基于无人船感知的自适应光照与特征增强算法

邹存龙, 吕正恺, 王宁

doi:10.16411/j.cnki.issn1006-7736.2025.02.011

大连海事大学学报 >

2025 , Vol. 51 >Issue 2: 97 - 105

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2025.02.011

基于无人船感知的自适应光照与特征增强算法

展开

(大连海事大学轮机工程学院，辽宁大连 116026)

邹存龙（1994 — ），男，硕士生。研究方向：图像增强、无人船视觉定位。吕正恺（1991— ），男，博士，讲师，硕士生导师。研究方向：绿色智能船舶，新能源发电。王宁*（1983 — ），男，博士，教授，博士生导师。研究方向：绿色智能船舶、无人艇自主控制，E-mail:n.wang@ieee.org。

网络出版日期: 2025-02-09

基金资助

国家高层次人才支持计划项目（SQ2022QB00329）、国家自然科学基金项目（U23A20680、52271306）、国防基础科研计划一般项目基础前沿寻宝项目（JCKY2022410C013）、辽宁省“兴辽英才计划”领军人才项目（XLYC2202005）、大连市科技创新基金重大基础研究项目（2023JJ11CG009）、中央高校基本科研业务费专项资金项目（3132023501）。

收起

Adaptive illumination enhancement and feature enhancement algorithm based on unmanned surface vehicle perception

Expand

（College of Marine Engineering, Dalian Maritime University, Dalian 116026,China）

Online published: 2025-02-09

Fold

摘要

针对无人船自主航行过程中因光照不均匀及感知图像纹理模糊而导致的特征点匹配失败问题，本文提出了一种自适应校正与特征增强图像预处理算法。首先使用了非锐化掩蔽，起到了增强图像细节的效果，随后通过多尺度高斯卷积在亮度通道提取光照分量，并使用了二维伽马校正起到了均匀化亮度的效果，对色调通道使用了高斯滤波，起到了抑制低通噪声的效果，最后使用了直方图均匀化算法，起到了提升图像对比度的效果。相比于MSR算法、MSRCR算法和SSR算法，本文算法平均梯度最多分别提高了50.55%、151.21%和43.68%，特征匹配准确度最多分别提升了86.81%、176.08%和61.96%。本研究成果为无人船自主航行中的视觉感知图像提供了预处理技术，提升了图像质量，具有一定的应用价值。

关键词： 无人船; 光照不均匀; 二维伽马函数; 多维高斯函数; 特征点匹配

本文引用格式

邹存龙, 吕正恺, 王宁 . 基于无人船感知的自适应光照与特征增强算法[J]. 大连海事大学学报, 2025 , 51(2) : 97 -105 . DOI: 10.16411/j.cnki.issn1006-7736.2025.02.011

Abstract

This paper proposes an adaptive correction and feature enhancement image preprocessing algorithm to address the problem of feature point matching failure caused by uneven lighting and blurry perceived image texture during autonomous navigation of unmanned ships. Firstly, Unsharp Masking was used to enhance image details. Then, multi-scale Gaussian convolution was used to extract lighting components in the brightness channel, and two-dimensional gamma correction was used to homogenize brightness. Gaussian filtering was applied to the tone channel to suppress low-pass noise. Finally, histogram homogenization algorithm was used to improve image contrast. Compared with the MSR algorithm, MSRCR algorithm, and SSR algorithm, the average gradient of this algorithm has increased by up to 50.55%, 151.21%, and 43.68% respectively, and the feature matching accuracy has increased by up to 86.81%, 176.08%, and 61.96% respectively. This research provides preprocessing techniques for visual perception images in autonomous navigation of unmanned ships, improving image quality and having certain application value.

Key words： unmanned surface vehicle; uneven illumination; two-dimensional gamma function; multi dimensional gaussian function; feature point matching

参考文献

[1]WANG N, ZHANG Y, AHN C K, et al. Autonomous pilot of unmanned surface vehicles: Bridging path planning and tracking[J]. IEEE Transactions on Vehicular Technology, 2021, 71(3): 2358-2374.
[2]何红坤, 王宁. 欠驱动无人船单目视觉伺服镇定控制[J]. 中国舰船研究, 2022, 17(5): 166-174, 183.
HE H K, WANG N. Underactuated unmanned ship monocular visual servo stabilization control[J]. Chinese Journal of Ship Research, 2022, 17(5): 166-174, 183. (in Chinese)
[3]WANG N, HE H. K Dynamics-level finite-time fuzzy monocular visual servo of an unmanned surface vehicle[J]. IEEE Transactions on Industrial Electronics, 2019, 67(11): 9648-9658.
[4]郭强, 王嘉琪, 张显库, 等. 基于 BLF 的浅水效应下无人船自适应路径跟踪控制[J]. 中国舰船研究, 2024.
GUO Q, WANG J Q, ZHANG X K, et al. Adaptive Path Tracking Control of Unmanned Ships under Shallow Water Effect Based on BLF [J]. Chinese Journal of Ship Research, 2024. (in Chinese)
[5]WANG N, HE H K, HOU Y, et al. Model-free visual servo swarming of manned-unmanned surface vehicles with visibility maintenance and collision avoidance[J]. IEEE Transactions on Intelligent Transportation Systems, 2023.
[6]LAND E H, MCCANN J J. Lightness and retinex theory[J]. Josa, 1971, 61(1): 1-11.
[7]GOPAL M, YEDULAPURAM S, KOMMABATLA M. Single scale RETINEX algorithm for low light image enhancement[C]//AIP Conference Proceedings. AIP Publishing, 2024, 2971(1).
[8]WANG X X, YI R, SUN M Y, et al. Low-light Image Enhancement Algorithm Based on Improved Multi-scale Retinex with Adaptive Brightness Compensation[C]//2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, 2024: 2234-2239.
[9]PARTHASARATHY S, SANKARAN P. An automated multi scale retinex with color restoration for image enhancement[C]//2012 National Conference on Communications (NCC). IEEE, 2012: 1-5.
[10]DHAL K G, DAS A, RAY S, et al. Histogram equalization variants as optimization problems: a review[J]. Archives of Computational Methods in Engineering, 2021, 28: 1471-1496. Zuiderveld K. Contrast limited adaptive histogram equalization[M]Graphics gems IV. 1994: 474-485.
[11]HU C S, LI H, MA T, et al. An improved image enhancement algorithm: Radial contrast-limited adaptive histogram equalization[J]. Multimedia Tools and Applications, 2024: 1-13.
[12]CHANG Y K, JUNG C K, KE P, et al. Automatic contrast-limited adaptive histogram equalization with dual gamma correction[J]. IEEE Access, 2018, 6: 11782-11792.
[13]WEI C, WANG W J, YANG W H, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv preprint arXiv, 2018,1808:04560.
[14]HAI J, XUAN Z, YANG R, et al. R2rnet: Low-light image enhancement via real-low to real-normal network[J]. Journal of Visual Communication and Image Representation, 2023, 90: 103712.
[15]张航瑛,王雪琦,王华英,等.基于明度分量的Retinex-Net图像增强改进方法[J].物理学报,2022,71(11):107-115.
ZHANG H Y,WANG X Q,WANG H Y, et al. Improved Retinex Net image enhancement method based on brightness component[J]. Acta Physica Sinica, 2022,71(11):107-115. (in Chinese)
[16]张金泽, 赵红, 王宁, 等. 密集障碍物下无人艇模糊双窗口 DWA 避障算法[J]. 中国舰船研究, 2021, 16(6): 10-18.
ZHANG J Z, ZHAO H, WANG N, et al. Fuzzy dual window DWA obstacle avoidance algorithm for unmanned boats under dense obstacles[J]. Chinese Journal of Ship Research, 2021, 16(6): 10-18. (in Chinese)
[17] WANG N, GAO Y, ZHANG X. Data-driven performance-prescribed reinforcement learning control of an unmanned surface vehicle[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(12): 5456-5467.
[18] KONG X Y, LIU L, QIAN Y S. Low-light image enhancement via poisson noise aware retinex model[J]. IEEE Signal Processing Letters, 2021, 28: 1540-1544.
[19]刘志成,王殿伟,刘颖,等.基于二维伽马函数的光照不均匀图像自适应校正算法[J].北京理工大学学报,2016,36(2):191-196+214.
LIU Z C, WANG D W, LIU Y, et al. Adaptive correction algorithm for uneven illumination images based on two-dimensional gamma function[J]. Journal of Beijing Institute of Technology,2016,36(2):191-196+214.(in Chinese)
[20] LEE S, KWON H, HAN H, et al. A space-variant luminance map based color image enhancement[J]. IEEE Transactions on Consumer Electronics, 2010, 56(4): 2636-2643.
[21]BOVCON, BORJA, JON MUHOVIČ, et al. "Stereo obstacle detection for unmanned surface vehicles by IMU-assisted semantic segmentation."Robotics and Autonomous Systems , 2018,104: 1-13.
[22]赵瑞祥,畅海峰,白晓勇,等.面向无人船感知的低对比度水面图像增强方法[J].舰船科学技术,2023,45(14):83-89.
ZHAO R X,CHANG H F,BAI X Y, et al. Low contrast water surface image enhancement method for unmanned ship perception[J]. Ship Science and Technology,2023,45(14):83-89.
[23]胡瀚文,王猛,程卫平,等.水下视觉SLAM的图像滤波除尘与特征增强算法[J].机器人,2023,45(2):197-206.
HU H W, WANG M, CHENG W P, et al. Image filtering, dust removal, and feature enhancement algorithm for underwater visual SLAM[J]. Robot,2023,45(2):197-206.
[24]黄静,欧余韬.光照不均匀条件下无人机航拍低照度图像增强方法[J].现代电子技术,2025,48(1):55-59.
HUANG J, OU Y T. Enhancement method for low light images captured by unmanned aerial vehicles under uneven lighting conditions[J]. Modern Electronic Technology,2025,48(1):55-59.
[25]LUO C, YANG W, HUANG P, et al. Overview of image matching based on ORB algorithm[C]//Journal of Physics: Conference Series. IOP Publishing, 2019, 1237(3): 032020.
[26]JAKUBOVIĆ A, VELAGIĆ J. Image feature matching and object detection using brute-force matchers[C]//2018 International Symposium ELMAR. IEEE, 2018: 83-86.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献