San Jose Urban Forest – An Open-Source Tree Canopy Surveying and Assessment Tool

Publication Date

1-1-2025

Document Type

Conference Proceeding

Publication Title

Communications in Computer and Information Science

Volume

2487 CCIS

DOI

10.1007/978-981-96-6400-9_11

First Page

145

Last Page

156

Abstract

The accurate monitoring of tree canopy coverage is crucial for social and environmental studies as well as city planning. Our goal is to provide a solution that utilizes available resources like yearly aerial imagery to generate tree data to track all tree canopy within a city such as San Jose, CA. By utilizing open-source software and publicly available data, we streamlined the process by eliminating the need for expensive equipment and time-consuming manual efforts associated with traditional methods. The methodology involves the conversion of aerial imagery datasets into geo-referenced TIFF format through a resampling process. To optimize efficiency, we strategically select 2% of the images from the dataset for labeling, minimizing the manual effort required. The labeled images serve as the foundation for training our advanced model, enabling it to accurately identify and categorize individual trees. The result is a highly efficient, cost-effective solution that significantly reduces manual labor while providing precise tree canopy coverage calculations for the entire city. Our approach not only improves accuracy but also enhances scalability for future endeavors such as adaptation to seasonal variations, monitoring tree growth patterns, and identifying areas susceptible to potential canopy loss or even potential adoption of our solution by other cities.

Keywords

computer vision, data mining, deep learning, GIS, machine learning, Tree canopy, urban planning

Department

Computer Engineering

Link to Full Text

Share

COinS