Pitt Logo LinkContact Us

Food Dimension Estimation from A Single Image Using Structured Lights

Yao, Ning (2011) Food Dimension Estimation from A Single Image Using Structured Lights. Doctoral Dissertation, University of Pittsburgh.

[img]
Preview
PDF - Primary Text
Download (2344Kb) | Preview

    Abstract

    Two-thirds the population in the United States of America are overweight or obese. The annual medical expenditures attributable to obesity may be as high as $215 billion per year. Obesity has been linked to many types of diseases, including cancer, type 2 diabetes, cardiovascular diseases, respiratory diseases, stroke and birth defects. Deaths related to obesity are estimated at 300,000 each year in the United States. In order to understand the etiology of the obesity epidemic and develop effective weight management methods for obese patients, accurate dietary data is an essential requirement. However, the current dietary assessment methods, which depend on self-reported data by the respondents, have an estimated 20% to 50% discrepancy from the intake. This large error severely affects obesity research.The recent rapid advances in electrical engineering and information technology fields have provided sophisticated devices and intelligent algorithms for dietary assessment. Considering portability and battery-life, systems installed with a single camera have the advantages of low cost, space saving, and low power consumption. Although severalmethods have been proposed to estimate food quantities and dimensions, many of these methods cannot be used in practice because of their inconvenience, and the requirement of calibration andmaintenance. In this dissertation, we present several approaches to food dimensional estimation using two types of structured lights. These approaches are low in costand power consumption, and suitable for small and portable image acquisition devices.Our first design uses structured laser beams as reference lights. Three identical laser modules are structured to form an equilateraltriangle on the plane orthogonal to the camera optical axis. A new method based on orthogonallinear regression is proposed to release restrictions on the laserbeams, so that the precision requirement for equilateral triangle can be relaxed. Based on the perspective projectiongeometry, intersections of structured laser beams andperspective projection rays are estimated, which construct a spatial planecontaining the projection of the objects of interest. The dimensions of the objects on theobserved plane are then calculated. In the second design, an LED diode is used as a reference light. A new algorithm is developed to estimate the object plane using the deformation of the observed ellipse.In order to provide a precise system calibration between the structured lights and the camera, an orthogonal linear regression method is proposed to calibrate the structured lights. Characteristics of the reference features are investigated. A color-based thresholding method is proposed to segment features. An ellipse fitting method is used to extract feature parameters. The extraction results of our algorithms are very close to those manually performed by human.Several experiments are performed to test our designs using both artificial and real food. Our experimental results show an average estimation error of lessthan 10%.


    Share

    Citation/Export:
    Social Networking:

    Details

    Item Type: University of Pittsburgh ETD
    ETD Committee:
    ETD Committee TypeCommittee MemberEmailORCID
    Committee ChairSun, Minguidrsun@pitt.edu
    Committee MemberLi, Ching-Chungccl@pitt.edu
    Committee MemberChaparro, Luis Flfch@pitt.edu
    Committee MemberSclabassi, Robert Jbobs@cdi.com
    Committee MemberMao, Zhi-Hongzhm4@pitt.edu
    Title: Food Dimension Estimation from A Single Image Using Structured Lights
    Status: Unpublished
    Abstract: Two-thirds the population in the United States of America are overweight or obese. The annual medical expenditures attributable to obesity may be as high as $215 billion per year. Obesity has been linked to many types of diseases, including cancer, type 2 diabetes, cardiovascular diseases, respiratory diseases, stroke and birth defects. Deaths related to obesity are estimated at 300,000 each year in the United States. In order to understand the etiology of the obesity epidemic and develop effective weight management methods for obese patients, accurate dietary data is an essential requirement. However, the current dietary assessment methods, which depend on self-reported data by the respondents, have an estimated 20% to 50% discrepancy from the intake. This large error severely affects obesity research.The recent rapid advances in electrical engineering and information technology fields have provided sophisticated devices and intelligent algorithms for dietary assessment. Considering portability and battery-life, systems installed with a single camera have the advantages of low cost, space saving, and low power consumption. Although severalmethods have been proposed to estimate food quantities and dimensions, many of these methods cannot be used in practice because of their inconvenience, and the requirement of calibration andmaintenance. In this dissertation, we present several approaches to food dimensional estimation using two types of structured lights. These approaches are low in costand power consumption, and suitable for small and portable image acquisition devices.Our first design uses structured laser beams as reference lights. Three identical laser modules are structured to form an equilateraltriangle on the plane orthogonal to the camera optical axis. A new method based on orthogonallinear regression is proposed to release restrictions on the laserbeams, so that the precision requirement for equilateral triangle can be relaxed. Based on the perspective projectiongeometry, intersections of structured laser beams andperspective projection rays are estimated, which construct a spatial planecontaining the projection of the objects of interest. The dimensions of the objects on theobserved plane are then calculated. In the second design, an LED diode is used as a reference light. A new algorithm is developed to estimate the object plane using the deformation of the observed ellipse.In order to provide a precise system calibration between the structured lights and the camera, an orthogonal linear regression method is proposed to calibrate the structured lights. Characteristics of the reference features are investigated. A color-based thresholding method is proposed to segment features. An ellipse fitting method is used to extract feature parameters. The extraction results of our algorithms are very close to those manually performed by human.Several experiments are performed to test our designs using both artificial and real food. Our experimental results show an average estimation error of lessthan 10%.
    Date: 26 January 2011
    Date Type: Completion
    Defense Date: 18 October 2010
    Approval Date: 26 January 2011
    Submission Date: 01 October 2010
    Access Restriction: No restriction; The work is available for access worldwide immediately.
    Patent pending: No
    Institution: University of Pittsburgh
    Thesis Type: Doctoral Dissertation
    Refereed: Yes
    Degree: PhD - Doctor of Philosophy
    URN: etd-10012010-105153
    Uncontrolled Keywords: feature extraction; food dimension estimation; optical system design; perspective projection; structured light; system calibration; computer vision; geometric algorithm; laser
    Schools and Programs: Swanson School of Engineering > Electrical Engineering
    Date Deposited: 10 Nov 2011 15:02
    Last Modified: 07 May 2012 11:23
    Other ID: http://etd.library.pitt.edu/ETD/available/etd-10012010-105153/, etd-10012010-105153

    Actions (login required)

    View Item

    Document Downloads