Enhancement of Night Vision Images

20 Ott 2014
Enhancement of algorithms for Night Vision of Traffic Images
Voti totali: 0
Enhancement of algorithms for Night Vision of Traffic Images

Abstract

The porpose of our topic is to improve night images taken from a traffic control company. The field of engagement is traffic, infact we are interested in recognizing cars license plates and vehicles shapes. 

The used method are the following:

- histogram equalization;

-adaptive histogram equalization;

-clipping level adaptive histogram equalization;

- retinex;

-ace.

Finally we propose a comparison between the different used methods and we underline the advantages and disadvantages of each one.

References: 

[1]WANG Zhiming, TAO Jianhua, School of Information Engineering, University of Science and Technology Beijing, Beijing China 100083, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing China 100080, A fast Implementation of Adaptive Histogram Equalization
[2] Rizzi A., Gatta C., and Marini D., From retinex to automatic color equalization: issues in developing a new algorithm for unsupervised color equalization J. of Electronic Imaging, 75-84 (2004)
[3] Pascal Getreuer, CMLA, ENS Cachan, France, Automatic Color Enhancement (ACE) and its Fast Implementation