Remote Sensing Image Enhancement Technology of UAV Based on Improved GAN

Wu, Guoqiang; Ma, Xiangsen; Huang, Kun; Guo, Haolun

doi:10.1007/978-981-15-4163-6_84

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, choosing a proper value of gamma greatly influences the result. Deep learning-based approaches such as improved GAN (Generative adversarial network) are applied in remote sensing to enhance UAV (Unnamed Ariel Vehicles) images [19]. A multi-view learning approach developed in [18] incorporates local and global enhancement to enhance the contrast in glioblastoma images for accurate medical diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Correcting Low Illumination Images Using PSO-Based Gamma Correction and Image Classifying Method

Das

Roy

Mukhopadhyay

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

In this work, the authors have proposed a method for improving the visual quality of 2D color images suffering from low illumination. The input image is converted to HSV (Hue, Saturation, Value) color space, and the V component is subjected to high pass Laplace filter. The filtered output is then made to undergo a two-stage classifier and a brightness correction process. Finally, the resultant image obtained is gamma-corrected using an optimum gamma value computed using a well-known meta-heuristic based optimization technique namely, particle swarm optimization (PSO). The corrected V component is combined back with the H and S components to reconstruct the final result. The authors have tested this method on a number of 2D color images of natural scenes and the result is found to be satisfactory. Also, the experimental results are compared with similar methods in terms of subjective and objective metrics.

show abstract

Section: Introductionmentioning

confidence: 99%