【摘要】 无人机航拍影像空间分辨率高,纹理信息丰富,但其光谱信息匮乏,不利于遥感信息解译。为此提出一种基于脉冲耦合神经网络模型的融合算法,通过计算非规则区域的统计特性,将无人机航拍影像的亚米级高空间分辨率信息注入到遥感卫星多光谱影像中,以获取具有亚米级空间分辨率和高的光谱分辨率的遥感融合影像。通过定性和定量的对比实验,表明该算法优于经典的遥感影像融合方法,同时验证了其在减小光谱扭曲和空间纹理细节保持等方面的有效性。更多还原

【Abstract】 Aerial images captured by UAV have high spatial resolution and rich texture.However,the lack of spectral information makes it difficult to use for image interpretation.Therefore,a novel pulse-coupled neural network based fusion algorithm is proposed.Both the sub-meter spatial resolution and high spectral resolution can be obtained by injecting the information of sub-meter spatial resolution of UAV to the multispectral image of the remote sensing satellite,which is achieved by performing the statistics in irregular regions of the remote sensing images.The qualitative and quantitative experiments demonstrate that the proposed method outperforms the traditional remote sensing fusion methods.The validity of the fusion algorithm in reducing spectral distortion and preserving spatial texture details is also verified by comparative experiments.更多还原