Date of Submission

Fall 2017

Academic Programs and Concentrations

Computer Science

Project Advisor 1

Keith O'Hara

Abstract/Artist's Statement

This project explores how to compute 3D volume of cardboard boxes in 2D without a calibrated camera. Computer vision techniques to obtain 3D volume typically require camera calibration, the standard method for mapping 3D points to 2D. We created our own solution that doesn’t rely on camera calibration and obtains the areas of each box with unknown dimensions with the help of a chessboard pattern placed on each box side. The solution is a proportion that given the box area in pixels, chessboard pattern in pixels, and the chessboard pattern in inches, determines the box area in inches. We tested this method on 20 boxes, 5 pictures of each side for one box. The results showed positive feedback compared with the defined areas/ volumes and compared with the results of our homographies. Ultimately we determined that our solution has the potential, with improved photos, test methods, etc. to accurately find an unknown box’s volume given only the provided 2D data.

Open Access Agreement

Open Access

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Download

This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.

Share

COinS