Deep Learning is a new growing learning technology that can be used to locate illegally parked vehicles successfully with 99%.
If you live in a city and intend to buy car, in addition to road taxes you should also consider parking costs. In fact, you should also calculate the cost of the calls for illegal parking that you will receive at some point.
This is because as technology grows, the automatic road policing measures increase. Last month at 2017 International Conference on Deep Learning Technologies a group of researchers from Xidian University in China demonstrated a detection system based on Deep Learning and who can diagnose cars that have parked illegally with 99% accuracy.
The system described at the conference uses what is known as a Single Shot Multibox Detector (SSD). It is a species neuronal network that simplifies the task of detecting objects with the creation of a set of predefined "start boxes". When scanning begins, the algorithm compares the contents of these boxes to some basic level.
A prediction model is produced from object observations.
The Xidian team's method detects cars and so things in terms of processing the objects are a bit simpler because the cars are pretty much the same. This reduces the computational complexity of the processors, allowing the new system to run in real time.
Detection of illegal parking does not take place for the first time.
A corresponding experimental program had been implemented in Maryland a few years ago, achieving accuracy rates of around 95 percent. A critical difference between this system and most other methods is that it relied on magnetic rather than optical sensors. recognition of objects.
The relative report of the system states that this protects the privacy of citizens. Naturally in Greece 99% is not covered by the law, and for the sake of 1% we will never see it on the busy streets of our cities.
