In terms of perimeter security, solution based on UAVs provide several advantages over mounted cameras or simply patrolling the property yourself, including mobile video surveillance, remote control and stealth.
The key part of such solution is automatic detection and recognition of possible threats from bird-view perspective. DataFromSky is the most advance aerial artificial intelligence (AAI) trained and tested on thousands of millions of images to identify vehicles, pedestrians, bikes and other objects. It opens a new dimension of applications of drones for reliable and mobile protection of critical areas/infrastructure. Take a look at the brief demonstration of technology we are working on.
Are you interested in cooperation? Don’t hesitate to contact us, we are looking for system and integration partners in the segment of perimeter surveillance using UAVs.
Massive progress we have made in DataFromSky! As we keep on further development of DataFromSky solution, we can now boast great successes in the field of automatic detection from a moving UAV!
Imagine that you can directly detect and count the vehicles in traffic congestions while flying a drone over the traffic node! Impossible? Not anymore – since this moment, DataFromSky can detect and analyze vehicles from a flying UAV and provide information about the total number of vehicles and its category. Knowing such valuable information in real time, one can immediately predict the length of delay in the traffic congestion or the length of the tailback itself.
The success rate of the detection exceeds 95,67 % and the detection works on 12 828 CUDA cores – the image is evaluated in 200 ms.
See the video below, showing the raw data output from the detector – the data is not additionally modified in any way (no tracking, no filtration), however, even with the raw output we reached such a high accuracy of detection. Further data processing (tracking, etc.) will make the output even more accurate!
Recently, DataFromSky has performed traffic analysis of another video from United Arab Emirates, Dubai! This huge multilevel intersection in the middle of the arabic desert, which you can see in the video below, was a challenging task due to the large area covered and the weather and climate environment with very dusty and sandy conditions. The object of the analysis was monitoring of traffic behaviour in this vast area with traffic density reaching almost 8 500 vehicles per hour!
As you may see in the video, large area of one busy cloverleaf near the city of Dubai was analyzed – the average length of one trajectory in the video reaches 800 meters.
If you regurarly follow our website, you may know, that we are still working on development of mobile solution, which will be capable of collecting and analyzing traffic data in real time. This smart UAV analyzer will be a subsystem of Intelligent Transportation System (ITS). The main objective is to design the cutting edge technology: an UAV based solution for the purpose of active traffic management over a road network.
See also our latest video analyzed in UAE by clicking on this link.
New research paper called “How accurate are small drones for measuring microscopic traffic parameters?” published in Transportation Letters Journal can provide an answer. Adam Babinec, one of the main IT developers standing behind DataFromSky solution, co-author of the article conducted by University of Athens and Brno University of Technology, says:
„With this paper, we wanted to examine the potential of using sUAV as part of the ITS infrastructure as a way of extracting naturalistic trajectory data from aerial video footage from a low volume intersection and a pedestrian passage. Moreover, we have examined the accuracy of speed data collected from a drone compared to data collected from an On-Board Diagnostics II (OBD-II) device.”
The results show, that the distortion correction and calibration phase of the video are of crucial importance for high level of accuracy, in terms of stabilizing and geo-referencing the video. In order to extract accurate data from drone video footage, each aerial video must be stabilized to compensate for camera movement, since sudden vibrations or small wind gusts can lead to large errors on the ground.
Picture: a lightweight hexacopter (left), study area – low volume intersection in University of Athens campus (right)
The research paper is accessible on this page.
The accuracy of DataFromSky system itself was examined in another research paper, created in collaboration with Faculty of Information Technology and Faculty of Civil Engineering at Brno University of Technology and posted in International Journal of Transportation Science and Technology, for more information click here.
Our team attended the event called “Industrial Day”, held between 21. and 22. 7. 2017 in local airport of Přerov. We presented our work and capabilities at the seminar on “UAV/UGV and its use in Security”, an event dedicted to introduction and presentation of cutting edge technologies to support the use of robotic and unmanned systems in the development of Intelligence Surveillance Reconnaissance (ISR) capabilities for the Czech Armed Forces. We demonstrated our technology DataFromSky for tracking the moving object in the aerial video data and also our project related to perimeter security with a drone.
The event has been organized and supported by Ministry of Defence of Czech Republic, in cooperation with the Department of Industrial Cooperation and Organization Management (SPSŘO), LOM PRAHA and the Association of Defence and Security Industry (AOBP).
We are delighted, that our solutions have attracted many participants of the event and that we have met with a very positive feedback!
We are happy to announce that we have succeeded with our proposed project and get supported in Programme Epsilon 2 conducted by Technological Agency of Czech Republic:
System for Preemptive Safety Analysis of Road Network Nodes and Traffic Flow
The aim of the project is development of a preemptive quantitative system for analysis of road network nodes in terms of safety. The system will be
based on analysis of time-space information about each individual traffic member. The information will be automatically extracted with high precision
and frequency from video data collected by UAVs. The trajectory data extracted from video will be analyzed in terms of traffic safety, based on
detection of non-standard and aggressive behaviour, conflict situations, incomfort during passage etc.
We are proud to announce our partnership with Elistair, from France, which has developed tethered solution for UAVs. Through this partnership, we can deliver a UAV solution for monitoring and analyzing of moving objects from bird’s-eye perspective. We are creating an unique access to unlimited aerial monitoring capabilities, for both public and private entities (traffic monitoring, perimeter security, etc.).
We teach drones to see, to understand image data!
Recently we got to analyzing a video of a roundabout in Roskilde, Denmark. And because Denmark is called: The land of bikes, we didn’t focus only on vehicles but also on bikes! And here is the result of our traffic monitoring:
Length of analyzed video: 15:38.48
Number of objects being tracked: 298 (vehicles and bicycles)
Total distance traveled: 79 354.4 m
Average speed: 34.0233 km per hour
Average distance on roundabout: 59.7474 m
And we would also like to thank Dansk Drone Kompagni for providing us the video.
What can we get from 4K resolution in the field of traffic monitoring? We tried it for the first time and the answer is – coverage of huge intersections with great accuracy in the vehicle localization! DataFromSky is prepared to bring you high quality aerial video data.
See the first analyzed video in 4K provided by DronExplore.