Education Commons^™

Long-Term Human Participation Detection Using A Dynamic Scene Analysis Model, Wenjing Shi

Electrical and Computer Engineering ETDs

The dissertation develops new methods for assessing student participation in long (>1 hour) classroom videos. First, the dissertation introduces the use of multiple image representations based on raw RGB images and AM-FM components to detect specific student groups. Second, a dynamic scene analysis model is developed for tracking under occlusion and variable camera angles. Third, a motion vector projection system identifies instances of students talking.

The proposed methods are validated using digital videos from the Advancing Out-of-school Learning in Mathematics and Engineering (AOLME) project. The proposed methods are shown to provide better group detection, and better talking detection at …

Speaker Diarization And Identification From Single-Channel Classroom Audio Recording Using Virtual Microphones, Antonio Gomez

Electrical and Computer Engineering ETDs

Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking at the same time. To solve the problem, we assume the use of a single microphone per student group without any access to previous large datasets for training.

This dissertation proposes a method of speaker identification using cross-correlation patterns associated to an array of virtual microphones, centered around the physical microphone. The virtual microphones are simulated by using approximate speaker geometry observed from a video recording. The patterns …

Distributed And Scalable Video Analysis Architecture For Human Activity Recognition Using Cloud Services, Cody Wilson Eilar

Electrical and Computer Engineering ETDs

This thesis proposes an open-source, maintainable system for detecting human activity in large video datasets using scalable hardware architectures. The system is validated by detecting writing and typing activities that were collected as part of the Advancing Out of School Learning in Mathematics and Engineering (AOLME) project. The implementation of the system using Amazon Web Services (AWS) is shown to be both horizontally and vertically scalable. The software associated with the system was designed to be robust so as to facilitate reproducibility and extensibility for future research.