@book{scholars17658,
           pages = {109--127},
           title = {Using artificial intelligence search in solving the camera placement problem},
         journal = {Applications of Computational Intelligence in Multi-Disciplinary Research},
       publisher = {Elsevier},
             doi = {10.1016/B978-0-12-823978-0.00014-9},
            year = {2022},
            note = {cited By 0},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130187483&doi=10.1016\%2fB978-0-12-823978-0.00014-9&partnerID=40&md5=2a5ce50dc306327c706d79a85a548a6f},
        abstract = {Due to the impact of optimal camera placement on the efficiency and the cost of surveillance systems as well as the rapid development in sensor technologies and the pressing security needs, the last two decades witnessed an increasing interest in developing and introducing efficient methods for solving what is known as the camera placement problem. Given some monitoring quality measures coupled with the specifications of the visual sensors in hand, the goal of the camera placement framework is to capitalize the area seen by a set of visual sensors. This problem is considered a discrete optimization problem and is known to have an NP-hard problem complexity. In order to solve the camera placement problem, a crucial fundamental step is modeling the coverage of the cameras in use. Following the coverage modeling, an optimization method needs to be used to locate the optimal poses and/or camera positions. In general, artificial intelligence search strategies are extensively used in solving discrete optimization problems. In particular, this chapter discusses formulating the camera placement problem in order to be solved by artificial intelligence search. Moreover, the chapter applies selective artificial intelligence search strategies to solve the camera placement problem. Most of these search formulations investigate the problem from a greedy-based perspective. Thus the target is to maximize the primary coverage of the camera network. Additionally, the initiation of the camera model and the subsequent coverage table are counted as key steps prior to applying the optimization method. Thus all instances of the camera coverage over the potential locations must be computed and stored in tabular form, usually known as a coverage table. The computation of the coverage table offers essential data to formulate the search space. Furthermore, in order to locate the solution to the problem, each search strategy defines a unique path throughout the search space. However, regardless of the selection of the search technique, the solutions are usually attained by utilizing randomization restart settings. The chapter also carries out an analytical review of three main searching algorithms namely, generate and test, uninformed search, and hill climbing search algorithms. Two case studies are used to evaluate those algorithms, and the camera placement problem is formulated as a coverage maximization problem. The various searching algorithms are implemented to seek the maximum coverage of the camera array. The placement results obtained based on those algorithms are critically compared in terms of the algorithms{\^a}?? efficiency and performance. Finally, the chapter highlights the strengths and weaknesses of each approach. {\^A}{\copyright} 2022 Elsevier Inc. All rights reserved.},
          author = {Altahir, A. A. and Asirvadam, V. S. and Hamid, N. H. B. and Sebastian, P.},
            isbn = {9780128239780; 9780128241769}
}