Aerial Image
Aerial image analysis focuses on extracting meaningful information from airborne imagery, primarily for applications like geographic localization, environmental monitoring, and infrastructure management. Current research emphasizes developing robust and efficient deep learning models, including transformers and convolutional neural networks, for tasks such as object detection, semantic segmentation, and 3D reconstruction, often incorporating techniques like attention mechanisms and multi-view geometry. These advancements are improving the accuracy and speed of analysis, leading to more effective solutions in diverse fields ranging from urban planning and disaster response to precision agriculture and resource management.
Papers
Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images
Dong Liang, Qixiang Geng, Zongqi Wei, Dmitry A. Vorontsov, Ekaterina L. Kim, Mingqiang Wei, Huiyu Zhou
Centroid-UNet: Detecting Centroids in Aerial Images
N. Lakmal Deshapriya, Dan Tran, Sriram Reddy, Kavinda Gunasekara
Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes
Jiachen Xu, Junlin Guo, James Zimmer-Dauphinee, Quan Liu, Yuxuan Shi, Zuhayr Asad, D. Mitchell Wilkes, Parker VanValkenburgh, Steven A. Wernke, Yuankai Huo
Lebanon Solar Rooftop Potential Assessment using Buildings Segmentation from Aerial Images
Hasan Nasrallah, Abed Ellatif Samhat, Yilei Shi, Xiaoxiang Zhu, Ghaleb Faour, Ali J. Ghandour
MidNet: An Anchor-and-Angle-Free Detector for Oriented Ship Detection in Aerial Images
Feng Jie, Yuping Liang, Junpeng Zhang, Xiangrong Zhang, Quanhe Yao, Licheng Jiao