Imperial College London

DrBennyLo

Faculty of MedicineDepartment of Surgery & Cancer

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 0806benny.lo Website

 
 
//

Location

 

B414BBessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Gao,
author = {Gao, A and Lo, P and Lo, B},
publisher = {IEEE},
title = {Food volume estimation for quantifying dietary intake with a wearable camera},
url = {http://hdl.handle.net/10044/1/57659},
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - A novel food volume measurement technique isproposed in this paper for accurate quantification of the dailydietary intake of the user. The technique is based on simul-taneous localisation and mapping (SLAM), a modified versionof convex hull algorithm, and a 3D mesh object reconstructiontechnique. This paper explores the feasibility of applying SLAMtechniques for continuous food volume measurement with amonocular wearable camera. A sparse map will be generatedby SLAM after capturing the images of the food item withthe camera and the multiple convex hull algorithm is appliedto form a 3D mesh object. The volume of the target objectcan then be computed based on the mesh object. Comparedto previous volume measurement techniques, the proposedmethod can measure the food volume continuously with no priorinformation such as pre-defined food shape model. Experimentshave been carried out to evaluate this new technique andshowed the feasibility and accuracy of the proposed algorithmin measuring food volume.
AU - Gao,A
AU - Lo,P
AU - Lo,B
PB - IEEE
TI - Food volume estimation for quantifying dietary intake with a wearable camera
UR - http://hdl.handle.net/10044/1/57659
ER -