Vehicle detector demo
How does the traffic move after recent adjustings? What kind of vehicle will pass by on a certain crossing? With the use of artificial intelligence it is possible to detect unique vehicles. Therefore it is possible to trace or follow vehicles with the use of multiple cameras and to map certain streams or to automatically count how many times a certain event in the traffic happens. To demonstrate we have made an online demo with a standard algorithm where you can test your own image.
Common Objects in COntext
In the example above, the image is trained with the COCO dataset and it will calculate the possibility that the object is a vehicle. An example of a project with vehicles and image recognition that Studio diip worked on was Automatic number plate recognition (ANPR): A Custom built number plate recognition system that can feed information into many different systems. The learning algorithm that we use here is trained to detect the following vehicles:
- Cars
- Busses
- Boats
- Bicycles
- Motors
- Airplanes
- Trains
- Trucks
Common Objects in COntext
In the example above, the image is trained with the COCO dataset and it will calculate the possibility that the object is a vehicle. An example of a project with vehicles and image recognition that Studio diip worked on was Automatic number plate recognition (ANPR): A Custom built number plate recognition system that can feed information into many different systems. The learning algorithm that we use here is trained to detect the following vehicles:
- Cars
- Busses
- Boats
- Bicycles
- Motors
- Airplanes
- Trains
- Trucks
Image recognition with deep learning
For this example we have used an algorithm that is trained on a thousand photos with all sorts of vehicles from the COCO dataset (Common Objects in COntext). This database includes images of the chosen vehicles where you can exactly see where the vehicle is hidden in the photo. Therefore, a learning algorithm can train itself to automatically recognize vehicles in different photos. Off course you can also use this technique to detect other objects as well. We use tools like Keras and TensorFlow to see how well the algorithm performs.