Low-light image enhancement for UAVs guided by a light weighted map

Xiaotong Bai; Dianwei Wang; Jie Fang; Yuanqing Li; Zhijie Xu

doi:10.1007/s11801-025-4038-4

Low-light image enhancement for UAVs guided by a light weighted map

Xiaotong Bai, Dianwei Wang^*, Jie Fang, Yuanqing Li, Zhijie Xu

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

The unmanned aerial vehicle (UAV) images captured under low-light conditions are often suffering from noise and uneven illumination. To address these issues, we propose a low-light image enhancement algorithm for UAV images, which is inspired by the Retinex theory and guided by a light weighted map. Firstly, we propose a new network for reflectance component processing to suppress the noise in images. Secondly, we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process. Finally, the processed reflectance and illumination components are recombined to obtain the enhancement results. Experimental results show that our method can suppress the noise in images while enhancing image brightness, and prevent over enhancement in bright regions. Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.

Original language	English
Pages (from-to)	348-353
Number of pages	6
Journal	Optoelectronics Letters
Volume	21
Issue number	6
DOIs	https://doi.org/10.1007/s11801-025-4038-4
Publication status	Published - Jun 2025
Externally published	Yes

Keywords

A

Access to Document

10.1007/s11801-025-4038-4

Cite this

@article{0fa9852442d3430880cfa1b032e36526,

title = "Low-light image enhancement for UAVs guided by a light weighted map",

abstract = "The unmanned aerial vehicle (UAV) images captured under low-light conditions are often suffering from noise and uneven illumination. To address these issues, we propose a low-light image enhancement algorithm for UAV images, which is inspired by the Retinex theory and guided by a light weighted map. Firstly, we propose a new network for reflectance component processing to suppress the noise in images. Secondly, we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process. Finally, the processed reflectance and illumination components are recombined to obtain the enhancement results. Experimental results show that our method can suppress the noise in images while enhancing image brightness, and prevent over enhancement in bright regions. Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.",

keywords = "A",

author = "Xiaotong Bai and Dianwei Wang and Jie Fang and Yuanqing Li and Zhijie Xu",

note = "Publisher Copyright: {\textcopyright} Tianjin University of Technology 2025.",

year = "2025",

month = jun,

doi = "10.1007/s11801-025-4038-4",

language = "English",

volume = "21",

pages = "348--353",

journal = "Optoelectronics Letters",

issn = "1673-1905",

number = "6",

}

TY - JOUR

T1 - Low-light image enhancement for UAVs guided by a light weighted map

AU - Bai, Xiaotong

AU - Wang, Dianwei

AU - Fang, Jie

AU - Li, Yuanqing

AU - Xu, Zhijie

N1 - Publisher Copyright: © Tianjin University of Technology 2025.

PY - 2025/6

Y1 - 2025/6

N2 - The unmanned aerial vehicle (UAV) images captured under low-light conditions are often suffering from noise and uneven illumination. To address these issues, we propose a low-light image enhancement algorithm for UAV images, which is inspired by the Retinex theory and guided by a light weighted map. Firstly, we propose a new network for reflectance component processing to suppress the noise in images. Secondly, we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process. Finally, the processed reflectance and illumination components are recombined to obtain the enhancement results. Experimental results show that our method can suppress the noise in images while enhancing image brightness, and prevent over enhancement in bright regions. Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.

AB - The unmanned aerial vehicle (UAV) images captured under low-light conditions are often suffering from noise and uneven illumination. To address these issues, we propose a low-light image enhancement algorithm for UAV images, which is inspired by the Retinex theory and guided by a light weighted map. Firstly, we propose a new network for reflectance component processing to suppress the noise in images. Secondly, we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process. Finally, the processed reflectance and illumination components are recombined to obtain the enhancement results. Experimental results show that our method can suppress the noise in images while enhancing image brightness, and prevent over enhancement in bright regions. Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.

KW - A

UR - http://www.scopus.com/inward/record.url?scp=105004016184&partnerID=8YFLogxK

U2 - 10.1007/s11801-025-4038-4

DO - 10.1007/s11801-025-4038-4

M3 - Article

AN - SCOPUS:105004016184

SN - 1673-1905

VL - 21

SP - 348

EP - 353

JO - Optoelectronics Letters

JF - Optoelectronics Letters

IS - 6

ER -

Low-light image enhancement for UAVs guided by a light weighted map

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this