Smart-Traffic-Junction

This repository contains the working implementation of the paper link. A simple algorithm for traffic density estimation using image processing and machine learning.

HOG, LBP and SVM based Traffic Density Estimation at Intersection
Devashish Prasad, Ayan Gadpal, Kshitij Kapadni, Manish Visave,

Dataset

The dataset was created using QMUL junction 2 video. We manually sorted the rois of the dataset.

Files

1. save_rois.py : saves ROIs (small blocks of image) from the QMUL junction 2 video
   
2. save_HOG_LBP.py : saves the HOG(Histogram of Oriented Gradients) and LBP(Local Binary Pattern) features into pickle file
3. classifier.py : trains the SVM classifier and saves the model into pickle
4. predictor.py : reads the video and predicts the output on the image

System Architecture

Results

Contact

Devashish Prasad : devashishkprasad [at] gmail [dot] com
Ayan Gadpal : ayangadpal2 [at] gmail [dot] com
Kshitij Kapadni : kshitij.kapadni [at] gmail [dot] com
Manish Visave : manishvisave149 [at] gmail [dot] com