计算机科学
遥感
水准点(测量)
最小边界框
像素
目标检测
探测器
跳跃式监视
战场
人工智能
实时计算
计算机视觉
图像(数学)
模式识别(心理学)
地质学
电信
历史
古代史
大地测量学
作者
Tianjun Shi,Jinnan Gong,Shikai Jiang,Xu Zhi,Gang Bao,Yu Sun,Wei Zhang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:61: 1-9
标识
DOI:10.1109/tgrs.2023.3283137
摘要
Aircraft detection in remote sensing images is significant in both military and civilian fields, such as air traffic control and battlefield dynamic monitoring. Deep learning methods can achieve promising detection performance with sufficient and labeled samples. However, current aircraft datasets are mainly from a single data source and lack diverse scenes and targets, making it difficult to train a robust and generalized detector. Therefore, we manually label and construct a complex optical remote sensing aircraft target detection dataset (CORS-ADD) from Google Earth and multiple satellites such as WorldView-2, WorldView-3, Pleiades, Jilin-1, and IKONOS. It contains 7,337 images covering typical airports and various rare scenes, including the aircraft carrier, ocean and land with flying aircraft. The dataset consists of 32,285 civil and military aircraft instances, including bombers, fighters, and early warning aircraft. These targets range from 4×4 pixels to 240×240 pixels and are all labeled with both horizontal bounding box (HBB) and oriented bounding box (OBB) annotations. The various scenes and sufficient instances can fully support the training and evaluation of data-driven algorithms. Meanwhile, based on the constructed dataset, we train and evaluate several detectors to provide a benchmark and help promote the development of aircraft detection techniques.
科研通智能强力驱动
Strongly Powered by AbleSci AI