Crime Detection from Pre-crime Video Analysis

dc.contributor.advisorTuceryan, Mihran
dc.contributor.authorKilic, Sedat
dc.contributor.otherZheng, Jiang Yu
dc.contributor.otherTsechpenakis, Gavriil
dc.contributor.otherDurresi, Arjan
dc.date.accessioned2024-06-04T09:29:04Z
dc.date.available2024-06-04T09:29:04Z
dc.date.issued2024-05
dc.degree.date2024
dc.degree.disciplineComputer and Information Science
dc.degree.grantorPurdue University
dc.degree.levelPh.D.
dc.descriptionIndiana University-Purdue University Indianapolis (IUPUI)en
dc.description.abstractThis research investigates the detection of pre-crime events, specifically targeting behaviors indicative of shoplifting, through the advanced analysis of CCTV video data. The study introduces an innovative approach that leverages augmented human pose and emotion information within individual frames, combined with the extraction of activity information across subsequent frames, to enhance the identification of potential shoplifting actions before they occur. Utilizing a diverse set of models including 3D Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Recurrent Neural Networks (RNNs), and a specially developed transformer architecture, the research systematically explores the impact of integrating additional contextual information into video analysis. By augmenting frame-level video data with detailed pose and emotion insights, and focusing on the temporal dynamics between frames, our methodology aims to capture the nuanced behavioral patterns that precede shoplifting events. The comprehensive experimental evaluation of our models across different configurations reveals a significant improvement in the accuracy of pre-crime detection. The findings underscore the crucial role of combining visual features with augmented data and the importance of analyzing activity patterns over time for a deeper understanding of pre-shoplifting behaviors. The study’s contributions are multifaceted, including a detailed examination of pre-crime frames, strategic augmentation of video data with added contextual information, the creation of a novel transformer architecture customized for pre-crime analysis, and an extensive evaluation of various computational models to improve predictive accuracy.
dc.identifier.urihttps://hdl.handle.net/1805/41165
dc.language.isoen_US
dc.subjectcrime detection
dc.subjectvideo analysis
dc.subjectaugmented information
dc.subjectpose estimation
dc.subjectoptical flow
dc.subjectemotion estimation
dc.subjectdeep learning
dc.subjectpre-crime video analysis
dc.subjectvideo understanding
dc.subjectanomaly detection
dc.subjectcontextual information
dc.subjectshoplifting prevention
dc.subjectcrime prevention
dc.subjectvision transformer
dc.subjecttransformer
dc.subjectgenerative AI
dc.titleCrime Detection from Pre-crime Video Analysis
dc.typeThesisen
thesis.degree.disciplineComputer & Information Scienceen
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
PurdueThesis_CrimeDetectionFromPre_CrimeVideoAnalysis_SedatKilic-5.pdf
Size:
10.53 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.99 KB
Format:
Item-specific license agreed upon to submission
Description: