Estimation of Energy Expenditure during Treadmill Exercise via Thermal Imaging

Jensen, Martin Møller; Poulsen, Mathias Krogh; Alldieck, Thiemo; Larsen, Ryan Godsk; Gade, Rikke; Moeslund, Thomas B.; Franch, Jesper

doi:10.1249/mss.0000000000001013

Cited by 16 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Correspondingly, a person's M is estimated by measuring his or her oxygen consumption and carbon dioxide generation [23][24][25], heart rates [26][27][28][29], or blood pressure [30]. Though [31][32][33] adopt cameras for such a task, they still partly rely on sophisticated equipment mentioned above. These devices have to be worn by subjects, making them unrealistically used in daily life.…”

Section: CL and M Estimationmentioning

confidence: 99%

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Liu

Foged

Moeslund

2022

Sensors

View full text Add to dashboard Cite

Satisfactory indoor thermal environments can improve working efficiencies of office staff. To build such satisfactory indoor microclimates, individual thermal comfort assessment is important, for which personal clothing insulation rate (Icl) and metabolic rate (M) need to be estimated dynamically. Therefore, this paper proposes a vision-based method. Specifically, a human tracking-by-detection framework is implemented to acquire each person’s clothing status (short-sleeved, long-sleeved), key posture (sitting, standing), and bounding box information simultaneously. The clothing status together with a key body points detector locate the person’s skin region and clothes region, allowing the measurement of skin temperature (Ts) and clothes temperature (Tc), and realizing the calculation of Icl from Ts and Tc. The key posture and the bounding box change across time can category the person’s activity intensity into a corresponding level, from which the M value is estimated. Moreover, we have collected a multi-person thermal dataset to evaluate the method. The tracking-by-detection framework achieves a mAP50 (Mean Average Precision) rate of 89.1% and a MOTA (Multiple Object Tracking Accuracy) rate of 99.5%. The Icl estimation module gets an accuracy of 96.2% in locating skin and clothes. The M estimation module obtains a classification rate of 95.6% in categorizing activity level. All of these prove the usefulness of the proposed method in a multi-person scenario of real-life applications.

show abstract

Section: CL and M Estimationmentioning

confidence: 99%

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Liu

Foged

Moeslund

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Current methods applied within health and sports science require direct measurements of oxygen uptake by metabolic carts (wearing respiratory masks) [26] or indirect measurements using heart rate monitors, accelerometers [27], or GPS data [28]. In this work we introduce a non-intrusive method based on thermal video, which is evaluated against traditional measurements of oxygen uptake [29]. The ultimate goal is to be able to estimate energy expenditure of all individuals participating in a sports activity, but the first research in this direction will start with a controlled environment using a treadmill experiment.…”

Section: Estimating Energy Expenditurementioning

confidence: 99%

Automatic Analysis of Activities in Sports Arenas Using Thermal Cameras

Gade¹,

Jorgensen²,

Jensen

et al. 2016

2016 12th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

Self Cite

View full text Add to dashboard Cite

Abstract-The demand for automatically gathered data is a societal trend quickly extending to all aspects of human life. Knowledge on the utilization of public facilities is of interest for optimising use and cutting expenses for the owners. Manual observations are both cumbersome and expensive, and they have a risk of incorrect results due to subjective opinions or lack of interest in the given task. In this paper we present the main results of a 5-year long research project revolving around the real-world application of automatic analysis of activities in sports arenas. Three topics are explored: Counting people, recognising activities, and estimating energy expenditure. The project is based on thermal image data, to preserve privacy while capturing video in public sports arenas. This paper aim to provide an overview of our published methods and results within these three topics and add a discussion of the results and perspectives of this research.

show abstract

“…Running is the primary modality of aerobic exercise performed by many physically active adults, athletes, and military personnel. This ubiquity has inspired over a century of sports and exercise research focused on quantifying the rate of metabolic energy expenditure (Ṁ) during running (1)(2)(3)(4)(5)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20)(20)(21)(22)(23)23,24,(24)(25)(26)26,27,(27)(28)(29)(30)32,(35)(36)(37)(38)(39)(41)(42)(43)(44)(45)47,(49)(50)(51)56,58,…”

Section: Introductionmentioning

confidence: 99%

“…Running is the primary modality of aerobic exercise performed by many physically active adults, athletes, and military personnel. This ubiquity has inspired over a century of sports and exercise research focused on quantifying the rate of metabolic energy expenditure (Ṁ) during running (1–5,8–20,20–23,23,24,24–26,26,27,27–30,32,35–39,41–45,47,49–51,56,58,60,65–67,73,74,76,77,79,80). Precise Ṁ estimates are needed to optimize distance running performance (48) and nutritional interventions (33).…”

Section: Introductionmentioning

confidence: 99%

Estimating Metabolic Energy Expenditure During Level Running in Healthy, Military-Age Women and Men

Looney,

Hoogkamer,

Kram

et al. 2023

Journal of Strength and Conditioning Research

View full text Add to dashboard Cite

Looney, DP, Hoogkamer, W, Kram, R, Arellano, CJ, and Spiering, BA. Estimating metabolic energy expenditure during level running in healthy, military-age women and men. J Strength Cond Res 37(12): 2496–2503, 2023—Quantifying the rate of metabolic energy expenditure (Ṁ) of varied aerobic exercise modalities is important for optimizing fueling and performance and maintaining safety in military personnel operating in extreme conditions. However, although equations exist for estimating oxygen uptake during running, surprisingly, there are no general equations that estimate Ṁ. Our purpose was to generate a general equation for estimating Ṁ during level running in healthy, military-age (18–44 years) women and men. We compiled indirect calorimetry data collected during treadmill running from 3 types of sources: original individual subject data (n = 45), published individual subject data (30 studies; n = 421), and published group mean data (20 studies, n = 619). Linear and quadratic equations were fit on the aggregated data set using a mixed-effects modeling approach. A chi-squared (χ 2) difference test was conducted to determine whether the more complex quadratic equation was justified (p < 0.05). Our primary indicator of model goodness-of-fit was the root-mean-square deviation (RMSD). We also examined whether individual characteristics (age, height, body mass, and maximal oxygen uptake [V̇O2max]) could minimize prediction errors. The compiled data set exhibited considerable variability in Ṁ (14.54 ± 3.52 W·kg−1), respiratory exchange ratios (0.89 ± 0.06), and running speeds (3.50 ± 0.86 m·s−1). The quadratic regression equation had reduced residual sum of squares compared with the linear fit (χ 2, 3,484; p < 0.001), with higher combined accuracy and precision (RMSD, 1.31 vs. 1.33 W·kg−1). Age (p = 0.034), height (p = 0.026), and body mass (p = 0.019) were associated with the magnitude of under and overestimation, which was not the case for V̇O2max (p = 0.898). The newly derived running energy expenditure estimation (RE3) model accurately predicts level running Ṁ at speeds from 1.78 to 5.70 m·s−1 in healthy, military-age women and men. Users can rely on the following equations for improved predictions of running Ṁ as a function of running speed (S, m·s−1) in either watts (W·kg−1 = 4.43 + 1.51·S + 0.37·S2) or kilocalories per minute (kcal·kg−1·min−1 = 308.8 + 105.2·S + 25.58·S2).

show abstract

Estimation of Energy Expenditure during Treadmill Exercise via Thermal Imaging

Abstract: Optical flow measurements provide an accurate estimation of energy expenditure during horizontal walking and running. The technique offers a novel experimental method of estimating energy expenditure during human locomotion, without use of interfering equipment attached to the subject.

Cited by 16 publications

References 27 publications

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Automatic Analysis of Activities in Sports Arenas Using Thermal Cameras

Estimating Metabolic Energy Expenditure During Level Running in Healthy, Military-Age Women and Men

Contact Info

Product

Resources

About