This paper presents a framework for extracting georeferenced vehicle trajectories from high-altitude drone imagery, addressing key challenges in urban traffic monitoring and the limitations of traditional ground-based systems. Our approach integrates several novel contributions, including a tailored object detector optimized for high-altitude bird's-eye view perspectives, a unique track stabilization method that uses detected vehicle bounding boxes as exclusion masks during image registration, and an orthophoto and master frame-based georeferencing strategy that enhances consistent alignment across multiple drone viewpoints. Additionally, our framework features robust vehicle dimension estimation and detailed road segmentation, enabling comprehensive traffic analysis. Conducted in the Songdo International Business District, South Korea, the study utilized a multi-drone experiment covering 20 intersections, capturing approximately 12TB of 4K video data over four days. The framework produced two high-quality datasets: the Songdo Traffic dataset, comprising approximately 700,000 unique vehicle trajectories, and the Songdo Vision dataset, containing over 5,000 human-annotated images with about 300,000 vehicle instances in four classes. Comparisons with high-precision sensor data from an instrumented probe vehicle highlight the accuracy and consistency of our extraction pipeline in dense urban environments. The public release of Songdo Traffic and Songdo Vision, and the complete source code for the extraction pipeline, establishes new benchmarks in data quality, reproducibility, and scalability in traffic research. Results demonstrate the potential of integrating drone technology with advanced computer vision for precise and cost-effective urban traffic monitoring, providing valuable resources for developing intelligent transportation systems and enhancing traffic management strategies.
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
National College for Excellent Engineers, Beihang University, Beijing, China（北京航空航天大学优秀工程师学院）；School of Computer Science and Engineering, Beihang University, Beijing, China（北京航空航天大学计算机科学与工程学院）；School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China（合肥工业大学计算机科学与信息工程学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室）；Innovation Center for Intelligent System Cognition and Decision-Making, Beijing, China（智能系统认知与决策创新中心）；Information Science Academy of China Electronics Technology Group Corporation, Beijing, China（中国电子科技集团有限公司信息科学研究院）
DeepUrban: Interaction-Aware Trajectory Prediction and Planning for Automated Driving by Aerial Imagery
Department of Electrical Engineering and Information Technology, Intelligent Vehicles Lab (IVL), Munich University of Applied Science（电气工程与信息学院，智能车辆实验室（IVL），慕尼黑应用技术大学）
Understanding Representation Gaps Across Scales in Tropical Tree Species Classification from Drone Imagery
Mila – Quebec AI Institute（魁北克人工智能研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；Cary Institute of Ecosystem Studies（生态系统研究所）；Smithsonian Tropical Research Institute（史密松国家热带研究所）；Department of Plant Sciences, University of Cambridge（剑桥大学植物科学系）；Universidade do Estado do Mato Grosso (UNEMAT)（马托格罗索州立大学（UNEMAT））
Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery
Beihang University（北京航空航天大学）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Detection of Degraded Acacia tree species using deep neural networks on uav drone imagery
The Technical University of Kenya（肯尼亚技术大学）；IRISA（法国国家信息与自动化研究所雷恩分院（IRISA））；Université Bretagne Sud（南布列塔尼大学）
基于深度学习的图像分类和目标检测已成功应用于树木监测。然而，对树冠和倒下的树木的研究，特别是对洪水淹没地区的研究，在很大程度上仍然没有得到探索。由于图像背景的混色性，在自然环境如水、泥滩和自然植被覆盖区域上检测退化的树干具有挑战性。在本文中，无人机（UAV），或无人机，嵌入式RGB摄像头被用来捕捉倒下的相思树从六个指定地块周围纳库鲁湖，肯尼亚。由于需要检测湖泊周围的倒下的树木，两个成熟的深度神经网络，即更快的基于区域的卷积神经网络（更快的R-CNN）和视网膜网络用于倒下的树木检测。本研究共使用了256 x 256图像块上三个类别的7，590个注释。实验结果显示了深度学习在这种情况下的相关性，Retina-Net模型实现了38.9%的准确率和57.9%的召回率。
Zero-shot Shark Tracking and Biometrics from Aerial Imagery
Stanford University（斯坦福大学）；Flinders University（弗林德斯大学）；Centro de Investigación en Ciencias del Mar y Limnología, Universidad de Costa Rica（哥斯达黎加大学海洋与湖沼科学研究中心）
LAF-YOLOv10 with Partial Convolution Backbone, Attention-Guided Feature Pyramid, Auxiliary P2 Head, and Wise-IoU Loss for Small Object Detection in Drone Aerial Imagery
Department of Information Technology（信息科技系）；Department of Computer Science and Engineering（计算机科学与工程系）
From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China
School of Geography and Planning, Sun Yat-Sen University（中山大学地理科学与规划学院）；China Regional Coordinated Development and Rural Construction Institute, Urbanization Institute, Sun Yat-Sen University（中山大学中国区域协调发展与乡村建设研究院、城市化研究院）；Key Laboratory of Rural Digital Technology, Ministry of Housing and Urban-Rural Development（住房和城乡建设部乡村数字化技术重点实验室）；School of Geography and Information Engineering, China University of Geosciences（中国地质大学地理与信息工程学院）
Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping
Shandong University of Science and Technology（山东科技大学）；Technical University of Munich（慕尼黑工业大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；University of Iceland（冰岛大学）
Seed Classification using Synthetic Image Datasets Generated from Low-Altitude UAV Imagery
Kansas State University（堪萨斯州立大学）
植物育种计划广泛地监测种子籽粒的进化以用于种子认证，其中需要按类型和质量适当地标记种子籽粒。然而，育种环境很大，其中由于种子仁的微小尺寸，种子仁的监测可能具有挑战性。无人驾驶飞行器的使用有助于种子监测和标记，因为它们可以在低空拍摄图像，同时能够进入环境中最偏远的地区。使用无人机图像标记种子的关键瓶颈是无人机高度，即由于较低的图像细节，分类精度随着高度的增加而降低。当有一个训练数据集紧密代表网络在评估过程中可能遇到的不同场景时，卷积神经网络是多类图像分类的一个很好的工具。这篇文章解决了使用域随机化创建训练数据的挑战，其中合成图像数据集是从自主驾驶的Parrot AR Drone 2.0的底部相机捕获的种子的微薄样本中生成的。此外，本文提出了一个种子分类框架，作为使用微软的ResNet-100，牛津大学的VGG-16和VGG-19的卷积神经网络的概念验证。为了提高框架的分类精度，集成模型的开发，导致94.6%的整体精度。
An FPGA smart camera implementation of segmentation models for drone wildfire imagery
Tecnologico de Monterrey（蒙特雷科技大学）；Hasso-Plattner Institute, University of Postdam（波茨坦大学哈索·普拉特纳研究所）；Universidad Autonoma de Guadalajara（瓜达拉哈拉自治大学）；Universidad de las Americas Puebla（普埃布拉美洲大学）；Università di Corsica（科西嘉大学）
