Skip to content

Latest commit

 

History

History
39 lines (28 loc) · 1.87 KB

README.md

File metadata and controls

39 lines (28 loc) · 1.87 KB
Raw

Smart-Traffic-Junction

This repository contains the working implementation of our research paper link. The paper was presented and published at IEEE PuneCon 19 conference. We propose 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.

Algorithm

Please go through our paper paper link.

Results of the traffic density algorithm

System Architecture

System Architecture of smart traffic junction

Video Demo

Smart management and Remote monitoring

Files in this repo

  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

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