Paper Info
Title
Accurate Chronic Wound Area Measurement using Structure from Motion
Abstract
Chronic wounds are ulcers that have a difficult or nearly interrupted healing process, leading to an increased risk of health complications, such as amputations and infections. The accurate measurement of quantitative areas is of great significance in clinical trials, wound pathological analysis, and daily patient care. Manual and 2D methods cannot solve the problems caused by human body curvatures and different camera shooting angles. This work proposes the use of a noninvasive methodology to perform the 3D reconstruction of human body surface for measuring wound areas, which combines image segmentation, structure from motion (SfM), and mesh reconstruction to obtain a better approximation of the surface. The results show that accurate 3D area measurements can be performed with images acquired with a smartphone, with average errors of 12.47%, 8.5%, 6.6% and 3.8%, when 2, 3, 5 and 10 images were used, respectively, while the average error for the 2D measurements was 32.7%.
Year
DOI
Venue
2020
10.1109/CBMS49503.2020.00047
2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)
Keywords
DocType
ISSN
Chronic Wounds, Computer Vision, 3D Reconstruction, Structure From Motion, Surface Area
Conference
2372-918X
ISBN
Citations 
PageRank 
978-1-7281-9430-1
0
0.34
References 
Authors
8
3
Name
Order
Citations
PageRank
Fellipe M. C. Barbosa100.34
Bruno M. Carvalho218219.31
Rafael Beserra Gomes3314.14