A Face Recognition System Based on Cloud Computing and AI Edge for IOT
With the demand for interconnection of all things, more and more kinds of sensors are connected to the Internet of Things. Different from traditional sensors, such as low transmission frequency and small data volume, visual sensors have the characteristics of high transmission rate and large data volume. Vision sensors are widely used in security, health care and other face recognition. This paper proposes a combination of edge-based artificial intelligence and cloud computing that is suitable for areas such as face recognition and security that require a large number of visual sensors and image processing and analysis. In order to verify the effectiveness of the technical framework proposed in this paper, a complete demonstration system was built at the end of the paper based on the rk3288 and cloud server to prove the excellence of the system described in this paper.
KeywordsFace recognition system AI Edge IOT Cloud computing
This work is partially supported by the technical projects No. 2016YFB1000803, No. 2017YFB1400604, No. 2017YFB0802703, No. 2012FU125Q09, No. 2015B010131008 and No. JSGG20160331101809920.
- 1.Medina, C.A., Perez, M.R., Trujillo, L.C.: IoT paradigm into the smart city vision: a survey. In: 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 21–23 June 2017Google Scholar
- 3.Ericsson: More than 50 billion connected devices. Ericsson white paper, pp. 1–12 (2011)Google Scholar
- 4.Internet of things (IoT) 2013 to 2020 market analysis: Billions of things, trillions of dollars. International Data Corporation, Technical Report (2013)Google Scholar
- 5.Yigitoglu, E., Mohamed, M., Liu, L., Ludwig, H.: Foggy: a framework for continuous automated IoT application deployment in fog computing. In: 2017 IEEE 6th International Conference on AI and Mobile Services, June 2017Google Scholar
- 6.Munaro, M., Basso, F., Menegatti, E.: Tracking people within groups with RGB-D data. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2101–2107, October 2012Google Scholar
- 8.Ess, A., Leibe, B., Schindler, K., Van Gool, L.: A mobile vision system for robust multi-person tracking. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)Google Scholar
- 9.Piatkowska, E., Belbachir, A., Schraml, S., Gelautz, M.: Spatiotemporal multiple persons tracking using dynamic vision sensor. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 35–40, June 2012Google Scholar
- 10.Reverter Valeiras, D., Orchard, G., Ieng, S.H., Benosman, R.B.: Neuromorphic event-based 3D pose estimation. Front. Neurosci. 9(522) (2015)Google Scholar