Capturing Eating Behavior from Video Analysis: A Systematic Review

Tufano, Michele; Lasschuijt, Marlou; Chauhan, Aneesh; Feskens, Edith J. M.; Camps, Guido

doi:10.3390/nu14224847

Cited by 12 publications

(7 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ideally, the experiments should allow data to be collected anonymously if this information is not needed for a certain purpose such as clinical data collection. This could be achieved by only storing extracted features from the camera data rather than the images themselves, though this prohibits later validation and improvement of feature extraction [ 135 ]. Systems using weight sensors do not suffer from privacy issues as camera images from the face do.…”

Section: Discussionmentioning

confidence: 99%

“… Since 2000 67 Articles published in peer-reviewed venues; […] Papers that describe methods for estimation of portion size; FPSE methods that are either automatic or semi-automatic; written in English. [ 135 ] 2022 [They] reviewed the current methods to automatically detect eating behavior events from video recordings. 2010–2021 13 Original research articles […] published in the English language and containing findings on video analysis for human eating behavior from January 2010 to December 2021.…”

Section: Table A1mentioning

confidence: 99%

See 1 more Smart Citation

Technology to Automatically Record Eating Behavior in Real Life: A Systematic Review

Hiraguchi,

Perone,

Toet

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

To monitor adherence to diets and to design and evaluate nutritional interventions, it is essential to obtain objective knowledge about eating behavior. In most research, measures of eating behavior are based on self-reporting, such as 24-h recalls, food records (food diaries) and food frequency questionnaires. Self-reporting is prone to inaccuracies due to inaccurate and subjective recall and other biases. Recording behavior using nonobtrusive technology in daily life would overcome this. Here, we provide an up-to-date systematic overview encompassing all (close-to) publicly or commercially available technologies to automatically record eating behavior in real-life settings. A total of 1328 studies were screened and, after applying defined inclusion and exclusion criteria, 122 studies were included for in-depth evaluation. Technologies in these studies were categorized by what type of eating behavior they measure and which type of sensor technology they use. In general, we found that relatively simple sensors are often used. Depending on the purpose, these are mainly motion sensors, microphones, weight sensors and photo cameras. While several of these technologies are commercially available, there is still a lack of publicly available algorithms that are needed to process and interpret the resulting data. We argue that future work should focus on developing robust algorithms and validating these technologies in real-life settings. Combining technologies (e.g., prompting individuals for self-reports at sensed, opportune moments) is a promising route toward ecologically valid studies of eating behavior.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Table A1mentioning

confidence: 99%

Technology to Automatically Record Eating Behavior in Real Life: A Systematic Review

Hiraguchi,

Perone,

Toet

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…We argue that the measurement of dietary behavior in people affected by obesity should be either assessed in a complementary way that combines the GDBI with food frequency questionnaires [ 66 , 67 ], or by developing a new instrument that covers the situation and circumstances of this population. Other approaches, such as video analyses [ 68 ] or sensing technology [ 69 ], should also be considered as a substitute for self-reported questionnaires. Therefore, future studies should engage with the conceptualization and valid measurement of dietary behavior in people affected by obesity.…”

Section: Discussionmentioning

confidence: 99%

Exploring the Applicability of General Dietary Recommendations for People Affected by Obesity

et al. 2023

View full text Add to dashboard Cite

(1) Obesity has emerged as a major public health challenge with increasing prevalence globally. The General Dietary Behavior Inventory (GDBI) was developed based on official dietary recommendations. However, little is known about whether general dietary recommendations also apply to people affected by obesity and whether the GDBI can be used appropriately. (2) A cross-sectional study was conducted. A total of 458 people meeting the inclusion criteria participated in the study. The assessment consisted of the GDBI and behavioral, dietary, and health-related variables. We used descriptive analysis to examine the item characteristics of the GDBI and inferential statistics to investigate the associations between the GDBI score and behavioral, dietary, and health-related outcomes. (3) Several items of the GDBI were concerned by ceiling effects. A higher GDBI score (indicating a higher adherence to dietary recommendations) was related to higher age, higher nutrition knowledge, more restrained eating behavior, lower impulsivity, and higher body mass index. There were no associations between the GDBI score and reported physical and mental health or quality of life. (4) The GDBI showed inconsistent relationships with the study outcomes. General dietary recommendations do not appear to be applicable to people with obesity. Hence, there is an urgent need for specific recommendations and subsequent assessments of behavioral adherence for people affected by obesity.

show abstract

“…Novel research involving wearable devices has been developed to alleviate the burden and accuracy problems with self-reported data and offer automatic detection and monitoring of food intake ( 18 ). A recent systematic review assessing available methods to automatically detect eating behavior found the use of facial landmarks (i.e., localize and track key points on a human face) is the most promising method for detecting eating events ( 19 ). Using novel wearable devices that automatically capture images during food and beverage intake, direct annotation of eating environment can be obtained by capturing meal images, eating location, and who someone is eating with ( 12 ).…”

Section: Introductionmentioning

confidence: 99%

The spectrum of eating environments encountered in free living adults documented using a passive capture food intake wearable device

et al. 2023

View full text Add to dashboard Cite

IntroductionThe aim of this feasibility and proof-of-concept study was to examine the use of a novel wearable device for automatic food intake detection to capture the full range of free-living eating environments of adults with overweight and obesity. In this paper, we document eating environments of individuals that have not been thoroughly described previously in nutrition software as current practices rely on participant self-report and methods with limited eating environment options.MethodsData from 25 participants and 116 total days (7 men, 18 women, Mage = 44 ± 12 years, BMI 34.3 ± 5.2 kg/mm2), who wore the passive capture device for at least 7 consecutive days (≥12h waking hours/d) were analyzed. Data were analyzed at the participant level and stratified amongst meal type into breakfast, lunch, dinner, and snack categories. Out of 116 days, 68.1% included breakfast, 71.5% included lunch, 82.8% included dinner, and 86.2% included at least one snack.ResultsThe most prevalent eating environment among all eating occasions was at home and with one or more screens in use (breakfast: 48.1%, lunch: 42.2%, dinner: 50%, and snacks: 55%), eating alone (breakfast: 75.9%, lunch: 89.2%, dinner: 74.3%, snacks: 74.3%), in the dining room (breakfast: 36.7%, lunch: 30.1%, dinner: 45.8%) or living room (snacks: 28.0%), and in multiple locations (breakfast: 44.3%, lunch: 28.8%, dinner: 44.8%, snacks: 41.3%).DiscussionResults suggest a passive capture device can provide accurate detection of food intake in multiple eating environments. To our knowledge, this is the first study to classify eating occasions in multiple eating environments and may be a useful tool for future behavioral research studies to accurately codify eating environments.

show abstract

Capturing Eating Behavior from Video Analysis: A Systematic Review

Cited by 12 publications

References 65 publications

Technology to Automatically Record Eating Behavior in Real Life: A Systematic Review

Technology to Automatically Record Eating Behavior in Real Life: A Systematic Review

Exploring the Applicability of General Dietary Recommendations for People Affected by Obesity

The spectrum of eating environments encountered in free living adults documented using a passive capture food intake wearable device

Contact Info

Product

Resources

About