What is SINAR ?
The lack of attention, associated with driving at high speed, is considered by the World Health Organization one of the main causes of car accidents worldwide. Along with traffic signals and visual pollution in big cities, several gadgets were introduced into the panel of vehicles, such as GPS devices, parking assistants and rear view cameras. All these new technologies contribute to take the driver's attention away from the road, which might lead to several kinds of accidents. SINAR is a low-cost real-time embedded system projected to redirect the conductors' attention to their own speed.
SINAR is a Free Software tool to help enforcing respect to speed limits by providing conductors with a visual warning of their speed, in a way that does not divert drivers attention to the main task of safely conducting the vehicle. It is built using a video camera capable of capturing images from street lanes, a panel of LEDs to display the vehicle speed and a simple embedded computer, running SINAR application under a distribution of GNU/Linux.
It works by positioning the camera to obtain images from a traffic lane of a street or avenue in a way that allow us to observe any vehicles that pass through that lane. The images are processed by the embedded computer that displays the speed at the LED panel, positioned at the side of the road, where it is easily visible to the conductor of a vehicle.
It use computer vision techniques and the open-source OpenCV computer vision library to build algorithms capable of identifying moving objects in the scene and, given a prior calibration, compute the real speed of their movement with a mean absolute percentage error (MAPE) of only 6.16%.
Systems like SINAR are already used to enforce speed limits around the world. Many companies in the USA produce visual warnings similar to those generated by SINAR. Although they have very positive feedback from drivers and report increase on driver's compliance to speed limit of up to 30%, their systems are very expensive, mainly because they use conventional radars to estimate vehicle speed.
Conventional radar systems are based on radio waves to determine objects position, speed and direction. This kind of equipment is expensive and professional radars, like the ones used by the Rio de Janeiro police department, may cost up to 5,000 American dollars. SINAR is a much cheaper alternative to address the problem of reporting speed of vehicles, because it is based on a camera system, and may be used even with a low-cost webcam.
We believe that SINAR can be used not only by public authorities, but also by the population in general to help making their neighborhood streets safer, without requiring high investments. Such a system would be specially useful inside parking lots, small neighborhoods, gated communities and large garages of apartment blocks to help reduce the amount of small accidents caused by excess of speed.
The source code for SINAR is Free Software, licensed under GPLv3. Contributions are very welcome.
How it started
SINAR was presented at the Intel Embedded Systems Competition, during the III Brazilian Symposium on Computer Systems Engineering, in 2013. Our team built the prototype using a board with a low-cost Atom processor, a webcam taken from one of our laptops, and a few LED stripes to build a 7-segment panel to display the speed.
The source code to track and estimate speed of vehicles was made freely available after the contest, under a Free Software license.
We were awarded with the second place at that competition.
What does SINAR stands for?
SINAR is a recursive acronym standing for SINAR Is Not A Radar.
According to Wikipedia, a radar is an object-detection system that uses Radio waves. Even though SINAR is also an object-detection system to track the speed and the trajectory of vehicles, it does not use any kind of radar waves. That is why we say that SINAR Is Not A Radar. :-)
MORGAN, A. ; BERTAZI, G. ; Medeiros, A. ; BORIN, E. ; Goldenstein, S. . SINAR: A low-Cost Image-Based Speed Radar. Presented at Intel Embedded Systems Competition 2013. III Brazilian Symposium on Computer Systems Engineering. 2013. Paper
Contributions are deeply appreciated.
Anyone who wants to contribute to SINAR is invited to send his/her contribution to sinar at krisman dot be.
Download SINAR directly from the GIT repository:
git clone git://git.krisman.be/sinar.git