1 - 4 of 4
ItemCommon Data and Technological Partnership - The Foundation for the Development of Smart Cities - Poznań Case Study( 2019-01-08)Over the recent years communities have been working towards changing the paradigm of city development into the so-called smart approaches. While various revolutionary solutions have been deployed to make the cities smarter, we believe that a more evolutionary path makes it easier for the cities to change into smart ecosystems. Such an evolutionary path is possible with the right foundation. In this paper we discuss such a foundation that has been making the city of Poznań, Poland, smarter over the last 20 years, and opens opportunities for employing the Citizen Science model of smart city development. This foundation relates to the combination of the creation of a common data space, and the technological partnership with a research and development center and research cyberinfrastructure operator such as the Poznań Supercomputing and Networking Center.
ItemBuilding a FIWARE Smart City Platform( 2019-01-08)This paper describes the architecture of a comprehensive IoT solution entirely based on the FIWARE platform. The application is designed to record data from environmental sensors and to eventually visualize them on a Smart City Dashboard. Besides solving certain architectural and technical issues, one particular challenge arose from the fact that some of the sensors were assumed to be mounted on public transportation vehicles like buses and trams. It could be shown that the FIWARE platform provides a range of components that allows for building such an IoT platform in a very efficient way.
ItemComputer Vision System with 2D and 3D Data Fusion for Detection of Possible Auxiliaries Routes in Stretches of Interdicted Roads( 2019-01-08)In this paper we present an intelligent system to help autonomous vehicles in real cities and with local trafﬁc rules. A 2D and 3D visual attention system is proposed, capable of detecting the use of signs and aids in cases of major roadblock (road under work, with a trafﬁc accident, etc.). For this to be possible, we analyze the cones and trafﬁc signs that usually alert a driver about this type of problem. The main objective is to provide support for autonomous vehicles to be able to ﬁnd an auxiliary route that is not previously mapped. For this we use a Grid Point Cloud Map. Using the ORB-SLAM visual odometry system we can correctly ﬁt each stereo frame point cloud in the pose where the images were collected. With the concatenation of point clouds generated by the stereo camera, every grid block can draw the main characteristics of its region and an auxiliary route can be mapped. In this type of situation the vision system must work in real time. The results are promising and very satisfactory, we obtained an accuracy of 98.4% in the 2D classiﬁcation task and 83% accuracy in the single frame 3D detection task.