Authors:

Christina Zhang

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

The purpose of this project is to analyze a drone under-canopy footage uploaded by the user and provide tree visualizations, information for each tree, and an annotated video that visually highlights each detected tree along the drone's flight path while displaying the assigned ID and the estimated DBH (Diameter at Breast Height) for each detected tree. This project utilizes Typescript and React for the frontend of the website, which consists of a tab for email recording and file uploading. The frontend requires a pair of MP4 and SRT files to be uploaded and sends a request to the backend to begin the processing. The backend is mostly written in Python and uses algorithms developed by the team to process the uploaded files. Once processing completes, the results are ready to be viewed - the frontend displays the annotated video and uses the JSON file from the backend to create an interactive tree visualization that shows the ID, estimated DBH, and position of each tree when hovered over. The user can switch between different views, including UTM and Latitude/Longitude. The tree information is saved in a CSV file and can be downloaded along with the annotated video from the website. Farmers could use this tool to estimate the value of their trees by simply using a drone without needing a LiDAR. By improving the accuracy of the DBH estimations, this tool could obviate the need to manually measure each tree. Keywords: [no keywords provided]

Source:

Purdue University / 2025

Topics:

No topics listed

Co-authors:

Christina Zhang