Wavelet energy-based adaptive retinex algorithm for low light mobile video enhancement

Abstract

ABSTRACTOur paper presents an adaptive multiscale retinex algorithm and a new wavelet energy metric to improve low-light video captured on mobile devices. Initially, we extract RGB frames from the video and convert them to hue-saturation-value (HSV) format, preserving the hue channel to prevent common RGB colour shifting issues. Saturation channel enhancement is achieved through histogram equalization (HE), extending the dynamic range. The adaptive retinex algorithm enhances the value channel, quantified by our new wavelet energy metric. Combining the modified value and saturation channels improves the contrast of the reconstructed image. As a final step, we transform the HSV video back to RGB and restore naturalness using a modified colour restoration technique. The proposed approach has been tested on over 300 images and videos. It is evident from the experimental results presented that the proposed method lowers noise and halo artifacts more effectively than existing methods.KEYWORDS: Low light enhancementmobile videoHSV colour spaceadaptive multiscale retinexwavelet energy Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsG. R. VishalakshiVishalakshi G. R. completed a Bachelor of Engineering (B. E) in Electronics and Communication and a Masters of Technology (M. Tech) in Digital Electronics from Visvesvaraya Technological University (VTU), Belagavi, Karnataka, India, in the years 2005 and 2012, respectively and Pursuing Ph.D. in VTU under the guidance of A. Shobharani on video enhancement technique. Her research interest is in subjects like image and video processing, VLSI, and CNN.A. ShobharaniA. Shobha Rani received her B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2000, M. Tech (Digital Electronics and Communication) Degree from Visveswaraya Technological University (VTU), Belgaum in the year 2005, and Ph. D. (Networking) degree from Kuvempu University, Shimoga, in the year, 2014. She works as an Associate Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. She has 23 technical articles in well-reputed journals and conferences. Her research interests include designing and implementing efficient protocols for wireless networks such as Ad hoc, Sensor, and Mesh networks.M. C. HanumantharajuM. C. Hanumantharaju received his B. E (Electronics and Communication Engineering) degree from Bangalore University in the year 2001, M. Tech (Digital Communication and Network Engineering) degree from Visvesvaraya Technological University (VTU), Belagavi in the year 2004, and Ph. D (VLSI Signal and Image Processing) degree from VTU, Belagavi, in the year, 2014. He works as a Professor in the Department of ECE at BMS Institute of Technology and Management, Bengaluru, India. He has authored two books and 50 technical articles in refereed journals and proceedings such as IEEE, Intelligent Systems, Particle Swarm Optimization, etc. He is currently a reviewer for IEEE Transactions on Industrial Electronics, Computers and Electrical Engineering Journal, Journal of Microscopy and Ultrastructure, etc. His research interests include the Design of hardware architectures for signal and image processing algorithms, computer vision, Register Transfer Level (RTL) Verilog coding, synthesis and optimization of Integrated Circuits (ICs), and FPGA/ASIC Design.