Abstract:
Due to the increasing urban population and hence the number of cars has
increased enormously and need of controlling the traffic on roads is vital. The
resulting wastage of time and increase in pollution can be eliminated on a city-wide
scale by the following system. Automatic detecting and counting vehicles in video on
roads is a very challenging problem in computer vision with important practical
applications such as to monitor activities at traffic and then predict the traffic flow
which assists in regulating traffic. In this thesis, the system is developed for counting
the number of cars running on the road to analyze traffic in any region. The system
applied the video file that captured the cars running on roads with the help of a
stationary camera. Detection of the moving object and removal of the noise is
achieved by some morphological operations and the result shows the number of cars
on roads is counted. This system uses MATLAB Program for the implementation.
