Results 241 to 250 of about 57,062 (333)
Water Resources Research, Volume 62, Issue 1, January 2026.Abstract Drought significantly affects water resources, agriculture, energy, and ecosystems, revealing enduring socio‐economic vulnerabilities over the centuries. This review synthesizes a century of development and recent advances in drought research (1900–2023), drawing on a bibliometric analysis of over 152,000 peer‐reviewed publications. The review
Amitesh Sabut, Ashok Mishra
wiley +1 more source
A Joint Network of Edge-Aware and Spectral-Spatial Feature Learning for Hyperspectral Image Classification. [PDF]
Sensors (Basel)Zheng J +6 more
europepmc +1 more source
IET Cyber-Physical Systems: Theory &Applications, Volume 11, Issue 1, January/December 2026.This study presents an autonomous rover for real‐time weed detection in agriculture using advanced YOLO object detection models. Experimental results show that YOLOv9‐E achieves the highest accuracy among all models, whereas YOLOv8 variants offer faster processing, demonstrating their potential for efficient and precise weed management in the field ...
Md Shahriar Hossain Apu, Suman Saha
wiley +1 more source
Residual channel attention based sample adaptation few-shot learning for hyperspectral image classification. [PDF]
Sci RepZhao Y, Sun J, Hu N, Zai C, Han Y.
europepmc +1 more source
IET Image Processing, Volume 20, Issue 1, January/December 2026.This paper proposes a low‐light image enhancement and denoising algorithm tailored for tunnel scenes based on computer vision and deep learning technologies. On this basis, a tunnel pedestrian detection method based on connected domain dynamic threshold segmentation is designed, which can reduce the computational resources for identifying pedestrian ...
Yudan Tian +4 more
wiley +1 more source
Advanced Global Prototypical Segmentation Framework for Few-Shot Hyperspectral Image Classification. [PDF]
Sensors (Basel)Xia K +5 more
europepmc +1 more source
IET Image Processing, Volume 20, Issue 1, January/December 2026.This paper introduces the residual attention smoothing mixup network (RASMN) for tube image classification, which integrates residual blocks and attention mechanisms for effective feature extraction. To address overfitting with small datasets, RASMN incorporates label smoothing and mixup data augmentation, demonstrating superior performance on oil ...
Lijuan Zhu +5 more
wiley +1 more source
Dynamic weighted residual ensemble learning for hyperspectral image classification driven by features and samples. [PDF]
HeliyonWang J, Yang G, Lu H.
europepmc +1 more source