面向对象高分辨率遥感影像目标提取

Object-Oriented Target Extraction from High-Resolution Remote Sensing Images

在空间遥感技术空前发展、空间数据质量和获取能力大幅提升的背景下,如何准确地从遥感数据中提取目标成为亟待解决的问题。本文提出了基于面向对象技术的高分辨率遥感影像目标提取方法,从影像分割、对象知识库构建、对象特征计算三个方面对该方法进行了介绍和讨论,并以道路目标提取为例,对该方法的有效性进行了验证。实验结果显示,本文提出的方法可以有效提升高分辨率遥感影像目标提取的准确性。

Against the background of unprecedented development of spatial remote sensing technology and substantial improvement of spatial data quality and acquisition capability, how to accurately extract targets from remote sensing data has become an urgent problem to be solved. This paper proposes a target extraction method for high-resolution remote sensing images based on object-oriented technology, introduces and discusses the method from three aspects, namely, image segmentation, object knowledge base construction, and object feature computation, and verifies the effectiveness of the method by taking road target extraction as an example. The experimental results show that the method proposed in this paper can effectively improve the accuracy of target extraction from high-resolution remote sensing images.