Aerial image deblurring is a vital challenge in drone vision systems, where Gaussian, motion, and out-of-focus blurs significantly lowering the image quality and the quality of subsequent analysis. Standard deblurring algorithms usually implement one method uniformly in all situations without recognizing the type of blur. To address this issue, we introduce ROBIN (Rule, Based Optimization for Blur Identification and Neutralization), a hybrid deblurring system that identifies blur types and uses appropriate restoration methods. Our model uses a deep learning, based classifier to decide which of the three blur categories the input image belongs to. After the classification, a rule-based controller assigns each image to the respective restoration method: Total Variation, regularized Wiener deconvolution for Gaussian blur, Particle Swarm Optimization, augmented Richardson, Lucy deconvolution for motion blur, and Genetic Algorithm, tuned blind deconvolution for out of focus blur. Such a modular and adaptive system not only makes the process computationally efficient but also allows a high degree of restoration fidelity. A wide range of experiments under PSNR, SSIM, MSE, RMSE, and entropy metrics confirm that the proposed method is better than the traditional and state of the art methods in all blur categories in terms of clarity, detail retention, and robustness. ROBIN is an efficient solution for real-time aerial imaging use cases in environmental monitoring, surveillance, and disaster response missions. Experimental results show that the proposed method achieves a PSNR of 31.26 dB, SSIM of 0.94, and Entropy of 8.98, which is far superior to all the state-of-the-art approaches.
Shankramma S. Dhavalagimath, T. M. Rajesh, K. Madhura et al.· International Journal of Com...· 0 citations
Crop diseases pose significant challenges to productivity in resource-constrained settings, often remaining undiagnosed when diagnostic tools and infrastructure are either non-existent or inadequate. Current crop disease diagnosis relies on manual inspection methods that are labor-intensive, prone to error, and incapable of delivering real-time or region-specific insights in the process. Such limitations call for developing advanced diagnostic systems that are scalable and efficient in resource-constrained settings. This research introduced a comprehensive multi-spectral imaging and machine learning framework that can easily revolutionize the disease diagnosis and management inside the low-resource farming communities. Built within its core is the 3D Spectral-Spatial Convolutional Neural Network (3D SSCNN) that extracts high-resolution spectral-spatial features from hyperspectral image cubes. The accuracy achieved is around ~ 95% within 0.3 s per sample. Fed-DiagNet has provided support for distributed training that enables scalability and also data privacy to enhance the accuracy of regional models at approximately 92% as well as reduces training by almost 40%. Temporal disease progression modeling is enabled by Temporal Progression LSTM that provides dynamic trends with 90% accuracy up to a horizon of 10 days. This means that in addition to integrating disparate data sources-including hyperspectral imagery, environmental data, and pest observations-MTAN achieves an almost ~ 93% stress identification accuracy. Lastly, an RL-FO system tailors its treatment recommendations to local conditions so as to optimize for yield improvement and cost-effectiveness. With the proposed system, diagnostic precision increases to ~ 94%, and it is manifested in real-time efficiency while supporting scalability with actionable insights to empower farmers to mitigate crop losses and augment food security across several scenarios.
J. Sastry, Pannangi Naresh, A. Ayesha et al.· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
