Traffic Prediction for Intelligent Transportation System using Deep Learning

The primary challenge to achieving sustainable mobility is the ongoing traffic of varying intensity and duration within complex transportation networks. Conventional Adaptive Business Signal Control systems are inadequate for effectively managing this type of traffic. Mechanisms grounded on deep literacy have demonstrated their capability to prognosticate issues, thereby enhancing decision- making regarding business duration prognostications. For a long time, deep literacy models have been applied in colorful fields that bear the identification and prioritization of negative factors to simplify mortal life. multitudinous styles are generally employed to address real- time issues arising from business traffic. This exploration illustrates how deep literacy models can address business traffic by regulating business signals grounded on vehicle lengths. Our proposed system combines several strategies aimed at enhancing the effectiveness of the exploration process. In this design, we apply a fashion to identify the volume of vehicles in stoner- handed images and give vehicle counts. For vehicle counting, we use the YOLO pretrained weights. Keywords: Traffic, YOLO, Deep Learning, CNN (Convolution neural network)