Active Observers in a 3D World: Human Visual Behaviours for Active Vision

Simple item page
dc.contributor.advisorTsotsos, John K.
dc.contributor.authorSolbach, Markus Dieter
dc.date.accessioned2022-12-14T16:29:18Z
dc.date.available2022-12-14T16:29:18Z
dc.date.copyright2022-07-26
dc.date.issued2022-12-14
dc.date.updated2022-12-14T16:29:17Z
dc.degree.disciplineComputer Science
dc.degree.levelDoctoral
dc.degree.namePhD - Doctor of Philosophy
dc.description.abstractHuman-like performance in computational vision systems is yet to be achieved. In fact, human-like visuospatial behaviours are not well understood – a crucial capability for any robotic system whose role is to be a real assistant. This dissertation examines human visual behaviours involved in solving a well-known visual task; The Same-Different Task. It is used as a probe to explore the space of active human observation during visual problem-solving. It asks a simple question: “are two objects the same?”. To study this question, we created a set of novel objects with known complexity to push the boundaries of the human visual system. We wanted to examine these behaviours as opposed to the static, 2D, display-driven experiments done to date. We thus needed to develop a complete infrastructure for an experimental investigation using 3D objects and active, free, human observers. We have built a novel, psychophysical experimental setup that allows for precise and synchronized gaze and head-pose tracking to analyze subjects performing the task. To the best of our knowledge, no other system provides the same characteristics. We have collected detailed, first-of-its-kind data of humans performing a visuospatial task in hundreds of experiments. We present an in-depth analysis of different metrics of humans solving this task, who demonstrated up to 100% accuracy for specific settings and that no trial used less than six fixations. We provide a complexity analysis that reveals human performance in solving this task is about O(n), where n is the size of the object. Furthermore, we discovered that our subjects used many different visuospatial strategies and showed that they are deployed dynamically. Strikingly, no learning effect was observed that affected the accuracy. With this extensive and unique data set, we addressed its computational counterpart. We used reinforcement learning to learn the three-dimensional same-different task and discovered crucial limitations which only were overcome if the task was simplified to the point of trivialization. Lastly, we formalized a set of suggestions to inform the enhancement of existing machine learning methods based on our findings from the human experiments and multiple tests we performed with modern machine learning methods.
dc.identifier.urihttp://hdl.handle.net/10315/40680
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsComputer vision
dc.subject.keywordsActive vision
dc.subject.keywordsRobotics
dc.subject.keywordsReinforcement learning
dc.subject.keywordsMachine learning
dc.subject.keywordsVisual behaviours
dc.subject.keywordsHuman-like behaviours
dc.subject.keywordsVisual routines
dc.subject.keywordsCognitive programs
dc.subject.keywordsArtificial intelligence
dc.subject.keywordsActive observation
dc.subject.keywordsActive agent
dc.subject.keywordsActive observer
dc.subject.keywordsAgent
dc.subject.keywordsVisual perception
dc.subject.keywordsVisuospatial
dc.subject.keywordsPsychophysical
dc.subject.keywordsSame-different
dc.subject.keywordsSpeeded rotation
dc.subject.keywordsProgressive learning
dc.subject.keywordsHuman-computer interaction
dc.subject.keywordsHuman-robot interaction
dc.titleActive Observers in a 3D World: Human Visual Behaviours for Active Vision
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Solbach_Markus_D_2022_PhD.pdf
Size:
29.04 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.