Adaptive Multi-Scale Fusion Blind Deblurred Generative Adversarial Network Method for Sharpening Image Data

Abstract

Drone and aerial remote sensing images are widely used, but their imaging environment is complex and prone to image blurring. Existing CNN deblurring algorithms usually use multi-scale fusion to extract features in order to make full use of aerial remote sensing blurred image information, but images with different degrees of blurring use the same weights, leading to increasing errors in the feature fusion process layer by layer. Based on the physical properties of image blurring, this paper proposes an adaptive multi-scale fusion blind deblurred generative adversarial network (AMD-GAN), which innovatively applies the degree of image blurring to guide the adjustment of the weights of multi-scale fusion, effectively suppressing the errors in the multi-scale fusion process and enhancing the interpretability of the feature layer. The research work in this paper reveals the necessity and effectiveness of a priori information on image blurring levels in image deblurring tasks. By studying and exploring the image blurring levels, the network model focuses more on the basic physical features of image blurring. Meanwhile, this paper proposes an image blurring degree description model, which can effectively represent the blurring degree of aerial remote sensing images. The comparison experiments show that the algorithm in this paper can effectively recover images with different degrees of blur, obtain high-quality images with clear texture details, outperform the comparison algorithm in both qualitative and quantitative evaluation, and can effectively improve the object detection performance of blurred aerial remote sensing images. Moreover, the average PSNR of this paper’s algorithm tested on the publicly available dataset RealBlur-R reached 41.02 dB, surpassing the latest SOTA algorithm.

High-Resolution Profiling of Atmospheric Turbulence Using UAV Autopilot Data

“…With the Taylor hypothesis of frozen turbulence [33][34][35], we can pass to the spatial longitudinal and lateral correlation functions. Then, it follows from Equations ( 9) and (10) and ξ = Wt that L u and L v have the meaning of the integral longitudinal and lateral scales of turbulence, that is,…”

“…This distance was chosen from safety reasons for the experiment. Let us estimate the drop in the correlation of the wind velocity field at a distance of ~5 m using the Dryden model ( 9) and (10). It follows from Table 5 that the turbulence scales varied from 10 to 17 m depending on the height.…”

“…These scales were estimated by the least square fit method with the Dryden model as the best fit curve. The longitudinal and lateral correlation functions of this model have a simple analytical form described by Equations ( 9) and (10). The turbulence scales are the best fit coefficients when this method is used.…”

“…Such problems include a deterioration in the quality of drone images [10,11] and a deterioration of the communication quality in a quadcopter swarm in the presence of significant wind gusts [12]. In addition, the knowledge of the state of turbulence is decisive in the issue of including various types of UAVs in the Aircraft Meteorological Data Relay (AMDAR) system, one of the main tasks of which is to obtain atmospheric data for numerical weather forecasting (NWP) [13,14].…”

Gradient Structure Information-Guided Attention Generative Adversarial Networks for Remote Sensing Image Generation

“…Since they were proposed by Goodfellow et al, generative adversarial networks have become a popular research direction. A large number of variant structures based on generative adversarial networks have emerged and are widely used in various fields such as image generation, transformation, editing, and super-resolution [27][28][29]. Despite the great success of GANs in various applications, existing methods suffer from the mode collapse problem, which leads to a lack of diversity in the generated images.…”