Times are displayed in (UTC-05:00) Eastern Time (US & Canada)Change
Title: Leveraging Deep Learning and AI-Based Image Classification for Urban Planning in Detroit Amidst Projected Population Growth by U.N.
Topics:
Keywords: Detroit, Deep Learning, LULC Change, Object Detection, AI Abstract Type: Poster Abstract
Authors:
SM Ahsanullah, The Ohio State University
,
,
,
,
,
,
,
,
,
Abstract
This study seeks to effectively harness deep learning and artificial intelligence (AI) within an ArcGIS environment to enhance image classification and object detection significantly. By doing so, we can achieve improved accuracy in mapping the dynamic landscape of Detroit. Utilizing convolutional neural networks (CNNs) and cutting-edge machine learning algorithms allows for the extensive analysis of high-resolution satellite imagery. Integrating these AI techniques into ArcGIS Pro enables the creation of robust training data, which can successfully detect and classify various urban features, including cars, buildings, vacant lots, and green spaces. This innovative approach ultimately supports more precise urban planning and spatial development, contributing positively to the future of urban spaces.
Title: Leveraging Deep Learning and AI-Based Image Classification for Urban Planning in Detroit Amidst Projected Population Growth by U.N.