Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161771
G. Zajic, Katarina Popovic, A. Gavrovska, I. Reljin, B. Reljin
Computer vision techniques implemented in modern vehicles should be designed to distinguish different changes in a video sequence, captured by RGB and RGBD cameras mounted in or out a vehicle. Autonomous driving process could improve safety of all passengers by introducing additional sensing. In this paper, we used input data from mentioned cameras acquired with inertial sensor for road roughness as a limiter of velocity. Abrupt changes of the velocity and driver comfort affects the driver’s head position. The head position is monitored using 3D skeleton model and depth information. The results show possibility of detection of the potential risk found for unusual driver behavior. Then, the human control could be taken by safety application and system.
{"title":"Video-based Assistance for Autonomous Driving","authors":"G. Zajic, Katarina Popovic, A. Gavrovska, I. Reljin, B. Reljin","doi":"10.1109/ZINC50678.2020.9161771","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161771","url":null,"abstract":"Computer vision techniques implemented in modern vehicles should be designed to distinguish different changes in a video sequence, captured by RGB and RGBD cameras mounted in or out a vehicle. Autonomous driving process could improve safety of all passengers by introducing additional sensing. In this paper, we used input data from mentioned cameras acquired with inertial sensor for road roughness as a limiter of velocity. Abrupt changes of the velocity and driver comfort affects the driver’s head position. The head position is monitored using 3D skeleton model and depth information. The results show possibility of detection of the potential risk found for unusual driver behavior. Then, the human control could be taken by safety application and system.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"79 1","pages":"151-154"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84090874","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161805
Bojan Strbac, Marko Gostovic, Ž. Lukač, D. Samardzija
Due to challenging requirements in the competitive market and significant software expansion in automotive industry, there is a need and opportunity to develop and implement new algorithms and solutions, which can further enhance performances, features and quality of this fast growing and constantly changing industry. The aim of this paper is to present the possibility of using cameras instead of LIDARs for distance estimation. The proposed solution is based on the YOLO deep neural network and principles of stereoscopy. This solution uses two slightly moved cameras which obtain two pictures, which goes through algorithm for stereoscopy-based measurement. And estimate distance to detected objects.
{"title":"YOLO Multi-Camera Object Detection and Distance Estimation","authors":"Bojan Strbac, Marko Gostovic, Ž. Lukač, D. Samardzija","doi":"10.1109/ZINC50678.2020.9161805","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161805","url":null,"abstract":"Due to challenging requirements in the competitive market and significant software expansion in automotive industry, there is a need and opportunity to develop and implement new algorithms and solutions, which can further enhance performances, features and quality of this fast growing and constantly changing industry. The aim of this paper is to present the possibility of using cameras instead of LIDARs for distance estimation. The proposed solution is based on the YOLO deep neural network and principles of stereoscopy. This solution uses two slightly moved cameras which obtain two pictures, which goes through algorithm for stereoscopy-based measurement. And estimate distance to detected objects.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"214 1","pages":"26-30"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77428354","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161792
N. Petrovic
Vaporwave is an internet-based musical genre which emerged in early 2010s, inspired by digital consumer culture. In this paper, an approach to automated generation and performance of vaporwave visual art based on ontologies is presented. As a result, AR applications for music performers are generated, while VR applications provide the visual representation of a song to the audience.
{"title":"Digital Consumption as Art Expression: Ontological Approach to Vaporwave Generation","authors":"N. Petrovic","doi":"10.1109/ZINC50678.2020.9161792","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161792","url":null,"abstract":"Vaporwave is an internet-based musical genre which emerged in early 2010s, inspired by digital consumer culture. In this paper, an approach to automated generation and performance of vaporwave visual art based on ontologies is presented. As a result, AR applications for music performers are generated, while VR applications provide the visual representation of a song to the audience.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"195 1","pages":"118-122"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76023526","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161812
Stefan Končar, Ž. Lukač, Nevena Stojanović, Igor Kolak
Automotive industry is rapidly rising last couple of years and fully autonomous driving is the final goal for many car manufacturers. As we can see, Advanced Driver Assistance Systems (ADAS) are becoming increasingly available in many vehicles, in order to improve safety and comfort. Also, the automotive industry is investing a huge funds in order to reach level 4 and level 5 of Autonomous Driving (AD). Before starting mass production, all these vision-based systems must be properly tested, which means a lot of tests with real-life scenarios must be conducted. Different driving scenarios, with different conditions, must be taken into account. All this tests are time-consuming, and therefore money-consuming, in order to be performed in real traffic. Most of these tests can be replaced with appropriate HIL simulations. In this paper we will present one complete solution for Automotive Video Logger device, HIL (Hardware-in-the-Loop) a device of modular and expandable architecture. This kind of device can significantly simplify and reduce time for algorithms development which are necessary for autonomous driving.
{"title":"Development of Automotive Video Logger HIL Device for ADAS/AD Algorithms Development and Testing","authors":"Stefan Končar, Ž. Lukač, Nevena Stojanović, Igor Kolak","doi":"10.1109/ZINC50678.2020.9161812","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161812","url":null,"abstract":"Automotive industry is rapidly rising last couple of years and fully autonomous driving is the final goal for many car manufacturers. As we can see, Advanced Driver Assistance Systems (ADAS) are becoming increasingly available in many vehicles, in order to improve safety and comfort. Also, the automotive industry is investing a huge funds in order to reach level 4 and level 5 of Autonomous Driving (AD). Before starting mass production, all these vision-based systems must be properly tested, which means a lot of tests with real-life scenarios must be conducted. Different driving scenarios, with different conditions, must be taken into account. All this tests are time-consuming, and therefore money-consuming, in order to be performed in real traffic. Most of these tests can be replaced with appropriate HIL simulations. In this paper we will present one complete solution for Automotive Video Logger device, HIL (Hardware-in-the-Loop) a device of modular and expandable architecture. This kind of device can significantly simplify and reduce time for algorithms development which are necessary for autonomous driving.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"2011 1","pages":"295-300"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87710656","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161435
Mirko Spasić, Milena Vujošević Janičić
With increasing popularity and importance of Semantic Web and its application, SPARQL, as a standard language for querying RDF data, gains more importance and receives additional attention from both practitioners and researchers coming from various domains. In database world, the query containment problem is a fundamental problem, crucially important in verification and optimization of queries. In this paper, we present our work on developing SPECS, an efficient solver for this problem in SPARQL query language. Our approach reduces query containment problem to the satisfiability problem in theories of the first order logic, and exploits SMT solver Z3 for checking the constructed formula. We present an evaluation that shows that our solver is much faster and covers more language features than the other available state-of-the-art solvers.
{"title":"SpeCS — SPARQL Query Containment Solver","authors":"Mirko Spasić, Milena Vujošević Janičić","doi":"10.1109/ZINC50678.2020.9161435","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161435","url":null,"abstract":"With increasing popularity and importance of Semantic Web and its application, SPARQL, as a standard language for querying RDF data, gains more importance and receives additional attention from both practitioners and researchers coming from various domains. In database world, the query containment problem is a fundamental problem, crucially important in verification and optimization of queries. In this paper, we present our work on developing SPECS, an efficient solver for this problem in SPARQL query language. Our approach reduces query containment problem to the satisfiability problem in theories of the first order logic, and exploits SMT solver Z3 for checking the constructed formula. We present an evaluation that shows that our solver is much faster and covers more language features than the other available state-of-the-art solvers.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"1 1","pages":"31-35"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83107166","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161441
S. K. Datta
This paper presents a Cybersecurity Framework for end-to-end IoT Platforms called DRAFT. It is developed in response to rising number of Cyberattacks against IoT applications and services. The framework is composed of a risk assessment framework, a Security Incident and Event Monitoring (SIEM) tool, and a Cyberattack resilient framework. DRAFT framework has been integrated into an end-to-end IoT Platform and has been tested using five known and simulated Cyberattacks using the Fed4FIRE+ federated testbeds. The results obtained show that the proposed Cybersecurity framework is capable of increasing Cyberattack resilience of the IoT Platform under test.
{"title":"DRAFT - A Cybersecurity Framework for IoT Platforms","authors":"S. K. Datta","doi":"10.1109/ZINC50678.2020.9161441","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161441","url":null,"abstract":"This paper presents a Cybersecurity Framework for end-to-end IoT Platforms called DRAFT. It is developed in response to rising number of Cyberattacks against IoT applications and services. The framework is composed of a risk assessment framework, a Security Incident and Event Monitoring (SIEM) tool, and a Cyberattack resilient framework. DRAFT framework has been integrated into an end-to-end IoT Platform and has been tested using five known and simulated Cyberattacks using the Fed4FIRE+ federated testbeds. The results obtained show that the proposed Cybersecurity framework is capable of increasing Cyberattack resilience of the IoT Platform under test.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"104 1","pages":"77-81"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83256784","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161784
Dino Pečurlić, M. Herceg, N. Teslic, I. Kastelan
In this paper, the implementation of the XCP protocol over the CAN protocol on the AURIX platform is performed, using the C programming language. Because of its flexibility, the XCP protocol does not require implementation of all possible commands, but only the ones that are needed by a particular use-case. Moreover, the commands from the following groups are implemented: standard functions, calibration functions and measurement functions which use dynamic DAQ lists. During the development of the algorithm, the debugging device and the CANoe program were used. The CANoe measuring tool was used to send the CAN messages, validate the implemented protocol and visualize the collected data. The measurement results show that the module was working as expected, and that it was possible to send more than 25 commands in a 100 millisecond time interval with a very low CAN bus load.
{"title":"Implementation of the XCP Protocol Through the CAN Protocol on the Aurix Platform","authors":"Dino Pečurlić, M. Herceg, N. Teslic, I. Kastelan","doi":"10.1109/ZINC50678.2020.9161784","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161784","url":null,"abstract":"In this paper, the implementation of the XCP protocol over the CAN protocol on the AURIX platform is performed, using the C programming language. Because of its flexibility, the XCP protocol does not require implementation of all possible commands, but only the ones that are needed by a particular use-case. Moreover, the commands from the following groups are implemented: standard functions, calibration functions and measurement functions which use dynamic DAQ lists. During the development of the algorithm, the debugging device and the CANoe program were used. The CANoe measuring tool was used to send the CAN messages, validate the implemented protocol and visualize the collected data. The measurement results show that the module was working as expected, and that it was possible to send more than 25 commands in a 100 millisecond time interval with a very low CAN bus load.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"os-42 1","pages":"195-200"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87430879","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161782
A. Kokoulin, Aleksandr I. Knyazev
The automatic reverse vending machine (RVM) “Sortomat” accepts plastic bottles for further recycling. The analysis of the received containers is performed by running the neural network script. Computations are performed by the Raspberry Pi whose computing power is small and image processing by neural networks takes a lot of time. This paper discusses two procedures that verify the necessity to run a neural network script. The first function allows us to find out whether the camera is powered on and whether pictures are taken in focus and are sharp. The second function reports whether there is an object inside the RVM which is suitable for recognition. This approach helps to decrease the total operating time by estimating the necessity of neural network running and by avoiding the blurred and faulty image processing. The second problem discussed in this article is the image data source augmentation methods for object recognition accuracy enhancement.
{"title":"The Image Sharpness Estimation and the CNN Training Enhancement in the Empty Containers Recognition System of Reverse Vending Machine","authors":"A. Kokoulin, Aleksandr I. Knyazev","doi":"10.1109/ZINC50678.2020.9161782","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161782","url":null,"abstract":"The automatic reverse vending machine (RVM) “Sortomat” accepts plastic bottles for further recycling. The analysis of the received containers is performed by running the neural network script. Computations are performed by the Raspberry Pi whose computing power is small and image processing by neural networks takes a lot of time. This paper discusses two procedures that verify the necessity to run a neural network script. The first function allows us to find out whether the camera is powered on and whether pictures are taken in focus and are sharp. The second function reports whether there is an object inside the RVM which is suitable for recognition. This approach helps to decrease the total operating time by estimating the necessity of neural network running and by avoiding the blurred and faulty image processing. The second problem discussed in this article is the image data source augmentation methods for object recognition accuracy enhancement.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"89 1","pages":"142-145"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90960879","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161809
V. Ciric, Nikola Vidojkovic, Nadja Gavrilovic, I. Milentijevic
With the trend of moving all kind of services online, the number of globally connected services and, generally, devices had enormous growth in the last decade. In such an environment, a security becomes a big challenge. There are many network security architectures. However, most of them make a target service to suffer and struggle to maintain the functionalities behind all additional security layers. The first functionalities that are often lost are functionalities based on knowing the original consumer IP address (authentication, geo-location of consumers, etc). The preservation of the original IP addresses is a difficult task and requires advanced routing techniques at the service provider premises. In this paper the concept of advanced routing and network address translation which preserves the original consumer IP address is discussed. The concept involves load balancer, network intrusion detection, and proxy. The concept and the routing techniques will be described in detail. The results of the system implementation and evaluation will be given.
{"title":"The Concept of Consumer IP Address Preservation Behind the Load Balancer","authors":"V. Ciric, Nikola Vidojkovic, Nadja Gavrilovic, I. Milentijevic","doi":"10.1109/ZINC50678.2020.9161809","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161809","url":null,"abstract":"With the trend of moving all kind of services online, the number of globally connected services and, generally, devices had enormous growth in the last decade. In such an environment, a security becomes a big challenge. There are many network security architectures. However, most of them make a target service to suffer and struggle to maintain the functionalities behind all additional security layers. The first functionalities that are often lost are functionalities based on knowing the original consumer IP address (authentication, geo-location of consumers, etc). The preservation of the original IP addresses is a difficult task and requires advanced routing techniques at the service provider premises. In this paper the concept of advanced routing and network address translation which preserves the original consumer IP address is discussed. The concept involves load balancer, network intrusion detection, and proxy. The concept and the routing techniques will be described in detail. The results of the system implementation and evaluation will be given.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"503 1","pages":"58-61"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73591332","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}
Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161440
Nadja Gavrilovic, V. Ciric
According to recent reports, most of the overall email traffic consists of spam, which represents an abuse for the purpose of mass distribution of unwanted messages. Spam can lead to serious attempts at a data breach or email consumer’s identity theft, also. There are a lot of different anti-spam solutions. The aim of this paper is to design and evaluate an anti-spam solution based on a novel Proof of Work concept. The proposed solution requires a certain amount of work from a sender prior to the transfer of an email message. The extended SMTP protocol will be designed in order to enable the evaluation of client credibility using the Proof of work algorithm. The design of the proposed solution will be presented in detail. The implemented system will be evaluated in distributed spam attempt, simulated by Seagull tool. An evaluation of the client work, the impact on the overall amount of sent spam messages, as well as the impact of distributed spam attempt on the attacked server resource usage will be shown. We will show that the proposed solution helps in reducing spam traffic and server load, while it doesn’t diminish the consumer experience of legitimate email users.
{"title":"Design and Evaluation of Proof of Work Based Anti-Spam Solution","authors":"Nadja Gavrilovic, V. Ciric","doi":"10.1109/ZINC50678.2020.9161440","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161440","url":null,"abstract":"According to recent reports, most of the overall email traffic consists of spam, which represents an abuse for the purpose of mass distribution of unwanted messages. Spam can lead to serious attempts at a data breach or email consumer’s identity theft, also. There are a lot of different anti-spam solutions. The aim of this paper is to design and evaluate an anti-spam solution based on a novel Proof of Work concept. The proposed solution requires a certain amount of work from a sender prior to the transfer of an email message. The extended SMTP protocol will be designed in order to enable the evaluation of client credibility using the Proof of work algorithm. The design of the proposed solution will be presented in detail. The implemented system will be evaluated in distributed spam attempt, simulated by Seagull tool. An evaluation of the client work, the impact on the overall amount of sent spam messages, as well as the impact of distributed spam attempt on the attacked server resource usage will be shown. We will show that the proposed solution helps in reducing spam traffic and server load, while it doesn’t diminish the consumer experience of legitimate email users.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"PP 1","pages":"286-289"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84295304","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：