Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge
The rapid expansion of video conferencing and remote works due to the COVID-19 pandemic has resulted in a massive volume of video data to be analyzed in order to understand the audience engagement. However, analyzing this data efficiently, particularly in real-time, poses a scalability challenge as...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/16/2/86 |
| _version_ | 1797622842339098624 |
|---|---|
| author | Saw Thiha Jay Rajasekera |
| author_facet | Saw Thiha Jay Rajasekera |
| author_sort | Saw Thiha |
| collection | DOAJ |
| description | The rapid expansion of video conferencing and remote works due to the COVID-19 pandemic has resulted in a massive volume of video data to be analyzed in order to understand the audience engagement. However, analyzing this data efficiently, particularly in real-time, poses a scalability challenge as online events can involve hundreds of people and last for hours. Existing solutions, especially open-sourced contributions, usually require dedicated and expensive hardware, and are designed as centralized cloud systems. Additionally, they may also require users to stream their video to remote servers, which raises privacy concerns. This paper introduces scalable and efficient computer vision algorithms for analyzing face orientation and eye blink in real-time on edge devices, including Android, iOS, and Raspberry Pi. An example solution is presented for proctoring online meetings, workplaces, and exams. It analyzes audiences on their own devices, thus addressing scalability and privacy issues, and runs at up to 30 fps on a Raspberry Pi. The proposed face orientation detection algorithm is extremely simple, efficient, and able to estimate the head pose in two degrees of freedom, horizontal and vertical. The proposed Eye Aspect Ratio (EAR) with simple adaptive threshold demonstrated a significant improvement in terms of false positives and overall accuracy compared to the existing constant threshold method. Additionally, the algorithms are implemented and open sourced as a toolkit with modular, cross-platform MediaPipe Calculators and Graphs so that users can easily create custom solutions for a variety of purposes and devices. |
| first_indexed | 2024-03-11T09:16:00Z |
| format | Article |
| id | doaj.art-65510c3abda94c80b55d56977e433a1a |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-11T09:16:00Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-65510c3abda94c80b55d56977e433a1a2023-11-16T18:37:33ZengMDPI AGAlgorithms1999-48932023-02-011628610.3390/a16020086Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on EdgeSaw Thiha0Jay Rajasekera1Digital Business and Innovations, Tokyo International University, Saitama 350-1197, JapanDigital Business and Innovations, Tokyo International University, Saitama 350-1197, JapanThe rapid expansion of video conferencing and remote works due to the COVID-19 pandemic has resulted in a massive volume of video data to be analyzed in order to understand the audience engagement. However, analyzing this data efficiently, particularly in real-time, poses a scalability challenge as online events can involve hundreds of people and last for hours. Existing solutions, especially open-sourced contributions, usually require dedicated and expensive hardware, and are designed as centralized cloud systems. Additionally, they may also require users to stream their video to remote servers, which raises privacy concerns. This paper introduces scalable and efficient computer vision algorithms for analyzing face orientation and eye blink in real-time on edge devices, including Android, iOS, and Raspberry Pi. An example solution is presented for proctoring online meetings, workplaces, and exams. It analyzes audiences on their own devices, thus addressing scalability and privacy issues, and runs at up to 30 fps on a Raspberry Pi. The proposed face orientation detection algorithm is extremely simple, efficient, and able to estimate the head pose in two degrees of freedom, horizontal and vertical. The proposed Eye Aspect Ratio (EAR) with simple adaptive threshold demonstrated a significant improvement in terms of false positives and overall accuracy compared to the existing constant threshold method. Additionally, the algorithms are implemented and open sourced as a toolkit with modular, cross-platform MediaPipe Calculators and Graphs so that users can easily create custom solutions for a variety of purposes and devices.https://www.mdpi.com/1999-4893/16/2/86androidblinkcross-platformedge computingeye aspect ratioface orientation |
| spellingShingle | Saw Thiha Jay Rajasekera Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge Algorithms android blink cross-platform edge computing eye aspect ratio face orientation |
| title | Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge |
| title_full | Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge |
| title_fullStr | Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge |
| title_full_unstemmed | Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge |
| title_short | Efficient Online Engagement Analytics Algorithm Toolkit That Can Run on Edge |
| title_sort | efficient online engagement analytics algorithm toolkit that can run on edge |
| topic | android blink cross-platform edge computing eye aspect ratio face orientation |
| url | https://www.mdpi.com/1999-4893/16/2/86 |
| work_keys_str_mv | AT sawthiha efficientonlineengagementanalyticsalgorithmtoolkitthatcanrunonedge AT jayrajasekera efficientonlineengagementanalyticsalgorithmtoolkitthatcanrunonedge |