Big Data and development of smart city: System architecture and practical public safety example

Abstract

The concept of Smart City started its development path around two to three decades ago; it has been mainly influenced and driven by radical changes in technological, social and business environments. Big Data, Internet of Things and Networked Cyber-Physical Systems, together with the concepts of Cloud, Fog and Edge Computing, have tremendous impact on the development of Smart City, reforming its frame and tasks and redefining its requirements and challenges. We consider feasible architectures of the IT infrastructure and signal processing, taking into account aspects of Big Data, followed by summary of benefits and main challenges, like security of infrastructure and private data. As a practical example we present a public safety application of multi-sensor imaging system: a smart device with target detection subsystem based on artificial intelligence used for activation of target tracking. The experiments have been performed in the cities of Abu Dhabi and Belgrade, which have very different environment. The experiments have shown the effects of videostreaming compression on thermal imagers and the importance of distributed processing power that optimizes requirements for amount of transmitted data and delay.

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

“…Assuming that the scale of the at frame x is K(x) * H(x), the target scale pyramid for scale estimation is constructed near the target location with the number of layers B. e scale Q(x, n) for any image slice in the target scale pyramid is expressed as (8). ξ(x) and ζ(x) denote the scale factor of different scale layers.…”

“…Compared with panoramic video multitarget real-time tracking, the research related to panoramic video multitarget real-time tracking is still relatively small, but because it can reflect the real demand of autonomous driving environment perception, it is still in a booming stage of development, and a large number of related new algorithms are constantly proposed [8]. From the technical point of view, panoramic video multitarget real-time tracking needs to consider more frequent interactions and occlusions, and the interaction process is mostly nonregular and random, so it is suitable for the research of multisensor information fusion dual neural network approach.…”

Deep Learning Based SWIR Object Detection in Long-Range Surveillance Systems: An Automated Cross-Spectral Approach

“…Surveillance imaging systems are usually based on visible-light cameras. In addition to visible-light cameras, thermal cameras are most often used for night imaging [ 2 , 3 , 4 , 5 ].…”

The Scandinavian Third Way as a Proposal for Sustainable Smart City Development—A Case Study of Aarhus City

“…It is now emerging as a new paradigm of smart urban development in which modern technologies and socio-economically sustainable growth play a special role [2,3]. On the basis of the smart city concept, attempts are being made to deal with such contemporary urban challenges as, for example, air pollution [4,5] and increased water [6][7][8] and energy consumption [9][10][11][12], as well as waste disposal problems [13,14], traffic problems [15][16][17], and an increase in crime [18]. Moreover, with the digital means used by smart cities there are growing hopes of strengthening civic control over political urban life and consolidating grassroots democracy; citizens eventually gain access to simple tools by means of which they can participate in decisionmaking processes concerning issues that directly affect their mode and place of life [19].…”