Remote Sensing Image Target Detection Based on Multi-scale Feature Fusion
A remote sensing image target detection method based on multi-scale feature fusion is proposed. The selective search algo-rithm is used to filter and binarize the original data, extract the image data of the target area of the remote sensing image, and use RBM technology to obtain the semantic and detail features of the remote sensing image target. On this basis, a fusion network is estab-lished to deform, convolute and pool the semantic and detail features of the image target. The semantic features and detail features of the target are fused on multiple scales to obtain the depth features of the target, and then locate the target of remote sensing image. Ex-periments show that the design method has short detection time and can quickly detect remote sensing image targets.
万方数据
维普
