“Unveiling the Invisible”: Deep Learning-based Semantic Segmentation for Analyzing Activity Patterns

Gurkiran Kaur, Li Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Downloads (Pure)

Abstract

The ubiquity of internet-enabled devices has led to a rapid increase in the use of connected cameras for real-time monitoring, creating a high demand for (automated) visual data analytics across various industries. The prospect of automating visual data analysis to drive positive change involves extracting actionable insights from data that will inform decision-making processes, improving efficiency, and contributing to evidence-based strategies across diverse applications and industries. This research explores and compares well-known semantic segmentation models such as DeepLabV3+ and UNet, determining the best-suited for use in a visual analytics and scene understanding, culminating in a proof of concept program capable of automating video analysis, plotting detections, average trajectories, and identifying outliers.
Original languageEnglish
Title of host publicationIntelligent Management of Data and Information in Decision Making
Subtitle of host publicationProceedings of the 16th FLINS Conference on Computational Intelligence in Decision and Control & the 19th ISKE Conference on Intelligence Systems and Knowledge Engineering (FLINS-ISKE 2024)
Pages411-418
Number of pages8
ISBN (Electronic)978-981-12-9464-8
DOIs
Publication statusPublished - 30 Jul 2024

Publication series

NameWorld Scientific Proceedings Series on Computer Engineering and Information Science
ISSN (Print)1793-7868
ISSN (Electronic)2972-4465

Cite this