The Neural Network Method for Detection and Recognition of Moving Objects in Trajectory Tracking Tasks according to the Video Stream
O.S. Amosov, Svetlana Gennadievna Amosova · 2019
The neural network method for detecting and recognizing moving objects in the tasks of trajectory tracking according to the data from surveillance cameras is offered. The new method is effective in terms of accuracy and high-speed performance. The adapted architectures of neural networks are offered to identify vehicles, people and situations.