Multiband image fusion has become a thriving area of research in a number of different fields,such as space robotics,and remote sensing,etc.Many multiband image fusion methods have been proposed for hyperspectral shar...Multiband image fusion has become a thriving area of research in a number of different fields,such as space robotics,and remote sensing,etc.Many multiband image fusion methods have been proposed for hyperspectral sharpening with panchromatic images,hyperspectral sharpening with multispectral images and panchromatic images,etc.Despite the different motivations,we observe that many existing methods possibly lead to over-smooth regions.In this work,we consider a new problem formulation of two image fusion problems.A novel fusion model with total generalized variation regularization term is proposed,where the fusion process is performed on hybrid gradient domains.The optimization framework of alternating direction multiplier of method is used to solve the resulting problem.In an extensive evaluation,our method outperforms some state-of-the-art methods.展开更多
Object detection on multi-source images from satellite platforms is difficult due to the characteristics of imaging sensors.Multi-model image fusion provides a possibility to improve the performance of object detectio...Object detection on multi-source images from satellite platforms is difficult due to the characteristics of imaging sensors.Multi-model image fusion provides a possibility to improve the performance of object detection.This paper proposes a fusion object detection framework with arbitrary-oriented region convolutional neural network.First,nine kinds of pansharpening methods are utilized to fuse multi-source images.Second,a novel object detection framework based on Faster Region-based Convolutional Neural Network structure is used,which is suitable for large-scale satellite images.Region Proposal Network is adopted to generate axially aligned bounding boxes enclosing object sin different orientations,and then extract features by pooling layers with different sizes.These features are used to classify the proposals,adjust the bounding boxes,and predict the inclined boxes and the objectness/non-objectness score.Smaller anchors for small objects are considered.Finally,inclined non-maximum suppression method is utilized to get the detection results.Experimental results showed that the proposed method performs better than some state-of-the-art object detection techniques,such as YOLO-v2,YOLO-v3,etc.Some numerical tests validate the efficiency and effectiveness of the proposed method.展开更多
基金supported by Young Scientists Fund and National Natural Science Foundation of China(Grant nos.61603249,61673262)key project of Science and Technology Commission of Shanghai Municipality(Grant no.16JC1401100).
文摘Multiband image fusion has become a thriving area of research in a number of different fields,such as space robotics,and remote sensing,etc.Many multiband image fusion methods have been proposed for hyperspectral sharpening with panchromatic images,hyperspectral sharpening with multispectral images and panchromatic images,etc.Despite the different motivations,we observe that many existing methods possibly lead to over-smooth regions.In this work,we consider a new problem formulation of two image fusion problems.A novel fusion model with total generalized variation regularization term is proposed,where the fusion process is performed on hybrid gradient domains.The optimization framework of alternating direction multiplier of method is used to solve the resulting problem.In an extensive evaluation,our method outperforms some state-of-the-art methods.
基金supported by National Natural Science Foundation of China(Grant Nos.61673262,61603249)key project of Science and Technology Commission of Shanghai Municipality(Grant No.16JC1401100).
文摘Object detection on multi-source images from satellite platforms is difficult due to the characteristics of imaging sensors.Multi-model image fusion provides a possibility to improve the performance of object detection.This paper proposes a fusion object detection framework with arbitrary-oriented region convolutional neural network.First,nine kinds of pansharpening methods are utilized to fuse multi-source images.Second,a novel object detection framework based on Faster Region-based Convolutional Neural Network structure is used,which is suitable for large-scale satellite images.Region Proposal Network is adopted to generate axially aligned bounding boxes enclosing object sin different orientations,and then extract features by pooling layers with different sizes.These features are used to classify the proposals,adjust the bounding boxes,and predict the inclined boxes and the objectness/non-objectness score.Smaller anchors for small objects are considered.Finally,inclined non-maximum suppression method is utilized to get the detection results.Experimental results showed that the proposed method performs better than some state-of-the-art object detection techniques,such as YOLO-v2,YOLO-v3,etc.Some numerical tests validate the efficiency and effectiveness of the proposed method.
