Abstract
The Internet of Things has grown quickly in the last few years, with a variety of sensing, processing and storage devices interconnected, resulting in high data traffic. While some sensors such as temperature, or humidity sensors produce a few bits of data periodically, imaging sensors output data in the range of megabytes every second. This raises a complexity for battery operated smart cameras, as they would be required to perform intensive image processing operations on large volumes of data, within energy consumption constraints. By using intelligence partitioning we analyse the effects of different partitioning scenarios for the processing tasks between the smart camera node, the fog computing layer and cloud computing, in the node energy consumption as well as the real time performance of the WVSN (Wireless Vision Sensor Node). The results obtained show that traditional design space exploration approaches are inefficient for WVSN, while intelligence partitioning enhances the energy consumption performance of the smart camera node and meets the timing constraints.
Highlights
This is the era of information and technology, where data from a variety of sensors and devices are merged into products and services for the end user [1,2,3]
The aim of this paper is to analyse aspects related to smart camera node energy consumption and the latency of a WVSN system consisting of node, fog and cloud computing
In our WVSN architecture, in addition to the smart camera node, we considered the presence of fog and cloud computing elements, where the fog layer is allocated in the communication gateway and relies on a Raspberry Pi model 3B+
Summary
This is the era of information and technology, where data from a variety of sensors and devices are merged into products and services for the end user [1,2,3]. Depending on the scope of the application, the cloud can be used as an extensive storage unit for statistical analysis of large volumes of data. It can become part of the processing in the WSN providing real-time support for the sensor and the end user. Our focus lies on the latter, considering the cloud as a computational entity in an IoT application, where the sensor can offload processing tasks and data via the Internet. Segmentation Morphology Detection & Tracking Data Rate SC Fog Cl. The people counting scenario relies on a set of image processing tasks starting with background modelling and subtraction as described in [31]. The resulting binary image is used to detect and count people based on bounding box and Kalman filter methods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
