{"title":"Action Recognition by 3D Convolutional Network","authors":"Matúš Brezovský, Dominik Sopiak, M. Oravec","doi":"10.23919/ELMAR.2018.8534657","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534657","url":null,"abstract":"In this paper we focused on sport action recognition with 3D convolutional network. We executed two different experiments. In the first experiment we distinguished two similar activities: running and walking. The experiment proved that 3D convolutional network is able to learn spatio-temporal features of video sequence. We compared three different 3D convolutional networks and the best accuracy was achieved by architecture Al reached 85%. The second experiment was performed on subset of UCF101 dataset. We selected 15 activities. Architecture A1 achieved accuracy 80.7%. Our results show that it is possible to achieve relatively high accuracy using subtile architecture of 3D convolutional network.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123101413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martin Medvecky, R. Vargic, J. Londák, P. Podhradský, P. Trúchly
{"title":"Integration of Virtual SDN and NFV Laboratory with NEWTELP Platform","authors":"Martin Medvecky, R. Vargic, J. Londák, P. Podhradský, P. Trúchly","doi":"10.23919/ELMAR.2018.8534629","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534629","url":null,"abstract":"The paper provides a concept and architecture of the Virtual SDN and NFV Laboratory and its integration with NEWTELP platform - a learning platform developed with the EU Horizon 2020 NEWTON Project. The Virtual SDN and NFV Laboratory was proposed as a virtual laboratory for teaching and research activities in the field of Software Defined Networking (SDN) and Network Function Virtualization (NFV) technologies. The paper presents the concept, implementation and testing of integration of Virtual SDN and NFV laboratory with NEWTELP platform.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115039159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. Ivanjko, Gabriel Oliveira Melo, K. Kušić, M. Gregurić
{"title":"Comparison of Controllers for Variable Speed Limit Using Realistic Traffic Scenarios","authors":"E. Ivanjko, Gabriel Oliveira Melo, K. Kušić, M. Gregurić","doi":"10.23919/ELMAR.2018.8534633","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534633","url":null,"abstract":"Urban motorways are designed to serve higher traffic loads but rush hours are causing periodically unstable traffic flows and congestions. Variable Speed Limit Control (VSLC) can alleviate congestion by posting appropriate speed limits on Variable Message Signs. In this paper, three controllers for VSLC are compared using a simulation model based on real traffic data obtained from the PeMS database collected at a selected motorway of the State of California, USA. The results show that the implemented VSLC controllers have the ability to improve the traffic condition in case of higher traffic intensity compared to an uncontrolled case.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126705845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Croatian Society Electronics in Marine – Elmar","authors":"","doi":"10.23919/elmar.2018.8534623","DOIUrl":"https://doi.org/10.23919/elmar.2018.8534623","url":null,"abstract":"","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126789863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matija Pul, M. Vranješ, Zvonimir Kaprocki, Dejan Stefanovic
{"title":"Computer Generated Image Alterations Database","authors":"Matija Pul, M. Vranješ, Zvonimir Kaprocki, Dejan Stefanovic","doi":"10.23919/ELMAR.2018.8534596","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534596","url":null,"abstract":"Modern user interfaces (UI) use animations and special effects to appear more interesting and appealing to consumers, such is the case for modern Set-Top-Boxes (STB). In order to provide their consumers with functional and reliable products, manufacturers are required to perform functionality verification (FV) of each product. Automated FV systems are becoming a prevailing method of FV due to manual FV becoming exceedingly time consuming as the devices become more complex. Generally, full reference (FR) image comparison between the device output image and the referent image is used in order to perform FV of device under test (DUT). Common methods for image comparison proved to be ineffective when comparing images captured from UIs containing animated objects or dynamic background. In order to provide manufacturers with high-end FV systems, it is necessary to develop new methods for image comparison capable of comparing images despite alterations caused by UI animations. Development of such algorithms requires large image databases which effectively simulate such image alterations. In this paper we present new Computer Generated Image Alterations Database (CGIAD) which contains 10000 test images with alterations caused by object transformations commonly used in UI animations (rotation, scaling, occlusion, and translation). CGIAD is freely available to the research community at http://www.rt-rk.com/other/CGIAD.html.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127927104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alan Vogel, Izidor Oremović, Robert Šimić, E. Ivanjko
{"title":"Improving Traffic Light Control by Means of Fuzzy Logic","authors":"Alan Vogel, Izidor Oremović, Robert Šimić, E. Ivanjko","doi":"10.23919/ELMAR.2018.8534692","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534692","url":null,"abstract":"In urban areas, the traffic demand grows every year due to the constantly increasing number of vehicles. The consequence is a capacity drop of the roads followed by traffic problems like congestion, reduced travel time, increased fuel consumption, etc. This paper presents an adaptive traffic light controller based on fuzzy logic for improving the traffic flow on an isolated intersection. A set of fuzzy rules has been made that, using the collected information from road detectors (queue length, arrival flow, and exit flow), computes the amount of time for which the next phase should be shortened or extended. The proposed fuzzy control system is constituted of two parts: one for the primary driveway (with a higher volume of vehicles) and for the secondary driveway (with a lower volume of vehicles). The proposed controller is compared with a fixed signal program in three scenarios with different traffic demand proofing the effectiveness of the developed decision rules.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115907930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Gaita, Georgian Nicolae, A. Radoi, C. Burileanu
{"title":"Chainsaw Sound Detection Based on Spectral Haar Coeffluents","authors":"A. Gaita, Georgian Nicolae, A. Radoi, C. Burileanu","doi":"10.23919/ELMAR.2018.8534594","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534594","url":null,"abstract":"Illegal deforestation endangers the environment and facilitates the appearance of natural disasters as flooding and landslides. These actions lead also to major climate changes and to global warming. Illegal deforestation can be detected through a sound based monitoring system that records environmental sounds and decides whether the sound is generated by a chainsaw or the source is different. This paper presents a novel method of sound classification based on Haar like features extracted from the frequency domain and provides comparisons with other methods found in the related literature.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134512807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Smart Mobility","authors":"I. Šemanjski, S. Mandzuka, S. Gautama","doi":"10.23919/elmar.2018.8534693","DOIUrl":"https://doi.org/10.23919/elmar.2018.8534693","url":null,"abstract":"Together with smart cities, a new field emerged in the domain of mobility called smart mobility. However, literature lacks clear definition of smart mobility and clarification of its relationship with the already existing Intelligent Transport Systems. In this paper, we aim to give systematic overview of smart cities and smart mobility. To do so, we start from the Intelligent Transport Systems and look towards the context in which smart mobility aroused together with its reflection on sustainable mobility, autonomous vehicles and possibility to extract big data driven insights on mobility that were not available ever before.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127378386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of Split-Brain Autoencoders for High-Resolution Remote Sensing Scene Classification","authors":"Vladan Stojnić, V. Risojevic","doi":"10.23919/ELMAR.2018.8534634","DOIUrl":"https://doi.org/10.23919/ELMAR.2018.8534634","url":null,"abstract":"Self-supervised methods are interesting for remote sensing because there are not many human labeled datasets available, but there is practically unlimited amount of data that can be used for self-supervised learning. In this paper we analyze the use of split-brain autoencoders in the context of remote sensing image classification. Weinvestigate the importance of training set size, choice of color space and size of the model to the classification accuracy. We show that even with small amount of unlabeled training images, if we finetune the weights learned by the autoencoder, we can achieve almost state of the art results of 89.27% on AID dataset.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127457673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Measurements of Radiated Emissions up to 30 MHz from Installed Multi-pair Communication Cable","authors":"Mladen Jakovac","doi":"10.23919/elmar.2018.8534609","DOIUrl":"https://doi.org/10.23919/elmar.2018.8534609","url":null,"abstract":"This paper aims to determine the radiated emission of installed multi-pair cable most used in the Croatian access telecommunication networks. In order to do understandable measurements the most important parameters characterizing twisted pair cable and ability to radiate (egress) or receive (ingress) EM energy are shown. A brief description of the loop antenna is given, used for measurement of equivalent electrical field strength in frequency band 9 kHz to 30 MHz. Radio Frequency Interference (RFI) losses, which are equivalent to the negative antenna gain in the subscriber's xDSL loops derive on the basis of field strength measurement of known electrical field strength. Measurements were performed on intentionally installed multi-pair cable as well as on installed multi-pair cables implemented in real xDSL access network. The ITU-T K.60 recommendation is shown by setting out the procedure to be adopted for measuring radiation and defining the maximum permissible level of electromagnetic radiation from wireline telecommunication network to minimize electromagnetic disturbance of radio services.","PeriodicalId":175742,"journal":{"name":"2018 International Symposium ELMAR","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126504315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}