The Universities of Applied Sciences of Ulm and Heilbronn in Germnay, along with industrial partners, have created SALUS, a mix of radar, optical cameras, infrared sensors and neural networks system designed to detect animals on the road. The machine-learning system differentiates between other road users and animals, then predicts their behaviour and sends a message to nearby drivers.
“Car manufacturers are installing driver assistance systems starting with high end models but this will take time to filter down to other models. Similarly, high end motorcycles are starting to have such functionality but limited installation space will mean that it will be very difficult to achieve anything comparable to a car-based alert system. The aim of our project is to have small installations by the roadside that detect hazards and communicate this to vehicles as they approach. In addition, for road users without in-car warning displays, road lights could be turned on to highlight the area of the hazard and/or warning notices illuminated,” said Professor Hubert Mantz from the Ulm University of Applied Sciences.
Data of the micro-Doppler radar is gathered by a Spectrum Instrumentation PCIe digitiser card M2p.5926-x4 that provides the required number of channels and bitwidth. It gathers the information to teach the system as it enables processing of data simultaneously in real time.
The technical demonstrator system will be able to measure simultaneous data from three sources – radar, optical camera and infrared camera. Additional sensors could be integrated, for example, to measure pollution levels, which has already generated commercial interest from companies in the Project’s consortium. The project envisages widescale deployment of these self-contained units as posts beside roads across Germany, which means that they must be inexpensive and solar powered. The latter is particularly important for rural areas where mains electricity is not readily available and the need for such a warning system is greatest as street lighting is scarce.
This also means that the communication system between units to form an intelligent transport infrastructure must be low power so Long Range Wide Area Network (LoRaWAN) is used as it can reach up to 40 km in rural areas. This standard is characterized by its low energy consumption, and is based on unlicensed frequency bands and therefore available at low cost.
“We are using neural networks to develop the machine learning that enables the system to differentiate between e.g. bicyclists, cars or deer. This takes it far beyond pure motion detection,” added Professor Mantz. “We are at the critical part of the project which is the classification of detected objects, which has never been done before. With this, the system will be able to predict the movements of objects which adds incredibly useful, real-time intelligence to the system enabling it to foresee how a hazardous situation could develop.”
[Image credit: Edvin Karlsson for Unsplash]