Analysis of Visual Sensory System based Edge Computing Approach in IOT

被引:0
作者
Simsek, Emrah [1 ]
Ozyer, Baris [1 ]
机构
[1] Ataturk Univ, Bilgisayar Muhendisligi Bolumu, Erzurum, Turkey
来源
29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021) | 2021年
关键词
Internet of Things; Edge Computing; Visual Sensing; Object Detection; INTERNET; THINGS;
D O I
10.1109/SIU53274.2021.9477904
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Internet of Things technologies, have wide application area in daily life with Industry 4.0, interact with artificial intelligence, cloud computing and embedded systems. Internet of Things technology can be used in more comprehensive applications, supported by visual sensory systems. Due to the high processing, storage and communication requirements of visual sensory systems, problem-specific data processing architectures are used in the Internet of Things. Edge Computing means the methods process in the edge of the network instead of the server to reduce data transmission, processing and storage requirements. In this study, the storage, processing and transmission requirements of edge computing-based data processing architectures for the basic problems of visual perception such as object detection and object recognition are analyzed. The solution of the object detection or object recognition problems in the analysis was carried out in different scenarios. In these scenarios, the requirements are determined by sharing the methods used to solve the problem between the server and the IoT device. In the analysis, the requirements for pre and post processing methods, feature extraction methods and classification algorithms are used. According to the analysis results, it has been determined the scenario in image features are transmitted to the servers minimizes the general requirements.
引用
收藏
页数:4
相关论文
共 21 条
[1]   Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications [J].
Al-Fuqaha, Ala ;
Guizani, Mohsen ;
Mohammadi, Mehdi ;
Aledhari, Mohammed ;
Ayyash, Moussa .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2015, 17 (04) :2347-2376
[2]  
[Anonymous], 2005 IEEE COMPUTER S, DOI DOI 10.1109/CVPR.2005.177
[3]   SURF: Speeded up robust features [J].
Bay, Herbert ;
Tuytelaars, Tinne ;
Van Gool, Luc .
COMPUTER VISION - ECCV 2006 , PT 1, PROCEEDINGS, 2006, 3951 :404-417
[4]  
Bonomi F., 2012, P 1 ED MCC WORKSH MO
[5]   BRIEF: Binary Robust Independent Elementary Features [J].
Calonder, Michael ;
Lepetit, Vincent ;
Strecha, Christoph ;
Fua, Pascal .
COMPUTER VISION-ECCV 2010, PT IV, 2010, 6314 :778-792
[6]   Detecting moving objects, ghosts, and shadows in video streams [J].
Cucchiara, R ;
Grana, C ;
Piccardi, M ;
Prati, A .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (10) :1337-1342
[7]   Description of interest regions with local binary patterns [J].
Heikkila, Marko ;
Pietikainen, Matti ;
Schmid, Cordelia .
PATTERN RECOGNITION, 2009, 42 (03) :425-436
[8]  
Jain R., 1995, MACHINE VISION, V5
[9]  
Li SC, 2015, INFORM SYST FRONT, V17, P243, DOI 10.1007/s10796-014-9492-7
[10]  
Lowe D.G., 1999, P 7 IEEE INT C COMP, VVolume 2, P1150, DOI DOI 10.1109/ICCV.1999.790410