Real-time face recognition based on IoT: A comparative study between IoT platforms and cloud infrastructures

Abstract

The use of the Internet of Things (IoT) is steadily increasing in a wide range of applications. Among these applications, safety and security are some of the prominent applications. Through surveillance systems, we can restrict access to our premises and thus secure our assets. Nowadays face detection and recognition enabled surveillance systems are available in the market, which can detect faces from video frames captured using IP cameras, and then recognize those faces by comparing them with existing databases. However, higher prices and low accuracy are impeding the large scale deployment of those systems. In this paper, we have proposed a generic architecture for face detection and recognition system from real-time video frames that have been captured through IP cameras and processed using low-cost IoT devices by utilizing Cloud computing services. We have selected two IoT platforms: Eclipse Mosquitto IoT broker and Kaa IoT middleware to implement our proposed architecture. The face detection part is deployed in the IoT devices and the computation-intensive task, i.e., face recognition is carried out in backend Cloud servers. We have executed our experiments in two different Cloud infrastructures: Core Cloud and Edge Cloud and measured the total processing time in different scenarios. The experimental results show that the performance of the Mosquitto broker in terms of total processing time is better than Kaa middleware. Total processing time can be further reduced by deploying a face recognition application from Core Cloud to Edge Cloud. Furthermore, the k-nearest neighbor algorithm shows promising results compared to other face recognition algorithms.

Embedded intelligence and the data-driven future of application-specific Internet of Things for smart environments

“…87 Bottom-up methods such as voting and stacking are used to take into account the outputs of the local ML models and their combination. 32 concept drifting in incremental learning, 33,34 sliding time windows, 35 federated learning for edge nodes, 36 Singh 37 Nature-inspired algorithms for ASIoTs Taxonomy for nature-inspired algorithms, 38 FPSoC evolutionary computing 39 Coding approaches for ASIoTs IoT coding approaches, 40 Huffman coding, 41 JPEG/ DCT coding, 42 wavelet coding 43 Edge, fog, and cloud computing for ASIoTs IoT edge, fog, cloud platforms, 44,45 workload allocation policy for delay-sensitive IoT using GA, 46 Analytics Everywhere framework 47 Nano things for ASIoTs IoNT architecture, 21,48 nanonetwork transmission policy for human circulatory system, 49 routing protocol for nanoscale networks 50 Embedded intelligence and application requirements for ASIoT Embedded vision and image processing for ASIoTs Multimedia IoT, 51,52 coding standards, 53 compressive sensing, 54 multimedia traffic streams in ASIoTs, 55 IoT platforms and cloud infrastructures, 56 largescale M-IoT, 57 split and combine approach, 58 cooperative M-IoT edge computing framework 59…”

“…55 A major design factor for ASIoTs is to determine which parts of the information processing are required to be performed on the IoT device itself and which parts can be offloaded to the central cloud server to meet the delay and latency requirements. Ahmed et al 56 performed a comparative study between IoT platforms and cloud infrastructures for a real-time face recognition application. In their study, the face recognition task was divided into two sub-tasks (face detection and face classification).…”