Traffic Congestion Prediction using Deep Convolutional Neural Networks: A Color-coding Approach

TL;DR

This paper introduces a novel traffic congestion prediction method that transforms video data into color-coded images and employs deep convolutional neural networks for classification, achieving high accuracy.

Contribution

It presents a unique color-coding scheme for traffic video classification combined with deep learning, enhancing congestion prediction accuracy.

Findings

Achieved 98.2% classification accuracy on UCSD dataset.

Utilized YOLO for vehicle detection before classification.

Demonstrated effectiveness of color-coding in traffic video analysis.

Abstract

The traffic video data has become a critical factor in confining the state of traffic congestion due to the recent advancements in computer vision. This work proposes a unique technique for traffic video classification using a color-coding scheme before training the traffic data in a Deep convolutional neural network. At first, the video data is transformed into an imagery data set; then, the vehicle detection is performed using the You Only Look Once algorithm. A color-coded scheme has been adopted to transform the imagery dataset into a binary image dataset. These binary images are fed to a Deep Convolutional Neural Network. Using the UCSD dataset, we have obtained a classification accuracy of 98.2%.