Research and Grant Projects
We are pioneering new technologies and solutions to help cities solve their problems and aid their tranfrormation to smart cities.
DataFromSky and RCE Systems s.r.o. are pioneering new technologies and solutions to help cities solve their problems and aid their tranfrormation to smart cities thanks to various research grants. These technologies are based on computer vision and and focused for example on improving public space safety, improving traffic FLOW with V2X based technologies or providing new methods of traffic monitoring with the mobile surveillance TrafficDrone unit. To expand our innovation capabilities we work together with academic institutions and various business partners to deliver these projects.
List of the grant projects
Making the Road Traffic Emissions Visible
01/2023 - 12/2025
The goal of the project is to develop, demonstrate and validate a system for indirect measuring of exhaust and non-exhaust emissions. The system would be able to do this in real-time by utilizing a combination of detailed traffic data, morphology of the terrain and advanced multi-emission models. With the use of computer vision and AI the categorized trajectories of the individual road users would be extracted from the video streams. This data describing the dynamics of the traffic flow will be the essential part of new microscopic models for estimating the production of CO2, NOx, and PM emissions. The result of the project would be an easily applicable and scalable solution that will make use of the existing camera infrastructure for immediate and continuous emission measuring.
Classification of socio-psychological parameters of people using artificial intelligence and machine vision for the needs of people protection in real-time
01/2019 - 12/2021
The project focuses on the classification of the social and psychological parameters of persons in crowded places with the poor protection. This information will be extracted from a video data typical for a common surveillance infrastructure (such as a railway station or shopping center system) using methods of psychological analysis, machine vision and deep neural networks. The parameters obtained will serve, among other things, to determine the statistical distribution of the pre-evacuation time in the event of an emergency, when this time interval is for security personnel critical and hard to obtain, and generally to improve supervision. Used methods will comply with the General Data Protection Regulation.
Development and research of a V2X traffic detector combining radar and image data
01/2019 - 12/2021
The aim is to develop new traffic detection system for adaptive control of junctions and traffic surveys, which will combine the advantages of radar and optical technology using artificial intelligence methods both in image processing and aggregation of individual measurements. The detector computation unit will be based on new AI processors for embedded systems that allow deep neural networks and probabilistic object tracking to run. The resulting sensor will have a defined REST interface for integration into higher units. The sensor will also be equipped with a 4G / 5G modem for data connectivity, GPS locator and memory storage for recording and storing up to 3 weeks of data.
Mobile platform for traffic monitoring using drones and computer vision
01/2018 - 12/2021
The aim of the project is to develop and demonstrate a comprehensive mobile platform for real-time bird monitoring of traffic , using unmanned aerial vehicles (UAVs) and advanced computer vision methods based on artificial intelligence within three years. The output of the project will be a system for rapid deployment and supervision of the defined area with automatic recognition of objects, their monitoring and automatic evaluation of movements. The extracted data from the image will be analyzed in order to detect non-standard behavior, congestion, violation of the defined zone and other user-defined parameters. This will be integrated into a higher level of the system for traffic situation assessment and management (partner). The system has a great potential for use in traffic monitoring (police drone) and in surveillance tasks.
Classification of socio-psychological parameters of people using artificial intelligence and machine vision for the needs of people protection in real-time
01/2019 - 12/2021
The project focuses on the classification of the social and psychological parameters of persons in crowded places with the poor protection. This information will be extracted from a video data typical for a common surveillance infrastructure (such as a railway station or shopping center system) using methods of psychological analysis, machine vision and deep neural networks. The parameters obtained will serve, among other things, to determine the statistical distribution of the pre-evacuation time in the event of an emergency, when this time interval is for security personnel critical and hard to obtain, and generally to improve supervision. Used methods will comply with the General Data Protection Regulation.
Development and research of a V2X traffic detector combining radar and image data
01/2019 - 12/2021
The aim is to develop new traffic detection system for adaptive control of junctions and traffic surveys, which will combine the advantages of radar and optical technology using artificial intelligence methods both in image processing and aggregation of individual measurements. The detector computation unit will be based on new AI processors for embedded systems that allow deep neural networks and probabilistic object tracking to run. The resulting sensor will have a defined REST interface for integration into higher units. The sensor will also be equipped with a 4G / 5G modem for data connectivity, GPS locator and memory storage for recording and storing up to 3 weeks of data.
Mobile platform for traffic monitoring using drones and computer vision
01/2018 - 12/2021
The aim of the project is to develop and demonstrate a comprehensive mobile platform for real-time bird monitoring of traffic , using unmanned aerial vehicles (UAVs) and advanced computer vision methods based on artificial intelligence within three years. The output of the project will be a system for rapid deployment and supervision of the defined area with automatic recognition of objects, their monitoring and automatic evaluation of movements. The extracted data from the image will be analyzed in order to detect non-standard behavior, congestion, violation of the defined zone and other user-defined parameters. This will be integrated into a higher level of the system for traffic situation assessment and management (partner). The system has a great potential for use in traffic monitoring (police drone) and in surveillance tasks.