Capturing Eating Behavior from Video Analysis: A Systematic Review
Current methods to detect eating behavior events (i.e., bites, chews, and swallows) lack objective measurements, standard procedures, and automation. The video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we reviewed the current methods to automatica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Nutrients |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6643/14/22/4847 |
| _version_ | 1797464324037410816 |
|---|---|
| author | Michele Tufano Marlou Lasschuijt Aneesh Chauhan Edith J. M. Feskens Guido Camps |
| author_facet | Michele Tufano Marlou Lasschuijt Aneesh Chauhan Edith J. M. Feskens Guido Camps |
| author_sort | Michele Tufano |
| collection | DOAJ |
| description | Current methods to detect eating behavior events (i.e., bites, chews, and swallows) lack objective measurements, standard procedures, and automation. The video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we reviewed the current methods to automatically detect eating behavior events from video recordings. According to PRISMA guidelines, publications from 2010–2021 in PubMed, Scopus, ScienceDirect, and Google Scholar were screened through title and abstract, leading to the identification of 277 publications. We screened the full text of 52 publications and included 13 for analysis. We classified the methods in five distinct categories based on their similarities and analyzed their accuracy. Facial landmarks can count bites, chews, and food liking automatically (accuracy: 90%, 60%, 25%). Deep neural networks can detect bites and gesture intake (accuracy: 91%, 86%). The active appearance model can detect chewing (accuracy: 93%), and optical flow can count chews (accuracy: 88%). Video fluoroscopy can track swallows but is currently not suitable beyond clinical settings. The optimal method for automated counts of bites and chews is facial landmarks, although further improvements are required. Future methods should accurately predict bites, chews, and swallows using inexpensive hardware and limited computational capacity. Automatic eating behavior analysis will allow the study of eating behavior and real-time interventions to promote healthy eating behaviors. |
| first_indexed | 2024-03-09T18:05:32Z |
| format | Article |
| id | doaj.art-ecd93dd92d8e4886b6a929af2f93ccf9 |
| institution | Directory Open Access Journal |
| issn | 2072-6643 |
| language | English |
| last_indexed | 2024-03-09T18:05:32Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Nutrients |
| spelling | doaj.art-ecd93dd92d8e4886b6a929af2f93ccf92023-11-24T09:32:08ZengMDPI AGNutrients2072-66432022-11-011422484710.3390/nu14224847Capturing Eating Behavior from Video Analysis: A Systematic ReviewMichele Tufano0Marlou Lasschuijt1Aneesh Chauhan2Edith J. M. Feskens3Guido Camps4Division of Human Nutrition and Health, Wageningen University & Research, Stippeneng 4, 6708 WE Wageningen, The NetherlandsDivision of Human Nutrition and Health, Wageningen University & Research, Stippeneng 4, 6708 WE Wageningen, The NetherlandsWageningen Food and Biobased Research, Wageningen University & Research, Stippeneng 4, 6708 WE Wageningen, The NetherlandsDivision of Human Nutrition and Health, Wageningen University & Research, Stippeneng 4, 6708 WE Wageningen, The NetherlandsDivision of Human Nutrition and Health, Wageningen University & Research, Stippeneng 4, 6708 WE Wageningen, The NetherlandsCurrent methods to detect eating behavior events (i.e., bites, chews, and swallows) lack objective measurements, standard procedures, and automation. The video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we reviewed the current methods to automatically detect eating behavior events from video recordings. According to PRISMA guidelines, publications from 2010–2021 in PubMed, Scopus, ScienceDirect, and Google Scholar were screened through title and abstract, leading to the identification of 277 publications. We screened the full text of 52 publications and included 13 for analysis. We classified the methods in five distinct categories based on their similarities and analyzed their accuracy. Facial landmarks can count bites, chews, and food liking automatically (accuracy: 90%, 60%, 25%). Deep neural networks can detect bites and gesture intake (accuracy: 91%, 86%). The active appearance model can detect chewing (accuracy: 93%), and optical flow can count chews (accuracy: 88%). Video fluoroscopy can track swallows but is currently not suitable beyond clinical settings. The optimal method for automated counts of bites and chews is facial landmarks, although further improvements are required. Future methods should accurately predict bites, chews, and swallows using inexpensive hardware and limited computational capacity. Automatic eating behavior analysis will allow the study of eating behavior and real-time interventions to promote healthy eating behaviors.https://www.mdpi.com/2072-6643/14/22/4847eating behaviorcomputer visionAIautomatic analysishealthy eating |
| spellingShingle | Michele Tufano Marlou Lasschuijt Aneesh Chauhan Edith J. M. Feskens Guido Camps Capturing Eating Behavior from Video Analysis: A Systematic Review Nutrients eating behavior computer vision AI automatic analysis healthy eating |
| title | Capturing Eating Behavior from Video Analysis: A Systematic Review |
| title_full | Capturing Eating Behavior from Video Analysis: A Systematic Review |
| title_fullStr | Capturing Eating Behavior from Video Analysis: A Systematic Review |
| title_full_unstemmed | Capturing Eating Behavior from Video Analysis: A Systematic Review |
| title_short | Capturing Eating Behavior from Video Analysis: A Systematic Review |
| title_sort | capturing eating behavior from video analysis a systematic review |
| topic | eating behavior computer vision AI automatic analysis healthy eating |
| url | https://www.mdpi.com/2072-6643/14/22/4847 |
| work_keys_str_mv | AT micheletufano capturingeatingbehaviorfromvideoanalysisasystematicreview AT marloulasschuijt capturingeatingbehaviorfromvideoanalysisasystematicreview AT aneeshchauhan capturingeatingbehaviorfromvideoanalysisasystematicreview AT edithjmfeskens capturingeatingbehaviorfromvideoanalysisasystematicreview AT guidocamps capturingeatingbehaviorfromvideoanalysisasystematicreview |