A real-time low-light enhancement algorithm for intelligent analysis

Images captured by sensors in unpleasant environment like low illumination condition are usually degraded, which means low visibility, low brightness, and low contrast. In order to improve this kind of images, in this paper, a low-light sensor image enhancement algorithm based on HSI color model is proposed. At first, we propose a dataset generation method based on the Retinex model to overcome the shortage of sample data. Then, the original low-light image is transformed from RGB to HSI color space. The segmentation exponential method is used to process the saturation (S) and the specially designed Deep Convolutional Neural Network is applied to enhance the intensity component (I). At the end, we back into the original RGB space to get the final improved image. Experimental results show that the proposed algorithm not only enhances the image brightness and contrast significantly, but also avoids color distortion and over-enhancement in comparison with some other state-of-the-art research papers. So, it effectively improves the quality of sensor images.

Download Full-text

FPGA Implementation of Real-Time Adaptive Bidirectional Equalization for Histogram

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.461.215 ◽

2012 ◽

Vol 461 ◽

pp. 215-219

Author(s):

Yu Qian Zhao ◽

Zhi Gang Li

Keyword(s):

Image Processing ◽

Real Time ◽

Processing Speed ◽

Local Maximum ◽

Histogram Equalization ◽

Infrared Images ◽

Single Frame ◽

Processing Effects ◽

Simulation Results ◽

Enhancement Algorithm

According to the characteristics of infrared images, a contrast enhancement algorithm was presented. The principium of FPGA-based adaptive bidirectional plateau histogram equalization was given in this paper. The plateau value was obtained by finding local maximum and whole maximum in statistical histogram based on dimensional histogram statistic. Statistical histogram was modified by the plateau value and balanced in gray scale and gray spacing. Test data generated by single frame image, which was simulated by FPGA-based real-time adaptive bidirectional plateau histogram equalization. The simulation results indicates that the precept meet the requests well in both the image processing effects and processing speed

Download Full-text

Computationally efficient contrast enhancement algorithm suitable for real-time digital hardware

10.1117/12.562763 ◽

2004 ◽

Author(s):

Douglas R. Droege ◽

John J. Forsthoefel ◽

Russell C. Hardie

Keyword(s):

Contrast Enhancement ◽

Real Time ◽

Computationally Efficient ◽

Digital Hardware ◽

Enhancement Algorithm

Download Full-text

A Wavelet-Based Image Enhancement Algorithm for Real Time Multi-resolution Texture Mapping

Virtual Reality - Lecture Notes in Computer Science ◽

10.1007/978-3-540-73335-5_2 ◽

2007 ◽

pp. 13-21

Author(s):

Hai-feng Cui ◽

Xin Zheng

Keyword(s):

Real Time ◽

Image Enhancement ◽

Texture Mapping ◽

Enhancement Algorithm

Download Full-text

Perceptual Quality Assessment of Low-light Image Enhancement

ACM Transactions on Multimedia Computing Communications and Applications ◽

10.1145/3457905 ◽

2021 ◽

Vol 17 (4) ◽

pp. 1-24

Author(s):

Guangtao Zhai ◽

Wei Sun ◽

Xiongkuo Min ◽

Jiantao Zhou

Keyword(s):

Image Quality ◽

Quality Assessment ◽

Image Enhancement ◽

Dynamic Range ◽

State Of The Art ◽

Perceptual Quality ◽

Low Light ◽

Light Image ◽

Light Enhancement

Low-light image enhancement algorithms (LIEA) can light up images captured in dark or back-lighting conditions. However, LIEA may introduce various distortions such as structure damage, color shift, and noise into the enhanced images. Despite various LIEAs proposed in the literature, few efforts have been made to study the quality evaluation of low-light enhancement. In this article, we make one of the first attempts to investigate the quality assessment problem of low-light image enhancement. To facilitate the study of objective image quality assessment (IQA), we first build a large-scale low-light image enhancement quality (LIEQ) database. The LIEQ database includes 1,000 light-enhanced images, which are generated from 100 low-light images using 10 LIEAs. Rather than evaluating the quality of light-enhanced images directly, which is more difficult, we propose to use the multi-exposure fused (MEF) image and stack-based high dynamic range (HDR) image as a reference and evaluate the quality of low-light enhancement following a full-reference (FR) quality assessment routine. We observe that distortions introduced in low-light enhancement are significantly different from distortions considered in traditional image IQA databases that are well-studied, and the current state-of-the-art FR IQA models are also not suitable for evaluating their quality. Therefore, we propose a new FR low-light image enhancement quality assessment (LIEQA) index by evaluating the image quality from four aspects: luminance enhancement, color rendition, noise evaluation, and structure preserving, which have captured the most key aspects of low-light enhancement. Experimental results on the LIEQ database show that the proposed LIEQA index outperforms the state-of-the-art FR IQA models. LIEQA can act as an evaluator for various low-light enhancement algorithms and systems. To the best of our knowledge, this article is the first of its kind comprehensive low-light image enhancement quality assessment study.

Download Full-text