Two German universities and tech partners are designing a system of sensors along roadways paired with machine learning to spot deer and other wildlife to then warn drivers in an attempt to lower accidents.
The so-called SALUS system is envisioned to be spread across Germany. It will rely on radar, optical cameras and infrared sensors to spot animal movement that are installed in posts 40 kilometers apart. That data will then be automatically interpreted to predict the behavior of wild animals and separate them from cars and motorcycles.
“We are at a critical part of the project which is the classification of detected objects, which has never been done before,” said project leader Prof. Hubert Mantz from Ulm University of Applied Sciences. Heilbronn University is also a partner.
Mantz said the roadside approach makes sense because it will take years to for driver assistance systems with animal alert technology to be spread across various car models at all price points. Also motorcyles won’t have the same functionality of car alert systems. With roadside technology, drivers without warning systems might be alerted to hazards with road lights and digital signs.
In addition to measuring data from radar, optical cameras and infrared cameras, additional sensors could measure pollution. Because the system needs to be spread across Germany, it needs to be inexpensive and solar-powered to reach areas outside the electrical grid. The communication system between the units will be based on a low cost, low power Long Range Wide Area Network running on an unlicensed frequency that can reach the necessary 40 kilometers between detection posts.
Spectrum Instrumentation of Hamburg is providing a digitizer card to collect the micro-Doppler radar data. The card starts at $3,680 with an unusual five-year warranty that will help lower maintenance and repair costs as the detection units proliferate, Mantz said. The Spectrum digitizer runs on four channels and 10 MHz bandwidth to allow processing of data simultaneously in real time.