PTZ-Surveillance coverage based on artificial intelligence for smart cities

https://doi.org/10.1016/j.ijinfomgt.2019.04.017Get rights and content

Highlights

  • An improved soft computing algorithm proposed for optimizing the area coverage percentage of MWSN.

  • The proposed algorithm is validated using the benchmark problems addressed in the literature.

  • Results proved the effectiveness of the proposed algorithm.

Abstract

Surveillance cameras have a plethora of usages in newly born cities including smart traffic, healthcare, monitoring, and meeting security needs. One of the most famous new cites is the Egypt's new administration capital “New Cairo”. The new administration capital of Egypt mainly characterizes with the green life style via the "Green River ". In this paper, a new enhanced Artificial Intelligence (AI) algorithm is introduced for adjusting the orientation of Pan–Tilt–Zoom (PTZ) surveillance cameras in new Cairo. In other words, the new proposed algorithm is used for improving the field of view (FOV) coverage of PTZ cameras network. For validating the proposed algorithm, it is tested on many scenarios with different criterions. After that, the proposed algorithm is applied to adjust the PTZ monitoring cameras in the green river which locates on new administrative capital as an equivalent to the river Nile. In addition, it compared with several other AI algorithms through the appropriate statistical analysis. The overall experimental results indicate the prosperity of the proposed algorithm for increasing the coverage of the PTZ surveillance system.

Introduction

The wave of technological development has swept through our world until most of the modern residential cities have become smart cities characterized by automation and intelligence. The smart city can be defined as a high-level ontology that describes the semantic categories including a series of innovations in urban systems sustained by broadband networks, sensors, data management technologies, software applications and e-services (Komninos & Mora, 2018). Roughly speaking, the smartness of the city is determined by the Structure and Functions of its Semiotics (Data, Information, Knowledge) management system. So, these functions can be summarized as (Ramaprasad, Sánchez-Ortiz, & Syn, 2017):Functions[Sense,Monitor,Process,Translate,Comunicate]

Therefore, one of the most important pillars of such a smart urban is the surveillance systems so-called image sensors/camera networks, which can be considered vision organs of the smart city.

Network cameras are used in smart cities across the globe for monitoring, surveillance and other security needs. Due to the Internet of Things (IoT) comes to life; they extend well beyond simple surveillance tasks to other application scenarios. There are several types of cameras which differ in servo capabilities, sensor element, lens type, etc. In general, they can be categorized into three main types (Erdem & Sclaroff, 2006): Fixed Perspective, Omni-directional, and Pan-Tilt-Zoom (PTZ) cameras. The former has a fixed position, orientation, and focal length. The second has a full 2π horizontal coverage but it has a small focal length which may cause undesirable lens aberration effects. The last type of cameras (PTZ) is adjustable in a predefined range. They can be rotated horizontally and vertically around their (Tilt) and (Pan) axis respectively. Also, some PTZ cameras have an adjustable focal length (Zoom).

The cameras network become an essential component of a city cloud computing center for a variety of its services ranging from safety and security to green environmental solutions. These cameras are not in direct communication with the main cloud center but are controlled by and work through what called Fog computing. Fog computing (Eldrandaly, Abdel-Basset, & Shawky, 2019; Sodhro, Luo, Sangaiah, & Baik, 2019) is the practice of real-time data processing near the edge of the network, where the data is generated, instead of processing data in a centralized warehouse. Thus, cameras network take their instruction and adjustment from this edge computing. In addition, fog computing supports the employment of artificial intelligence for enhancing the performance of cameras systems (See Fig. 1).

In this paper, a new improved AI algorithm called "Enhanced FireFly Algorithm (EFA)" is proposed. EFPA is used to enhance the coverage of PTZ cameras network by altering the orientation of them. Many experiments on different scenarios are made and the overall results indicated the efficiency of the proposed algorithm. The present paper has many exclusive contributions, as follows:

  • An Enhanced FA (EFA) is proposed for solving area coverage problem of cameras network.

  • For the first time in literatures, the new administrative capital of Egypt is highlighted.

  • An optimization-based surveillance system is introduced for the constructed part of the Green River in Egypt.

The remaining paper structure is as go behinds: Section 2 represents a literature survey, the problem is defined in Section 3, the methodology is showed in Sections 4, 5 depicts the results of the proposed algorithm, the application of EFA on the Green River is represented in Section 6. Finally, in Section 7, the conclusions and future works are given.

Section snippets

Literature review

Several researches have been proposed from time to time in order to enhance the citizen's life in smart cities. For instance, the authors (Hashem et al., 2016) introduced a comprehensive study of the rule of Big Data (BD) (Oussous, Benjelloun, Lahcen, & Belfkih, 2018) in smart cities. In addition, the authors proposed a reference business model of big data for smart cities. In (Koo, Yoo, Lee, & Zanker, 2016; Yuan, Xu, Qian, & Li, 2016), the authors handling the technology of smart tourism

Problem definition

The camera network ROI coverage optimization can be defined as using fewest possible cameras to monitor/inspect a fixed area or maximizing the ROI coverage of a network with a fixed number of cameras. The coverage problem can be divided into three subcategories: point coverage, barrier coverage, and area coverage (Cardei & Wu, 2004; Gage, 1993; Ramsden, 2009). The point coverage problem, the objective is to cover a set of target points. The barrier coverage aims to correctly identify intruders

Firefly Algorithm (FA)

Firefly Algorithm (FA) (Yang, 2008, 2009) was inspired by the behaviour of flashing fireflies. i.e. FA focuses on the firefly observation of light at its position when trying to move to a greater light-source than its own. Besides, the following rules should be considered:

  • 1)

    For all fireflies, their sex is neglected.

  • 2)

    Firefly attracts to another firefly that is brighter than it.

  • 3)

    The solution fitness is determined by the firefly brightness.

The formulation of FA is based on a physical formula of light

Validation experiments & results

In this subsection, firstly the proposed algorithm is tested on many datasets that represented in Table 1. Secondly, EFA is applied in a selected practical case study. All the algorithms are coded in MATLAB© 2015. All experiments are carried out on a 64-bit operating system with a 2.60 GHz CPU and 6 GB RAM. EFA is tested on the four constructed datasets and compared with Particle Swarm Optimization (PSO) (Xu et al., 2011), Differential Evolution (DE) (Storn & Price, 1997), Whale Optimization

Case study: “the Green River in the new administrative capital in Egypt”

Egypt is entering a new smartness and technological century via releasing its new administrative capital "New Cairo". The New Capital Cairo is a new smart city that has been constructed to be an extension of the current capital. It extends 45 Km away from Cairo and 60 Km from Suez city. The city is destined to host 7 million inhabitants on a total area of 170,000 acres / 714 Km2 that making it larger than Washington D.C (CUBE, 2018). The new smart city will contain 100 districts that will host

Conclusions

The quality of any surveillance system is determined by the coverage of the cameras network consolidation. This paper proposes a new enhanced AI algorithm in order to optimize the coverage of PTZ cameras network. In particular, the original FA algorithm is hybrid with chaotic Lozi map and the mechanism of attractive search space border points. In Addition, the determination of coverage percentage is performed by grid-based separation of ROI. This method of calculating the solution fitness is

References (65)

  • R.A. Nyberg

    Using ‘smartness’ to reorganise sectors: Energy infrastructure and information engagement

    International Journal of Information Management

    (2018)
  • A.M.S. Osman

    A novel big data analytics framework for smart cities

    Future Generation Computer Systems

    (2019)
  • A. Oussous et al.

    Big data technologies: A survey

    Journal of King Saud University-Computer and Information Sciences

    (2018)
  • J.H. Park et al.

    An analysis of the utilization of Facebook by local Korean governments for tourism development and the network of smart tourism ecosystem

    International Journal of Information Management

    (2016)
  • O. Rahbari et al.

    A novel state of charge and capacity estimation technique for electric vehicles connected to a smart grid based on inverse theory and a metaheuristic algorithm

    Energy

    (2018)
  • A.H. Sodhro et al.

    Mobile edge computing based QoS optimization in medical healthcare applications

    International Journal of Information Management

    (2019)
  • H. Yuan et al.

    Make your travel smarter: Summarizing urban tourism information from massive blog data

    International Journal of Information Management

    (2016)
  • R. Zafar et al.

    Prosumer based energy management and sharing in smart grid

    Renewable and Sustainable Energy Reviews

    (2018)
  • O. Arslan et al.

    Voronoi-based coverage control of pan/tilt/zoom camera networks

    2018 IEEE International Conference on Robotics and Automation (ICRA)

    (2018)
  • C. Blum et al.

    Metaheuristics in combinatorial optimization: Overview and conceptual comparison

    ACM Computing Surveys (CSUR)

    (2003)
  • M. Cardei et al.

    Coverage in wireless sensor networks

    Handbook of Sensor Networks

    (2004)
  • F.T. Chan et al.

    Global supplier selection: a fuzzy-AHP approach

    International Journal of Production Research

    (2008)
  • O. Cosido et al.

    Automatic calculation of bicycle routes by combining meta-heuristics and GIS techniques within the framework of smart cities

    New Concepts in Smart Cities: Fostering Public and Private Alliances (SmartMILE)

    (2013)
  • CUBE

    The capital Cairo

    (2018)
  • R.L. Devaney

    One-dimensional dynamics

    An introduction to chaotic dynamical systems

    (2018)
  • R.C. Eberhart et al.

    A new optimizer using particle swarm theory

    Proceedings of the sixth international symposium on micro machine and human science

    (1995)
  • K.A. Eldrandaly et al.

    Internet of spatial things: A new reference model with insight analysis

    IEEE Access

    (2019)
  • R.C. Elston

    Fisher’s influence on me

    Genetic Epidemiology

    (2018)
  • U.M. Erdem et al.

    Optimal placement of cameras in floorplans to satisfy task requirements and cost constraints

    OMNIVIS workshop

    (2004)
  • D.W. Gage

    Sensor abstractions to support many-robot systems

    Mobile Robots VII. International Society for Optics and Photonics

    (1993)
  • A. Gellert et al.

    A study on forecasting electricity production and consumption in smart cities and factories

    International Journal of Information Management

    (2019)
  • N.C. Giri

    Some applications of analysis of variance

    Introduction to Probability and Statistics

    (2019)
  • Cited by (34)

    • Hybrid Computational Intelligence Algorithm for Autonomous Handling of COVID-19 Pandemic Emergency in Smart Cities

      2022, Sustainable Cities and Society
      Citation Excerpt :

      As the optimal-exact solution methods are exhaustive cost consumption methods, most of the proposed literature moves to the exploitation of near-optimal inspired solution methods or so-called metaheuristics. For instance, CI algorithms have been used in smart surveillance (Eldrandaly et al., 2019), smart home energy management (Kong et al., 2020), the evaluation of hybrid microgrid configurations (Haidar et al., 2020, Bagheri et al., 2020), energy-efficient fog computing (Reddy et al., 2020), smart healthcare (Ding et al., 2020), and smart agriculture (Abdel-Basset et al., 2020). As a consequence, CI algorithms are very suitable for optimizing the robot functions of movement, recognizing patients, and analyzing samples.

    • Real-time smart garbage bin mechanism for solid waste management in smart cities

      2021, Sustainable Cities and Society
      Citation Excerpt :

      With advancements in technology, a smart city requires many applications for providing services to the residents. The major applications include: smart health (Pramanik, Lau, Demirkan & Azad, 2017), smart surveillance and security (Eldrandaly, Abdel-Basset & Abdel-Fatah, 2019), smart traffic management and control (Rizwan, Suresh & Babu, 2016), smart environment monitoring (Ullo & Sinha, 2020), smart farming (Dagar et al., 2018) and many other many applications (Guerra et al., 2020;Javadzadeh et al., 2020). From the smart cities applications and literature review, big data and data analysis is required in development of these applications (Ahmad et al., 2020; Melakessou, Kugener, Alnaffakh, Faye & Khadraoui, 2020).

    • How can artificial intelligence enhance car manufacturing? A Delphi study-based identification and assessment of general use cases

      2021, International Journal of Information Management
      Citation Excerpt :

      Car manufacturing as well as AI can look back at a decades-long history and tradition. But whereas the industry associated with the former is currently being shaken to an unprecedented extent due to new disruptive trends like e-mobility (Lehmann & Kuhn, 2019), connectivity, or autonomous driving (Mocker & Fonstad, 2017), and additionally the global COVID-19 pandemic (Bunker, 2020; Coombs, 2020; Dwivedi, Hughes et al., 2020; Sipior, 2020), the latter is once again experiencing a sudden boom (Abubakar, Behravesh, Rezapouraghdam, & Yildiz, 2019; Dwivedi et al., 2019; Eldrandaly, Abdel-Basset, & Abdel-Fatah, 2019; Gursoy, Chi, Lu, & Nunkoo, 2019). It is therefore not really surprising that many people see AI as a promising means to help the automotive industry through these challenging times, especially in terms of the very complex and cost-intensive production process in that industry (Demlehner & Laumer, 2020a; Luckow et al., 2018).

    • Autonomous vehicles in the smart city era: An empirical study of adoption factors important for millennials

      2021, International Journal of Information Management
      Citation Excerpt :

      The IoT is a key enabler when a company wishes to acquire the benefits of implementing advanced services and functions since the IoT allows data collection and transmission in real time, e.g. the pay-per-use model (Ardolino et al., 2017). Besides that, big data and artificial intelligence have been emphasised in terms of their importance to facilitate the life in smart cities (Eldrandaly, Abdel-Basset, & Abdel-Fatah, 2019) and especially the convergence of all three, i.e. IoT, big data and artificial intelligence, that would enable smarter infrastructure, e.g. mobility, in smart cities (Appio, Lima, & Paroutis, 2019). The interconnectedness of devices and their real-time communication facilitates the so-called concept of smart cities that are built on ICT, the IoT and computer systems (CS) or information systems (IS).

    View all citing articles on Scopus
    View full text