Article Details

Abstract

To mitigate the impact of large field of view and non-uniform illumination on image quality, this paper proposes an adaptive enhancement algorithm for non-uniform illumination images with large field of view. Firstly, based on the illumination V-component in the HSV image domain, it calculates the light component of the V-component according to the proposed dynamic weighted white balance method. Then, combining the texture features of the V-component, an adaptive two-dimensional Gamma function is proposed to adjust the image V-channel value. Finally, the H-component, S-component and V-component are fused and adaptive image enhancement is realized. The experimental results show that the proposed method increases the average contrast of three types of object images of car, train, and truck images by 46%, improves average clarity by a factor of 4.23, and boosts average information entropy by 12%. This effectively enhances overall image quality.

Keywords

vehicle chassis image enhancement; non-uniform illumination image with large field of view; dynamic weighted illumination estimate; two-dimensional Gamma function; dynamic white balance

References

1. [1] Zhou Yifan, Yang Zhiwei, Wang Yueyang, etc Design of a cloud based mobile intelligent vehicle bottom hidden object detection system [J]. Journal of Jilin University (Information Science Edition), 2025, 43 (4): 903-912
2. [2] Ma Long, Ma Tengyu, Liu Risheng Overview of Low Light Image Enhancement Algorithms [J]. Chinese Journal of Image and Graphics, 2022, 27 (5): 1392-1409
3. [3] DENG W T，XIE G F. Image Contrast Enhancement and Brightness Preservation Based on an Adaptive Histogram Correction Framework [J].Applied Optics，2025，64（13）：3502-3515.
4. [4] PAUL A. Adaptive Tri-plateau Limit Tri-histogram Equalization Algorithm for Digital Image Enhancement [J].The Visual Computer，2021，39（1）：297-318.
5. [5] ACHARYA U K，KUMAR S. Image Sub-division and Quadruple Clipped Adaptive Histogram Equalization （ISQCAHE） for Low Exposure Image Enhancement [J].Multidimensional Systems and Signal Processing，2022，34（1）：25-45.
6. [6] FENG T，LI H，MA H G. Adaptively spatial PSF Removal Enables Contrast Enhancement for Multi-layer Image Fusion in Photoacoustic Microscopy [J].Optics Letters，2024，49（24）：7146-7149.
7. [7] YI X P，XU H，ZHANG H，et al. Diff-Retinex++: Retinex-driven Reinforced Diffusion Model for Low-light Image Enhancement [J].IEEE transactions on Pattern Analysis and Machine Intelligence，2025，47（8）：6823-6841.
8. [8] JIANG K S，ZHU C B，YANG J B. Research on Low-light Environment SLAM System via Retinex Enhancement and Deep Feature Optimization [J].IEEE Sensors Journal，2025，25（15）：29992-30004.
9. [9] LI Q S，DONG B Y，MENG X. Digital Media Image Colour Enhancement Processing Method Based on Multi-scale Retinex [J].International Journal of Computational Intelligence Studies，2024，13（1/2）：23-39.
10. [10] Guo Cheng, Hu Xiaoping, Peng Xiangqian, etc Improved Transparent Object Backlight Image Enhancement Algorithm for MSRCR [J]. Journal of Sensing Technology, 2024, 37 (4): 645-651
11. [11] YADAV P S，GUPTA B，LAMBA S S. A New Approach of Image Contrast Enhancement Based on Entropy Curve [J].Signal，Image and Video Processing，2024，18（4）：3431-3444.
12. [12] Wu Yahong Research on Enhancement Algorithm for Uneven Low Illumination and Low Quality Images [D]. Nanjing: Nanjing University of Posts and Telecommunications, 2021

Funding

Key Laboratory Project of the Ministry of Natural Resources (NRMSSHR2023Y16)

About the authors

Li Jian (1985-), male, Han ethnicity, from Huanggang, Hubei, is a senior engineer and doctoral student. His research direction is pattern recognition and intelligent systems.