The last seminar of MITS project has successfully ended. In addition to thorough presentations by our team, visitors were able to see and try out demonstrations, such as car detection in video and by magnetic sensors and microphone arrays using a remote control toy car. Of course recordings of tests with real cars were also provided but the seminar hall was too small for life size actual demonstration.

We are really happy about the interest shown by the people who arrived.

More pictures from the seminar will follow soon.

A seminar on results of the ERDF project “Multi-functional intelligent transport system point technology” will happen on December 11 – everyone is welcome!

When: On Wednesday, December 11, 13:00-17:00 (program available here)

Where: Days Hotel Riga, Brīvības street 199

Our project is coming to completion and we will be happy to tell You about our results and show parts of the system in action!c, Riga, Latvia. Top floor hall.

Vehicle license plate recognition is essential for making  automated traffic control systems. These kind of systems can be installed  in all kinds of locations, thus reducing the need for hard human labour.

Vehicle detection and analysis of the traffic flow is important part of intelligent transportation systems. Depending on weather conditions there are various sensors and techniques used for vehicle detection. There is no universal sensor with excellent performance in all weather and road surface condition. To get better vehicle detection in all weather condition one of solution is to use several sensors at the same time. In this case some of the sensors give better result in rain or fog, some sensors shows better performance in summer season but in cold weather performance is poor. Collecting information about traffic flow form several sensors with several physical features gives bigger precision of vehicle detection in different weather conditions.

Microphone array
Applying  microphone array and using signal processing it is possible to detect vehicle by it emitted sound. Most of noises coming from moving vehicles are noises from tires, noises generated by vehicle aerodynamics and noises generated by vehicle engines. Calculating sound signal delays between equidistantly spaced microphones allows to detect vehicle presence and motion direction.  There is difference between the emitted sound from the heavy and light vehicles. This can be used to classify vehicles using sound signature. Using microphone array or only single microphone, is possible to detect emergency vehicle.

PIR sensors
Using Passive Infrared Sensors (PIR) is possible to detect moving vehicles. PIR sensor perceives an thermal radiation that is emitted from the object. In our application sensors does´t give information about classification, they are used only to detect presence of the vehicles. Vehicle detection algorithm is implemented into the micro controller, all information about the traffic flow are sent using wireless data communication.

is case it is vehicle. This means – vehicle detection is carried out indirectly. Using magnetic field sensors it is possible to detect and classify vehicles by it’s magnetic signature. Magnetic sensor can be placed on the road surface, embedded in pavement (invasive solution) or placed on the side of the rod (non-invasive solution). Our approach – sensors are placed on the both sides of the road opposite to each other. Using this arrangement is possible to distinguish heavy and light vehicles.

Magnetic sensors
Vehicle radiates small magnetic field. The main source of magnetic field is alternator and other electrical devices. Magnetic sensor do not detect vehicle emitted magnetic field, it detects Earth´s magnetic field´s local distortions caused by metal object – in th

Laser sensors
These sensors belong to active sensor group. Laser sensor emits light and receive some portion of reflected light. Sensors are placed above the road – for each traffic lane one sensor. By measuring distance to the moving object(vehicle) that is located under the light beam of the laser sensor its possible to detect vehicles and also classify vehicles(light vehicle, SUV, minivan, heavy vehicle). The classification is based on measured height of the vehicle.

Traffic monitoring system can potentially consist of many separate traffic nodes, each working with many sensor inputs and maybe even several actuation outputs. Such a system should work robustly over a network of many physical devices and maintain maximum functionality and security even when several of those physical devices fail or develop problems. At the same time such system must be easily extendable.

System consists of several physical computers. On each of these computes a special process called system core is running. This process provides infrastructure to all other system processes in such a way, that the physical complexity of the system is obscured. Because of this, all processes, such as vehicle detector or number plate detector can communicate to each other and use system data storage and communication facilities as if all of the system was located on the same physical machine. Additionally system core provides distributed configuration services, data storage services and security and recovery mechanisms, such as watchdog.

Every system task, except the internal communication done by system core, is done by separate modules. Some modules gather data from sensors, some process this data, and even others act on the data processing results by either notifying someone or actuating traffic control lights.

Each of the modules can subscribe to information channels provided by system core. Communication is also provided to the outside world for such cases when some institutions must be notified of the situtaion (for example in cases of emergencies).

All gathered information from all system nodes is gathered together and used to build the best possible traffic model. This traffic model is then used as a base to intepret situation on the road and act on it if necesary.

* This system architecture has been described in more detail in the following publication:
Nesenbergs, K.; Selavo, L., “A distributed data processing architecture for real time intelligent transport systems,” Informatics and Applications (ICIA),2013 Second International Conference on , vol., no., pp.155,160, 23-25 Sept. 2013