Abstract: Traffic congestion not only. Affecting the human being, but also elevates the pollution .The most important causes that increase traffic congestion are lack of planning of city road, using vehicle widely .Traffic monitering has only the manual algorithm that is the man power. In manual use we can only able to analysis the vehicles in one particular direction, so the accident or vehicles that passing through the another road or side can’t be captured .Vehicle speed estimation used to calculate the speed in each image frame by using the vehicle position in each image frame .In this process it is possible to widely apply deep learning method to the analysis of traffic surveillance video. Traffic flow prediction ,anomaly detection, vehicles re-identification and vehicle tracking are basic components in traffic analysis. Among the application traffic flow prediction or vehicle speed estimation is one of the most important research topics of recent years .This project proposed the convolution neural network algorithm and hard clustering method will used to calculate the speed estimation. By using this process it will collect the details of the vehicles types, speed of the vehicle and vehicle detection.
Keywords: Machine Learning, Traffic monitering, Anomaly detection
|
DOI:
10.17148/IJARCCE.2022.11640
