With the increase in population, traveling has turned out to be a hectic task in the modern era. Traditional timer-based traffic lights, though functional, struggle to mitigate issues like traffic congestion, long wait times, increased fuel usage, and commuter frustration. Incorporating techniques like image processing in traffic control achieves better results than the existing methods. A Gaussian Mixture Model (GMM) and a morphological image processing-based solution are proposed in this paper to overcome these issues. Vehicles are identified by examining the captured images from recorded footage acquired through a static camera. Each extracted frame from the live video is compared with the original frame and undergoes morpho-logical and Gaussian model operations to get the overall count of vehicles. The two techniques are contrasted and compared to determine which is better suited for traffic control. Image processing techniques combined with GMM enhance vehicle count insights and reduce waiting times compared to the existing non-dynamic traffic control systems.
Density Control Smart Traffic Signal Using Image Processing
23.05.2024
2115550 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Real-Time Area-Based Traffic Density Calculation Using Image Processing for Smart Traffic System
Springer Verlag | 2021
|