Publication Date

Spring 2025

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering

Advisor

Kaikai Liu; Bernardo Flores; Wencen Wu

Abstract

Pose detection involves locating and identifying key body points for all individuals within a frame. This enables the ability to convert the pose into a digital format, which can then be recorded and analyzed for a variety of purposes. Advancements in the field have already opened applications in areas such as digital fitness coaches, fall detection, and virtual reality. Existing approaches primarily focus on tracking all detected individuals, which limits the practical applications when attempting to analyze a single or specific subject when there are other people in frame. Previous work has discussed integrating identification, but these approaches use identification primarily to improve tracking consistency rather than to enable targeted detection. This work addresses the understudied problem of targeted pose detection, where only specific individuals are recognized and tracked. A novel multi-task model and pipeline is proposed, integrating techniques for person detection, pose estimation, facial recognition, and object tracking. In addition, a proof of concept implementation is created. The approach enables pose detection for broader use in fields like sports data analytics where the frame includes crowds or other individuals, as well as in security applications such as prisons and airports. By streamlining detection for targeted results, the model provides more useful output while removing unnecessary computation for irrelevant subjects.

Download

Share

COinS