UAV remote sensing offers numerous advantages such as timeliness, mobility, safety, high resolution, and low cost. However, due to the poor attitude stability of UAV platforms and the influence of weather conditions, UAV remote sensing images commonly suffer from degraded contrast and clarity, making them difficult to directly apply in railway survey and design. To address this widespread degradation in UAV remote sensing images, this paper proposes a fast and effective image enhancement method based on guided filtering combined with histogram matching. The algorithm first corrects image grayscale through block-wise adaptive histogram matching, expanding the dynamic range to enhance contrast and amplify subtle grayscale variations. Subsequently, it applies a guided filter with noise reduction and edge preservation properties to the corrected image based on a local linear model, separating fine details from background noise. Finally, the guided map and filtered map are linearly recombined, with increased weighting applied to the detail layer to produce the enhanced image. Experimental results demonstrate that this method significantly enhances image texture details while reducing noise, outperforming the classic Wallis method in both contrast and information entropy metrics. When applied to image matching, it increases the number of correctly matched points by nearly 1.5 times without compromising matching point accuracy. UAV images optimized by this algorithm can be effectively applied to railway survey and design, offering high practical value.
ZHANGX, LIZ S, PANJ, et al. Spatiotemporal embodied intelligence: a new fusion direction of BeiDou satellite navigation system and high-resolution remote sensing[J]. Geomatics and Information Science of Wuhan University, 2025, 50(9): 1733-1754. (Ch).
YANL, LIAOX H, ZHOUC H, et al. The impact of UAV remote sensing technology on the industrial development of China: a review[J]. Journal of Geo-Information Science, 2019, 21(4): 476-495. (Ch).
HUANGY Q, DINGW R, LIH G. Haze removal method for UAV reconnaissance images based on image enhancement[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43(3): 592-601. (Ch).
LIJ Y, HUQ W, AIM Y, et al. Image haze removal based on sky region detection and dark channel prior[J]. Journal of Image and Graphics, 2015, 20(4): 514-519. (Ch).
YANGJ Y, ZHANGY S, ZOUX L, et al. Using dark channel prior to quickly remove haze from a single image[J]. Geomatics and Information Science of Wuhan University, 2010, 35(11): 1292-1295. (Ch).
LIUX C, YUQ F, LEIZ H. Researches into gray value transform to improve scene matching robustness[J]. Journal of National University of Defense Technology, 2010, 32(3): 48-52. (Ch).
HUC M, XIAG F, ZHANGX, et al. High-precision pose estimation method for close range sequence images of cultural relic objects[J]. Bulletin of Surveying and Mapping, 2022(1): 50-55. (Ch).
GENGL L, SUNQ S, JIZ X, et al. Adaptive enhancement via sparse recognition for automatic control point extraction in high-resolution images[J]. Journal of Image and Graphics, 2014, 19(4): 603-612. (Ch).
YANGY W, WANGM W, GAOX J, et al. Automatic shadow compensation based on improved Wallis model for high resolution remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2021, 46(3): 318-325. (Ch).
RENZ J, LIUX S. Algorithm for color consistency of tile images based on Wallis filter[J]. Journal of Jiangxi University of Science and Technology, 2019, 40(3): 95-102. (Ch).
[25]
HEK M, SUNJ, TANGX O. Guided image filtering[C]// Prolessings of European Conference on Computer Vision, 2010. Berlin, Heidelberg: Springer, 2010:1-14.
[26]
HEK M, SUNJ, TANGX O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.
WANGZ B, MAY K, CUIZ J. Medical image fusion based on guided filtering and sparse representation[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(2): 264-273. (Ch).
YANGZ J, ZENGL. Casting DR image fusion based on weighted least squares filter and guided filter[J]. Chinese Journal of Scientific Instrument, 2021, 42(6): 211-220. (Ch).
[33]
SMITHH, DRAPERN R. Applied regression analysis[M]. 2nd ed. New York: Wiley, 1981.
[34]
HASTIET, FRIEDMANJ, TIBSHIRANIR. The elements of statistical learning[M]. New York: Springer New York, 2001.
YANN, CUIC, WANGX M. Infrared image enhancement based on Gaussian multimodal fitting and histogram normalization[J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2018, 41(3): 115-119. (Ch).
[39]
DURANDF, DORSEYJ. Fast bilateral filtering for the display of high-dynamic-range images[C]//Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques. San Antonio Texas. ACM, 2002: 257-266.
[40]
Visual Geometry Group. Affine covariant region detectors[EB/OL]. [2025-11-26].
[41]
BAY H, TUYTELAARST, VAN GOOLL. SURF: speeded up robust features[C]//Computer Vision-ECCV 2006. Berlin, Heidelberg: Springer, 2006: 404-417.
[42]
FISCHLERM A, BOLLESR C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.