Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network
The rapid development of deep-learning-based edge artificial intelligence applications and their data-driven nature has led to several research issues. One key issue is the collaboration of the edge and cloud to optimize such applications by increasing inference speed and reducing latency. Some rese...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8371 |
| _version_ | 1827645509331845120 |
|---|---|
| author | Paul P. Oroceo Jeong-In Kim Ej Miguel Francisco Caliwag Sang-Ho Kim Wansu Lim |
| author_facet | Paul P. Oroceo Jeong-In Kim Ej Miguel Francisco Caliwag Sang-Ho Kim Wansu Lim |
| author_sort | Paul P. Oroceo |
| collection | DOAJ |
| description | The rapid development of deep-learning-based edge artificial intelligence applications and their data-driven nature has led to several research issues. One key issue is the collaboration of the edge and cloud to optimize such applications by increasing inference speed and reducing latency. Some researchers have focused on simulations that verify that a collaborative edge–cloud network would be optimal, but the real-world implementation is not considered. Most researchers focus on the accuracy of the detection and recognition algorithm but not the inference speed in actual deployment. Others have implemented such networks with minimal pressure on the cloud node, thus defeating the purpose of an edge–cloud collaboration. In this study, we propose a method to increase inference speed and reduce latency by implementing a real-time face recognition system in which all face detection tasks are handled on the edge device and by forwarding cropped face images that are significantly smaller than the whole video frame, while face recognition tasks are processed at the cloud. In this system, both devices communicate using the TCP/IP protocol of wireless communication. Our experiment is executed using a Jetson Nano GPU board and a PC as the cloud. This framework is studied in terms of the frame-per-second (FPS) rate. We further compare our framework using two scenarios in which face detection and recognition tasks are deployed on the (1) edge and (2) cloud. The experimental results show that combining the edge and cloud is an effective way to accelerate the inferencing process because the maximum FPS achieved by the edge–cloud deployment was 1.91× more than the cloud deployment and 8.5× more than the edge deployment. |
| first_indexed | 2024-03-09T18:40:15Z |
| format | Article |
| id | doaj.art-913b9492e5ca48f9a3163570702a0976 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:40:15Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-913b9492e5ca48f9a3163570702a09762023-11-24T06:47:02ZengMDPI AGSensors1424-82202022-11-012221837110.3390/s22218371Optimizing Face Recognition Inference with a Collaborative Edge–Cloud NetworkPaul P. Oroceo0Jeong-In Kim1Ej Miguel Francisco Caliwag2Sang-Ho Kim3Wansu Lim4Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaDepartment of Aeronautics, Mechanical and Electronic Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaDepartment of Aeronautics, Mechanical and Electronic Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaDepartment of Industrial Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaDepartment of Aeronautics, Mechanical and Electronic Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaThe rapid development of deep-learning-based edge artificial intelligence applications and their data-driven nature has led to several research issues. One key issue is the collaboration of the edge and cloud to optimize such applications by increasing inference speed and reducing latency. Some researchers have focused on simulations that verify that a collaborative edge–cloud network would be optimal, but the real-world implementation is not considered. Most researchers focus on the accuracy of the detection and recognition algorithm but not the inference speed in actual deployment. Others have implemented such networks with minimal pressure on the cloud node, thus defeating the purpose of an edge–cloud collaboration. In this study, we propose a method to increase inference speed and reduce latency by implementing a real-time face recognition system in which all face detection tasks are handled on the edge device and by forwarding cropped face images that are significantly smaller than the whole video frame, while face recognition tasks are processed at the cloud. In this system, both devices communicate using the TCP/IP protocol of wireless communication. Our experiment is executed using a Jetson Nano GPU board and a PC as the cloud. This framework is studied in terms of the frame-per-second (FPS) rate. We further compare our framework using two scenarios in which face detection and recognition tasks are deployed on the (1) edge and (2) cloud. The experimental results show that combining the edge and cloud is an effective way to accelerate the inferencing process because the maximum FPS achieved by the edge–cloud deployment was 1.91× more than the cloud deployment and 8.5× more than the edge deployment.https://www.mdpi.com/1424-8220/22/21/8371deep learningedge–cloudface recognitionreal-timeTCP/IP |
| spellingShingle | Paul P. Oroceo Jeong-In Kim Ej Miguel Francisco Caliwag Sang-Ho Kim Wansu Lim Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network Sensors deep learning edge–cloud face recognition real-time TCP/IP |
| title | Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network |
| title_full | Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network |
| title_fullStr | Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network |
| title_full_unstemmed | Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network |
| title_short | Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network |
| title_sort | optimizing face recognition inference with a collaborative edge cloud network |
| topic | deep learning edge–cloud face recognition real-time TCP/IP |
| url | https://www.mdpi.com/1424-8220/22/21/8371 |
| work_keys_str_mv | AT paulporoceo optimizingfacerecognitioninferencewithacollaborativeedgecloudnetwork AT jeonginkim optimizingfacerecognitioninferencewithacollaborativeedgecloudnetwork AT ejmiguelfranciscocaliwag optimizingfacerecognitioninferencewithacollaborativeedgecloudnetwork AT sanghokim optimizingfacerecognitioninferencewithacollaborativeedgecloudnetwork AT wansulim optimizingfacerecognitioninferencewithacollaborativeedgecloudnetwork |