Concealed Weapon Detection using Wavelet, Dual Tree Complex Wavelet Transform and Curvelet Transform

Ayush Dogra,Renu Vig,Sunil Agrawal,Bhawna Goyal,Apoorav Maulik Sharma

doi:10.3844/jcssp.2018.1341.1350

Abstract

In the field of military and law enforcement, detection and visualization of concealed weapons is a common practice. The infrared and visible cameras providing the information i.e., the characteristic visual features of the image and the thermal radiations are able to provide the complementary information like information about concealed objects or weapons. In this manuscript, we have proposed the integration of visible and infrared images of a scene using curvelet, wavelet and Dual Tree Complex Wavelet transform (DTCWT) with their brief introduction and background. The quantitative and visual results obtained from three techniques are compared and they reveal that DTCWT can be efficiently employed as an efficient image fusion tool in the context of concealed weapon detection.

Highlights

Infrared and Visible sensors acquire the complementary information about the scene under consideration
The source images have to be represented in an efficient manner in order to obtain a high quality fused images. Keeping this in mind, we propose the fusion of multi-sensory, infrared and visible image fusion for concealed weapon detection using Discrete Curvelet, Discrete Wavelet and Dual Tree Complex Wavelet Transform
Dual Tree Complex Wavelet transform (DTCWT) based image fusion technique has been analysed for concealed weapon detection

Summary

Introduction

Infrared and Visible sensors acquire the complementary information about the scene under consideration. The source images have to be represented in an efficient manner in order to obtain a high quality fused images Keeping this in mind, we propose the fusion of multi-sensory, infrared and visible image fusion for concealed weapon detection using Discrete Curvelet, Discrete Wavelet and Dual Tree Complex Wavelet Transform. Dual- Tree Complex Wavelet Transform (DTCWT) came as a solution to these problems but, directionality was still limited (Kingsbury, 2006) To surmount such limitations, Ridgelet and Ripplet Transform based parabolic scaling low was given (http://www.numericaltours.com/matlab/wavelet_3_daubechies1d/). The only difference being that in DTCWT 6 sub-bands are generated and in wavelet 3 sub-bands are generated These sub-bands are fused separately using averaging fusion rule and fused image is reconstructed

Results and Discussion

Objective evaluation

Conclusion