遥感
计算机科学
人工智能
高分辨率
计算机视觉
对象(语法)
分辨率(逻辑)
地理
作者
Wei Han,Jia Chen,Lizhe Wang,Ruyi Feng,Fengpeng Li,Lin Wu,Tian Tian,Jining Yan
标识
DOI:10.1109/mgrs.2020.3041450
摘要
Object detection that focuses on locating objects of interest and categorizing them has long played a critical role in the development of remote sensing imagery. Following significant improvements in Earth observation technologies, the objects in high-resolution remote sensing (HRRS) images show additional detailed information and more complex patterns. Some applications, such as urban monitoring, military reconnaissance, and national security, have urgent needs in terms of identifying small-scale (small) and weak-feature-response (weak) objects. However, these kinds of objects usually take up the small proportion of an image that has enough of its own variations in color, shape, and texture so that the objects' features are easily affected by weather, illumination, and occlusion. These characteristics of small, weak objects make their detection a more challenging task than generic object detection. This article comprehensively reviews the existing challenges and corresponding technologies for addressing that task and its specific problems.
科研通智能强力驱动
Strongly Powered by AbleSci AI