Ranko Petrovic
@vlatacominstitute.com
Vlatacom Institute
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Networks and Communications, Information Systems, Human-Computer Interaction, Electrical and Electronic Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Nemanja Ilić, Dejan Dašić, Miljan Vučetić, Aleksej Makarov, and Ranko Petrović
Elsevier BV
Stefan Stankovic, Zoran Cica, Dejan Drajic, Ranko Petrovic, and Miroslav Peric
IEEE
At the present times, many companies are engaged in the development and implementation of customized solutions for secure communication and traffic encryption. One such device comprising multiple subsystems is being developed at the Vlatacom Institute. One of its main subsystems is the routing system that supports GRE tunneling. The GRE tunneling solution should be absolutely safe and implemented on low-cost hardware. This paper presents an implementation of GRE tunnel support on low-cost routing system on module (SoM) which is under development.
Ranko Petrovic, Dejan Simic, Zoran Cica, Dejan Drajic, Marko Nerandzic, and Dejan Nikolic
MDPI AG
This paper explores the challenges and constraints when over the horizon (OTH) maritime surveillance service utilizes an Internet of Things (IoT) as its backbone. The service is based on High Frequency Surface Wave Radars (HFSWRs) and relies on a satellite communication network as its communication infrastructure in harsh environments. The complete IoT OTH maritime surveillance network is currently deployed in the Gulf of Guinea, which due to its tropical climate represents an unfavorable environment for sensors and communications. In this paper, we have examined the service performance under various meteorological conditions specific to the Gulf of Guinea. To the best of our knowledge, this is the first analysis of IoT OTH maritime surveillance service in equatorial environment. Our analysis aims to mathematically describe the impact of harsh weather conditions on the performance of the service in order to mitigate it with careful overall system design and provide constant quality of the service. Analyses presented in the paper show that average service latency is about 90 s, but it can rise to about 120 s, which is used as a key information during the sensor data fusion algorithm design. Validity of the analyses is demonstrated through high quality of service with an outage probability of just 0.1% in the driest months up to the 0.7% in the rainiest months. The work presented here can be used as a guideline for deployment of maritime surveillance service solutions in other equatorial regions. Moreover, the gained experience presented in this paper will significantly facilitate future expansions of the existing maritime surveillance network with more HFSWRs. This will be done in such a way that it will not affect the quality of service of the entire system on a large scale.
Ranko Petrovic, Dejan Simic, Stefan Stankovic, and Miroslav Peric
IEEE
Although the development and implementation of IoT systems is a very popular area in education, there is a perception that still not enough attention is devoted to the security of IoT systems, especially in a practical manner. This is especially important for the utilization of IoT in mission-critical applications that demand a high level of security. Accordingly, in this paper, an IoT educational platform for testing security vulnerabilities of IoT systems is presented. During the professional internship, students will get familiar, in a practical way, with the ease of address resolution protocol (ARP) spoofing attack, using the proposed educational platform. Also, students will simultaneously learn defense mechanisms.
Snezana Puzovic, Ranko Petrovic, Milos Pavlovic, and Srdan Stankovic
IEEE
Images in bad weather can be degraded by scattering atmospheric particles, and suffer from low contrast and faint color. Main focus of this work is on dehazing methods that can be used for low-light and low-contrast conditions. Dehazing algorithms can be applied to low-light (night) imaging in a way that inverted night images are considered as hazy images. Different image quality metrics are used to measure quality of image enhancement algorithm. Since it is not easy to obtain original image without haze, special attention is given to the no-reference metrics that evaluate image contrast enhancement.
Ranko Petrovic, Dejan Simic, Dejan Drajic, Zoran Cica, Dejan Nikolic, and Miroslav Peric
MDPI AG
The steady increase of the world population and economy leads to an increase in both types and amounts of goods transported over seas, which further inevitably leads to an increase of criminal activities in the maritime arena. In order to stifle criminal activities nations are forced to develop sophisticated sensor networks. The backbone of any sensor network is a communication network which connects all sensors with the command centers, most often located hundreds of kilometers away from the sensors. In developing countries, communication networks are very often poorly developed, leaving only satellite links as somewhat reliable means of communication. Henceforth, in this paper, a laboratory for the Internet of Things (IoT) communication infrastructure environment designed to facilitate maritime sensor network design process in areas where communication network is dependent on data transfer over satellite links is presented. In order to successfully describe and develop a laboratory for IoT communication infrastructure environment, necessary data are collected during the design and deployment of a maritime surveillance network in the Gulf of Guinea. The main advantage of the proposed laboratory environment is the inclusion of satellite link simulation in the IoT laboratory environment. This feature provides an opportunity to cover a much broader scope of IoT solutions compared to other IoT laboratories.
Nikola Latinović, Tijana Vuković, Ranko Petrović, Miloš Pavlović, Marko Kadijević, Ilija Popadić, and Mladen Veinović
Centre for Evaluation in Education and Science (CEON/CEES)
Face detection systems with color cameras were rapidly evolving and have been well researched. In environments with good visibility they can reach excellent accuracy. But changes in illumination conditions can result in performance degradation, which is the one of the major limitations in visible light face detection systems. The solution to this problem could be in using thermal infrared cameras, since their operation doesn't depend on illumination. Recent studies have shown that deep learning methods can achieve an impressive performance on object detection tasks, and face detection in particular. The goal of this paper is to find an effective way to take advantages from thermal infrared spectra and provide an analysis of various image degradation influence on thermal face detection performance in a system based on R-CNN with special accent on implementation on a hardware platform for video signal processing that institute Vlatacom has developed, called vVSP.
Tijana Vukovic, Ranko Petrovic, Milos Pavlovic, and Srdan Stankovic
IEEE
Visible light face detection systems have been well researched and in controlled environments can reach excellent accuracy. Variation in illumination conditions results in performance degradation and illumination is the one of the major limitations in visible light face detection systems. Using thermal infrared cameras one can provide a solution to this problem. Recent studies show that deep learning approaches can achieve impressive performance on object detection tasks, and face detection in particular. The goal of this paper is to find an effective way to take advantages from thermal IR spectra and provide a comparative analysis of various image degradation influence on thermal face detection performance in a system based on R-CNN.
Milos Pavlovic, Branka Stojanovic, Ranko Petrovic, Snezana Puzovic, and Srdjan Stankovic
National Library of Serbia
The main problem for modern visible light face recognition has been accurate identification under variable environmental conditions. Thermal infrared facial images utilization in face recognition systems can provide a solution for problems related to uncontrolled environmental conditions, especially to those caused by illumination limitations. This paper compares the results of the use of visible light and thermal infrared imagery for face recognition based on the HOG feature descriptor. In particular, the paper suggests an optimal HOG cell to image size ratio in order to improve recognition accuracy and reduce computational complexity. Performance statistics are presented on facial images with different facial expressions. The obtained results support the conclusion that recognition with thermal infrared images is more robust and that fusion of sensors should be included for improving recognition accuracy.
Ranko Petrovic, Branka Stojanovic, Milos Pavlovic, Snezana Puzovic, and Srdan Stankovic
IEEE
The utilization of a thermal band imaging sensor with aim to overcome the disadvantages of visible light face recognition systems, such as variation in lighting conditions, has become more popular in wide range of security and safety applications. Thermal imaging sensor enhances reliability of face recognition systems under different lighting conditions, including complete darkness. However, thermal imagery also possesses several disadvantages such as usual presence of noise, originating both from sensor and environment. This paper examines the influence of thermal imagery noise on face recognition performance in thermal-to-thermal face recognition applications.
Milos Pavlovic, Branka Stojanovic, Ranko Petrovic, and Srdan Stankovic
IEEE
Visible light face recognition systems have been well researched and in controlled environments can reach excellent accuracy. Variation in lighting conditions results in performance degradation and illumination is the one of the major limitations in visible light face recognition systems. Using infrared facial images can provide a solution to this problem. Nearly invariant to changes in illumination, thermal IR imagery provides ability for recognition under all lighting conditions, including complete darkness. The system proposed in this paper takes advantages from both spectra and provides an effective algorithm for illumination invariant face recognition system.
Branka Stojanovic, Snezana Puzovic, Natasa Vlahovic, Ranko Petrovic, and Srdan Stankovic
IEEE
Video enhancement algorithms in long-range multi-sensor surveillance systems are of great importance. Infrared sensors typically suffer from blur and noise originating from sensors and their environment. This paper proposes a real-time infrared imaging enhancement algorithm, applicable to multiple sensor types. The research presented in this paper is introductory for developing smart, adaptive, machine learning based enhancement systems.
Katarina Knezevic, Emilija Mandic, Ranko Petrovic, and Branka Stojanovic
IEEE
Face recognition is still one of the most popular biometric recognition techniques. It is widely used, both online and offline. Performance of such a system is directly connected to face image quality. Since blur and motion blur are common imagery problems, this paper explores the influence of such disturbances on the face recognition performance. The research described in this paper compares the performance of the face recognition algorithm based on the Haar features and Local Binary Patterns Histograms when it uses face images of a good quality, images with added Gaussian blur and motion blur, as well as enhanced images.
Aleksandar Valjarevic, Hein Venter, and Ranko Petrovic
IEEE
In order for digital evidence from a digital forensic investigation to be admissible, one needs to follow a formalised and ideally standardised process. The authors' previous research and initiative within ISO resulted in a new international standard ISO/IEC 27043:2015, titled “Information technology — Security techniques — Incident investigation principles and processes” as published in March 2015. The standard governs the digital forensic investigation process and covers it from a wide angle, while harmonising existing process models in this field. In this paper, the authors give an analysis of both the standard itself and of related standards so as to enable the reader to understand the ecosystem of standards relating to the digital forensic investigation process and role of ISO/IEC 27043:2015.
Ranko Petrović, Dejan Simić, Stefan Stanković, and Miroslav Perić
IEEE
Educational platforms are generally of great importance in the education process of students of technical sciences, because the increase of their practical knowledge is enabled through the experimental work. Such platforms are even more significant when considering highly specialized systems, such as IoT systems that rely on satellite link communication, because training courses at real systems in these cases are impractical for many reasons. One example of these educational platforms was developed and implemented at the Vlatacom Institute for the needs of technical sciences students during their mandatory internship. The aim of this specific educational platform is to provide the possibility to examine the influence of the simulated satellite link on overall communication inside of different IoT systems.