Target identification method and device for satellite remote sensing image

The embodiment of the invention provides a target identification method and device for a satellite remote sensing image, and relates to the field of satellite remote sensing, and the method comprises the steps: carrying out the feature extraction of the satellite remote sensing image through a residual network model, and obtaining a primary coding feature map; performing multi-size feature fusion on the satellite remote sensing image through an image semantic segmentation model to obtain a multi-size fusion feature map; performing global average pooling processing on the original image of the satellite remote sensing image, the primary coding feature map and the multi-size fusion feature map, and outputting a result map as recognized target feature information; the method can effectively improve the accuracy and efficiency of satellite remote sensing image target recognition. 本申请实施例提供一种卫星遥感影像的目标识别方法及装置，涉及卫星遥感领域，方法包括：通过残差网络模型对卫星遥感影像进行特征提取，得到初级编码特征图；通过图像语义分割模型对所述卫星遥感影像进行多尺寸特征融合，得到多尺寸融合特征图；对所述卫星遥感影像的原始图、所述初级编码特征