to predict future positions. At single timestep location prediction, we achieve an accuracy of 64.1%, over ten points better than the best applicable baseline. Over 30 timesteps (in our model, two seconds into the future), we achieve an average error of only 2.19 meters.
Description
Subjects
Citation
Collections