A parallel stereo reconstruction algorithm with applications in entomology (Apsra)

We propose a fast parallel algorithm for reconstruction of 3-Dimensional point clouds of insects from binocular stereo image pairs using a hierarchical approach for disparity estimation.When considering the large collections of insects Entomologists analyze,it becomes difficult to physically handle the entire collection and share the data with researchers from across the world.With the method presented in this thesis Entomologists can create an image data base for the collection and use the 3D models for studying the shape and structure of the insects.With our approach it is also easy to maintain and modify the collections. Feedback collected shows that the reconstructed 3D models are representative of the actual insects and help Entomologists identify & analyze important features of the insects like shape,size, color & texture patterns on the exoskeleton.Experimental results show the algorithm to be robust and accurate with an error of less than 0.5 cm between the dimensions of the original objects and the reconstructed models. We further optimize our results to incorporate multiview stereo which produces better overall structure of the insects.We also present some reconstruction results for faces.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Bhasin, Rajesh

Contributors dc:contributor

• Hart, John C.

• Stereo Reconstruction
• Entomology
• Insects
• Disparity Maps

Statement dc:rights

• Copyright 2011 Rajesh Bhasin

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/26243

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/26243