Bi-dimensional Empirical Mode Decomposition Based Contrast Enhancement Technique for UAV Thermal Images

Abstract

In this paper, a new contrast enhancement technique based on bi-dimensional empirical mode decomposition (BEMD) is proposed to enhance the target details in low contrast thermal images captured by unmanned aerial vehicle (UAV). Initially, thermal image acquired from UAV is separated into intrinsic mode functions (IMFs) and residue using BEMD. Then, local standard deviation based method is employed to the IMFs to improve the details of the image and histogram modification function is employed to the residue to enhance the contrast. The processed IMFs and residue are reconstructed to obtain the enhanced image using inverse BEMD. The performance of the proposed technique is analysed using quantitative and visual quality measures with the well-known histogram equalization, dynamic range partitioning and wavelet-based enhancement methods. Experimental results demonstrate that the proposed technique effectively enhances the contrast and details in the image with less noise and visual artefacts than other methods.

KEYWORDS:

• Bi-dimensional empirical mode decomposition
• Histogram modification function
• Smoothing function
• Thermal image enhancement
• Unmanned aerial vehicle
• Unmanned aerial vehicle surveillance image

Additional information

Notes on contributors

R. Thillainayagi

R. Thillainayagi received her BE degree in electronics and communication engineering and ME degree in avionics at Anna University, Chennai, India in 2008 and 2010, respectively. At present, she is pursuing her PhD in Avionics division of Aerospace Engineering Department at Madras Institute of Technology of Anna University, Chennai, India. Her field of interest includes digital image processing, avionics and data fusion. Corresponding author. E-mail: [email protected]

K. Senthil Kumar

K Senthil Kumar received his BE degree in electrical and electronics engineering, ME degree and PhD in avionics at Anna University, Chennai, India. He is working as associate professor at the Department of Aerospace Engineering in Madras Institute of technology of Anna University Chennai, India. He is an entrepreneurial scientist and with his years of eminent research he developed an Unmanned Aerial System named as Dhaksha in MIT campus which is the first of its kind for the use of civilian law enforcement agencies in India. His field of interest includes unmanned vehicle design, control, dynamics and video signal processing.E-mail: [email protected]