It is low definition for the ground object boundaries in visible light remote sensing images of unmanned aerial vehicles(UAVs),which easily leads to a decrease in the differentiation between ground object targets and background,making it difficult to extract ground object targets.To this end,an extracting ground object method for UAV visible light remote sensing images is pro-posed.The features of the UAV visible light remote sensing images are analyzed from three aspects of the spectral feature,texture feature,and edge feature.The augmention processing of the UAV visible light remote sensing image dataset is implemented by com-bining the three image features.The image encoding labels for the expanded dataset are defined to determine the weight of ground ob-ject enhancement.By parameterizing the spectral features of ground object targets,the spectral absorption index is calculated to ob-tain the expression of ground object extraction,and achive the unmanned aerial vehicle visible light remote sensing image ground ob-ject extraction.The experimental results show that the proposed method can ensure the clarity of ground object boundary,and it has a strong ability to extract ground objects.
关键词
无人机/可见光遥感影像/地物目标提取/编码标签/光谱吸收指数
Key words
UAV/visible light remote sensing image/object extraction/encoding label/spectral absorption index
维普
万方数据