With the help of artificial intelligence and machine learning technology, we can recognize, and count plants and sort fruits by size, weight and color. In our case study, we developed a machine vision based tomato seedling counting application for Syngenta Hungary Ltd.
With computer vision, we can monitor the movement of cattle and detect lameness early on. Recognition of cattle means the determination of the position of the body, head and hooves. The position or vertical displacement of the head of the cattle can indicate lameness. Unlike lame cattle, the hind legs of a healthy animal step into the footprints of its first legs. The movement of the bovine limbs is analyzed by machine vision, the position of the hooves is recorded, and machine learning is used to examine and classify them.
Machine learning is also a good way to count vehicles and people. We used the YOLOv3 model with the KITTI dataset. This model accurately classifies and determines the exact location of vehicles (car, truck, bus, bike) and people. The number of vehicles passing the main road in front of the office was stored, grouped by vehicle type and direction of travel. The demo on traffic counting is available at: ml.prompt.hu Computer vision also solves other problems, such as searching for and registering parking spots, filtering through traffic, detecting traffic or parking violations. In the video below, we can observe the movement of people and vehicles, whose arrival and departure are announced by the system
Artificial intelligence can also be of great help to doctors in diagnostic imaging. For example, the system is capable of accurately grouping various skin lesions and contributes to the elimination of misdiagnosis.