The focus of this research is to study how targets can be more faithfully detected in a multi-camera CCTV network system using spectral feature for the detection. The objective of the work is to develop colour constancy (CC) methodology to help maintain the spectral feature of the scene into a constant stable state irrespective of variable illuminations and camera calibration issues. Unlike previous work in the field of target detection, two versions of CC algorithms have been developed during the course of this work which are capable to maintain colour constancy for every image pixel in the scene: 1) a method termed as Enhanced Luminance Reflectance CC (ELRCC) which consists of a pixel-wise sigmoid function for an adaptive dynamic range compression, 2) Enhanced Target Detection and Recognition Colour Constancy (ETDCC) algorithm which employs a bidirectional pixel-wise non-linear transfer PWNLTF function, a centre-surround luminance enhancement and a Grey Edge white balancing routine. The effectiveness of target detections for all developed CC algorithms have been validated using multi-camera ‘Imagery Library for Intelligent Detection Systems’ (iLIDS), ‘Performance Evaluation of Tracking and Surveillance’ (PETS) and ‘Ground Truth Colour Chart’ (GTCC) datasets. It is shown that the developed CC algorithms have enhanced target detection efficiency by over 175% compared with that without CC enhancement. The contribution of this research has been one journal paper published in the Optical Engineering together with 3 conference papers in the subject of research.

The focus of this research is to study how targets can be more faithfully detected in a multi-camera CCTV network system using spectral feature for the detection. The objective of the work is to develop colour constancy (CC) methodology to help maintain the spectral feature of the scene into a constant stable state irrespective of variable illuminations and camera calibration issues. Unlike previous work in the field of target detection, two versions of CC algorithms have been developed during the course of this work which are capable to maintain colour constancy for every image pixel in the scene: 1) a method termed as Enhanced Luminance Reflectance CC (ELRCC) which consists of a pixel-wise sigmoid function for an adaptive dynamic range compression, 2) Enhanced Target Detection and Recognition Colour Constancy (ETDCC) algorithm which employs a bidirectional pixel-wise non-linear transfer PWNLTF function, a centre-surround luminance enhancement and a Grey Edge white balancing routine. The effectiveness of target detections for all developed CC algorithms have been validated using multi-camera ‘Imagery Library for Intelligent Detection Systems’ (iLIDS), ‘Performance Evaluation of Tracking and Surveillance’ (PETS) and ‘Ground Truth Colour Chart’ (GTCC) datasets. It is shown that the developed CC algorithms have enhanced target detection efficiency by over 175% compared with that without CC enhancement. The contribution of this research has been one journal paper published in the Optical Engineering together with 3 conference papers in the subject of research.

No description available.

This research evaluates crime prevention effects/impact of open-street closed circuit television (CCTV) surveillance systems as installed in the selected areas (research sites) of the cities of Johannesburg and Tshwane in the Gauteng Province of South Africa on crimes occurring in these surveilled areas. Currently, CCTV surveillance systems are a common sight in many of the urban areas of South Africa.The principal aim of this study was to explore the evaluation of CCTV for crime prevention, reduction and control. The results show that, despite a lack of empirical evidence as to the value of CCTV surveillance systems in preventing or reducing crime, there is strong public support for these systems and that the foundation for much of this support lies in the perceptions/feelings of members of the public of greater safety generated in areas with CCTV coverage. The method of sampling used was a purposive non-probability sampling approach. Participants were selected for interviews based on their knowledge and experience of CCTV systems. The results show that, despite this lack of empirical evidence, CCTV appears to be a viable option for crime prevention and control when integrated with evidence-based strategies rather than as a stand-alone tactic in order to achieve crime control benefits. / Criminology and Security Science / M. Tech. (Security Management)

The issue approached in this study is the possible gaps in cybersecurity in the Closed-Circuit TV system (CCTV) currently being implemented in Jamaica. During 2018, the government of Jamaica together with systems developers from MSTech Solutions developed and started to implement a video surveillance system with the aim to cover the entire nation to reduce criminal activities and create a safer society. To address potential problems of cybersecurity in this system, the purpose of this study was to explore which cybersecurity domains and factors were the most important in the JamaicaEye project. In order to examine such a purpose, the cybersecurity of the system is put into contrast with the cybersecurity domains of the C2M2 model to unveil similarities and differences in cybersecurity strategy and application. To be able to collect in-depth data of the JamaicaEye project, a hybrid of a field-and a case- study took place in Ocho Rios, Jamaica, during approximately 9 weeks. Data collection was carried out through interviews with representatives from the Jamaican government and the systems developer, MSTech Solutions. After compiling and transcribing the collected data from the interview the color coding and comparison of the results with the cybersecurity capability maturity model, C2M2, started. The C2M2 model was chosen as the theoretical framework for this study. The results of mapping the theoretical data with the empirical data gave underlying material and a perspective on the most important cybersecurity factors in the JamaicaEye system. This study will be a foundation for future expansion of the project in Jamaica, but also similar projects in other nations that are in need for cybersecurity development, management and assessment. Mainly, this study will be useful for those in the industry of development, analysis and assessment, and cybersecurity of CCTV systems.