UWSpace is currently experiencing technical difficulties resulting from its recent migration to a new version of its software. These technical issues are not affecting the submission and browse features of the site. UWaterloo community members may continue submitting items to UWSpace. We apologize for the inconvenience, and are actively working to resolve these technical issues.
 

On the Design of 2D Human Pose Estimation Networks using Accelerated Neuroevolution and Novel Keypoint Representations

dc.contributor.authorMcNally, William
dc.date.accessioned2022-05-02T13:31:06Z
dc.date.available2022-05-02T13:31:06Z
dc.date.issued2022-05-02
dc.date.submitted2022-04-21
dc.description.abstractMotion capture is a very useful technology that is employed across many industries. Biomechanical analysis, film production, video game development, and virtual reality are among its diverse applications. However, traditional marker-based motion capture systems are limited by their invasiveness, excessive cost, and lack of portability. Human pose estimation represents a promising markerless alternative, where 3D human poses are estimated from RGB images obtained using single or multi-camera setups. The estimation of 2D poses serves as the main foundation for these systems. As such, the development of accurate and efficient 2D human pose estimation algorithms is critical to the overall advancement of markerless motion capture, and that is the focus of this thesis. Two novel convolutional neural networks for 2D human pose estimation are presented, one for each of the two multi-person estimation paradigms (i.e., single-stage and two-stage). Motivated by the recent use of neural architecture search for convolutional neural network design, a novel neuroevolution framework is introduced and is leveraged in the design of a computationally efficient heatmap-based human pose estimation network for use in the two-stage paradigm. The neuroevolution was accelerated by a novel weight transfer scheme that relaxes the complete function-preservation constraint imposed by previous methods. Recognizing the drawbacks of heatmaps, including the inherent issue of quantization error and the excessive computation required to generate and post-process large heatmap fields, two novel heatmap-free keypoint representations are introduced for modeling keypoint locations more efficiently. Drawing inspiration from single-stage object detectors, the representations are centered around modeling individual keypoints and sets of spatially related keypoints (i.e., poses) as objects. It is found that pose objects lend themselves well to single-stage human pose estimation, and a method is introduced that jointly learns human pose objects and keypoint objects and fuses the detections to exploit the strengths of both object representations. At the time of development, both networks achieved state-of-the-art accuracy in their respective categories on the most established multi-person human pose estimation benchmarks when scaled. Moreover, they are more computationally efficient than previous networks as shown by having fewer parameters, fewer floating-point operations, and faster inference speed. The two-stage model is recommended for accuracy-critical scenarios with large computational budgets, whereas the single-stage model is more efficient and has greater potential for future research. It is hoped that these new models advance the current state of markerless motion capture systems based on human pose estimation.en
dc.identifier.urihttp://hdl.handle.net/10012/18215
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.relation.urihttps://github.com/wmcnally/evopose2den
dc.relation.urihttps://github.com/wmcnally/kapaoen
dc.subjecthuman pose estimationen
dc.subjectobject detectionen
dc.subjectcomputer visionen
dc.subjectdeep learningen
dc.subjectneural architecture searchen
dc.subjectneuroevolutionen
dc.subjectartificial intelligenceen
dc.titleOn the Design of 2D Human Pose Estimation Networks using Accelerated Neuroevolution and Novel Keypoint Representationsen
dc.typeDoctoral Thesisen
uws-etd.degreeDoctor of Philosophyen
uws-etd.degree.departmentSystems Design Engineeringen
uws-etd.degree.disciplineSystem Design Engineeringen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.embargo.terms0en
uws.contributor.advisorMcPhee, John
uws.contributor.advisorWong, Alexander
uws.contributor.affiliation1Faculty of Engineeringen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
McNally_William.pdf
Size:
15.15 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.4 KB
Format:
Item-specific license agreed upon to submission
Description: