A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-03242009-152733


Type of Document Dissertation
Author Hunter, Jonathan Edward
Author's Email Address jonathanhunter050908@gmail.com
URN etd-03242009-152733
Title Human Action Segmentation and Recognition with a High Dimensional Single Camera System
Degree PhD
Department Electrical Engineering
Advisory Committee
Advisor Name Title
Don Mitchell Wilkes Committee Chair
Daniel Levin Committee Member
Kazuhiko Kawamura Committee Member
Megan Saylor Committee Member
Richard Alan Peters II Committee Member
Keywords
  • high dimensional
  • sparse feature vectors
  • human motion segmentation
  • human motion analysis
  • behavioral cues
Date of Defense 2009-03-17
Availability unrestricted
Abstract
A key goal in machine vision is to understand how the actions of sentient agents such as humans are processed, identified, and understood. The most apparent challenge is the need to segment a continuous set of visual movements into meaningful discrete actions. Part of the work of the intentional vision research was to detect a set of determining features exhibited by human participants that account for the selection of significant action boundaries as judged by human raters. They found that action boundaries could be identified by a set of sub-actions such as hand-to-object contacts, object-to-object contacts, occlusions, and eye movements. Our goal was to create a cost effective vision system to be an easy-to-use tool for training and tracking to aid in analysis of video recordings of experiments for non-vision specialists. The system was validated for human motion analysis by applying it in conjunction with psychological studies performed with the intentional vision research. The results show correlation with the human rater data gathered from the intentional vision research showing that the cues observed in the intentional vision research are captured in our behavior feature vector. The system was extended to perform autonomous segmentation and analysis for motion studies to expand the possibility of interdisciplinary use. Of the 100 videos collected, 84 were successfully segmented and analyzed without intervention. The autonomous system was also shown to yield good results in natural scene segmentation.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  auto_p0_t1.avi 3.69 Mb 00:17:05 00:08:47 00:07:41 00:03:50 00:00:19
  auto_p0_t3.avi 2.38 Mb 00:10:59 00:05:39 00:04:56 00:02:28 00:00:12
  auto_p0_t4.avi 4.06 Mb 00:18:46 00:09:39 00:08:26 00:04:13 00:00:21
  auto_p12_t2.avi 1.50 Mb 00:06:56 00:03:34 00:03:07 00:01:33 00:00:07
  Jonathan_Hunter_Dissertation.pdf 4.48 Mb 00:20:45 00:10:40 00:09:20 00:04:40 00:00:23
  resultss12t2.avi 66.12 Mb 05:06:07 02:37:25 02:17:45 01:08:52 00:05:52
  s0_t1_vc.avi 2.57 Mb 00:11:52 00:06:06 00:05:20 00:02:40 00:00:13
  s0_t3_vc.avi 2.18 Mb 00:10:05 00:05:11 00:04:32 00:02:16 00:00:11
  s0_t4_vc.avi 11.01 Mb 00:50:59 00:26:13 00:22:56 00:11:28 00:00:58

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.