Histogram Equalization and Lane Detection

This Repository consists of two Projects

Histogram Equalization

Introduction

Histogram is a graphical representation of the intensity distribution of an image. In simple terms, it represents the number of pixels for each intensity value considered. Sometimes, images are taken in very dark or poor lightning conditions. An example of poor exposure image is given below in Fig 1

Poor Exposure Image

Histogram equalisation helps to enhance the intensity level of pixels with poor exposure.It also used to enhance the contrast in the image. The Histogram for above image is shown in Fig 2 and 3

Image after Histogram equalization

Image after Adaptive Histogram equalization

Lane Detection

Bird Eye View

A bird’s-eye view is an elevated view of an object from above, with a perspective as though the observer were a bird. For this I used a constant size "Parking frame" as shown in the Fig. 4 as target area.

Building Frame for Birds Eye View

Then Homography was performed using corners of the above frame and a portrait rectangle.

Birds Eye	Sliding Window

|

Back Propogation

Back projection was done using inverse of previously computed homography matrix H.

Results

Running Instructions

git clone [email protected]:nvnmangla/Lane_detection.git
cd Lane_detection/

To run Histogram

python3 solution.py --isHist=True

Else

python3 solution.py