Undergrad Research Project - Masking vegetation and sky in images for improved 3D reconstruction

Fall 2016

Student
Elizabeth Yan
Advisor
John Dolan
Project description

The goal of this project is to detect and mask vegetation and sky in a set of images to improve the 3D reconstruction of other objects. Programs like VisualSFM are able to make a 3D model of an object from a set of images that have been taken from different viewpoints. The Navlab group has used VisualSFM to make 3D models of accident scenes. The program works best when the scene is static. Parts of the scene that change, like clouds and vegetation moved by wind, can cause significant problems. It is therefore desirable to detect sky and vegetation in the images and mask them. Lisa will first learn how to use the 3D reconstruction methods used by the Navlab group. Then she will also learn to use a texture detection program. She will have to learn how to train this program to detect vegetation and sky. Lastly Lisa has to implement a mask that instructs VisualSFM to ignore all of the detected regions. The detection and masking algorithm should be validated by testing it on several of our accident data sets.

Return to project list