An article about DataFromSky appeared in an e-magazine Xataka. This online newsletter focuses on smart solutions in various areas, including smart businesses, smart cities and municipalities, or smart government. The article describes our path to success, how the project DataFromSky originated, what are our achievements and future goals.
The article also describes how the data is collected and what are some special conditions and requirement for the input video for DataFromSky analysis and mentions some legal restrictions for drones and other small UAVs that vary from country to country. Further on, the process of data and trajectory extraction using the DNN and machine learning is simply explained.
Our CEO also explains the future plans and vision of DataFromSky: “We want to apply everything we have learned with our algorithms for detecting vehicles and people in services such as traffic surveillance. And here we are not talking about a post-processed analysis, but monitoring and analyzing the data in real time directly on site. This could be done by drones or by fixed cameras, and would not be limited to detecting excesses of speed. The idea is to be able to determine aggressive driving, a sufficient safety distance between cars, calculate an excess of emissions or something as simple as counting the number of cars that pass through a point in a certain period of time, matched with a license plate. It would be a big evolution of the dreaded traffic cameras that are limited to detecting speeding nowadays.”
For more information, read the full article (available only in the Spanish language) available on this link.
Moreover, we have attended several Smart City conferences with our partners (see below) and we plan to attend several more in upcoming months.
Future of Transportation world conference held in Cologne, Germany, June 20th
Smart Cities Global Technology & Investment Summit 2018 in Algiers, June 28th
An article about DataFromSky appeared in Czech e-magazine Svět-chytře. This online newsletter focuses on smart solutions in various areas, including smart businesses, smart cities and municipalities, or smart government.
The article itself describes DataFromSky as a solution, which is often used to determine the traffic situation and evaluate the existing infrastructure, whether it is sufficient or not. Do you need a safety study of a particular traffic junction? Do you want to know the capacity of the roundabout? Analyze peak hours and driver’s behavior patterns in these critical periods in busy road segments? Or monitor a risky behavior of drivers on highways etc.?
The combination of drone technology for data collection and advanced video processing tool – DataFromSky – assists many users such as government entities and road agencies for effective traffic monitoring and management, police forces for continuous, precise and inconspicuous surveillance of the traffic situation, traffic engineers and many others. Because small UAVs can provide very good situational awareness from the bird’s eye perspective, it can be used in several situations in traffic monitoring, surveillance and control.
Besides traffic, the list of potential uses of DataFromSky technology goes on and on. There is congestion monitoring during mass events, crowd control during the demonstrations and strikes, perimeter surveillance and much more.
As the article summarize, our AAI (Aerial Artificial Intelligence) uses deep neural networks that are trained on millions of shots from junctions of all over the world, including Mexico, United Arab Emirates, the United States, India and other countries of the world. The machine learning is an ongoing process and the ability to automatically analyze and detect the objects in the video is constantly improved. Thanks to that, DataFromSky analysis reaches the accuracy over 98,5 %.
For more information, read the full article (available only in Czech language).
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 new scientific article answers… Since the inception of DataFromSky we were actively collaborating with academics to analyse traffic and design safer transportations systems for a better future. Beside the development of the processes to extract and analyse trajectories of the vehicles from aerial videos, we also aimed to analyse the accuracy of our approach itself.
In collaboration with Faculty of Information Technology and Faculty of Civil Engineering at Brno University of Technology, we are working to analyse the accuracy of object position estimation and accuracy of extracted trajectories and their properties when estimated by a low flying UAVs. (see our news from a year ago).
In the previous year, we have developed a tool to assess the accuracy of object position estimation algorithm similar to the one used in DataFromSky. We used this tool to estimate the accuracy of object position estimation from aerial imagery captured by a general-purpose drone in various scenes and compared the results with spatial data collected with an industrial grade GPS sensor. A part of this research and its results have been recently published in special issue on Unmanned Aerial Vehicles in peer-reviewed scientific journal International Journal of Transportation Science and Technology and is already available for pre-press preview at the following link: http://dx.doi.org/10.1016/j.ijtst.2017.02.002
The article provides an insight into the nature of the accuracy of position estimation and properties of uncertainty propagation through the algorithm with respect to various aspects of the camera, scene and its setup. The additional contribution of article is to provide a guiding tool to properly choose and set the drone pose and camera to achieve the desired accuracy of the position estimation of objects in the traffic scene prior the capture of the scene itself.
Picture: “Spatial visualisation of the resulting position estimation error in metres caused by non-linear deformation, across the camera field of view. The 4 red crosses represent the images of the landmarks. The camera is situated at position (0,0,100)[m] looking directly down.”
DroneBlog covered us a few days ago in a post called DataFromSky offers traffic analysis of aerial video data. Given that the blog is mostly for the drone sector, there is a lot of text dealing with traffic data collection basics and particulars. There is a bit of history behind DataFromSky as well – how a group of computer vision specialists got into traffic analysis.
In other news, we are at Intertraffic in Amsterdam and the concentration of minds and companies is spectacular. We hope to get some newsworthy partnerships and arrangements!
DronEzine, an Italian electronic drone magazine, published an article dedicated to Smart Mobility World 2015. This year, a section will be dedicated to drone use in the field of traffic, intelligent transport systems and mobility. The article mentioned DataFromSky: “All over the world, the businesses that use UAV for this kind of mission have proliferated, such as DataFromSky, to mention just one name“.
We are happy to be mentioned, since we are planning to participate again this year, after our participation last year in Turin. The 2015 edition will start on 28th October at the Italian F1 circuit in Monza, conveniently located in time and space near the end of Expo 2015. Don’t hesitate and come!
Read the whole article in Italian (or the vaguely useful Google translation).
Alan Sackrin, Florida based Civil Trial Lawyer, published an article about the importance of road design and its influence on road crash statistics.
Current conditions of roadways and their design – these two factors play a major role in number of car accidents.
There are times when people are seriously injured or even killed in auto accidents on a traffic path where the design itself causes danger mentions Alan Sackrin.
Read the whole article at South Florida Injury Accident Blog.
Transportation is one of global issues and the road traffic accidents death rate is annually increasing. DataFromSky wants to fight against this problem by providing advanced safety analysis. Join us to keep our roads well-designed and safe!
Mike On Traffic is a blog about “the Less Boring Side of Traffic Engineering“. DataFromSky was recently mentioned in a post called Counting Cars from the Sky: The Future of Traffic Monitoring.
At the beginning of July, sUAS news reported about drone traffic monitoring demonstration in Netherlands.
Traffic technology International, an international web-and-print magazine, published in their June/July 2015 issue an article about UAV-based road traffic monitoring based on the Netherlands event under the title Farewell to fixed cameras?.
While the one-off demonstration showcased real-time monitoring, not analysis, it is an application of UAVs in traffic nevertheless. The article title is especially poignant for us, since drones can replace fixed cameras for both monitoring and analysis.
Meanwhile, another monitoring application is on the horizon: “The Jakarta City police to use drones to monitor traffic”. Doubtless, many more are to come…