Search

The available wide-baseline image matching algorithms have been prone to failure or only producing few matches, due to the complex affine deformation and perspective distortion. On this basis, we proposed a novel affine invariant feature matching algorithm for oblique stereo images based on multivariate network. In our method, we applied the Hessian algorithm to extract initial feature regions, then we constructed triplet network (TN) model, and obtained affine invariant feature regions through deep learning. To improve the matching performance of similar features, we proposed multilateral constraint loss function to train multi-branch descriptor network (MDN) model, and then generated deep learning descriptors with higher discrimination for image features. Afterwards, the conjugate features were produced by the matching metric of nearest/next distance ratio (NNDR), and eliminated possible mismatch points through random sampling consistency (RANSAC) algorithm. Finally, experiments on oblique stereo images acquired by unmanned aerial vehicle verified the effectiveness of the proposed approach.

Using deep convolutional neural network (CNN) to intelligently extract buildings from remote sensing images is of great significance for digital city construction, disaster detection and land management. The color difference between multi-temporal remote sensing images will lead to the decrease of generalization ability of building semantic segmentation model. In view of this, this paper proposes the attention-guided color consistency adversarial network (ACGAN). The algorithm takes the reference color style images and the images to be corrected in the same area and different phases as the training set and adopts the consistency adversarial network with the U-shaped attention mechanism to train the color consistency model. In the prediction stage, this model converts the hue of the images to that of the reference color style image, which is based on the reasoning ability of the deep learning model, instead of the corresponding reference color style image. This model transforms the hue of the images to be corrected into that of the reference color style images. This stage is based on the reasoning ability of the deep learning model, and the corresponding reference color style image is no longer needed. In order to verify the effectiveness of the algorithm, firstly, we compare the algorithm of this paper with the traditional image processing algorithm and other consistency adversarial network. The results show that the images after ACGAN color consistency processing are more similar to that of the reference color style images. Secondly, we carried out the building semantic segmentation experiment on the images processed by the above different color consistency algorithms, which proved that the method in this paper is more conducive to the impro-vement of the generalization ability of multi-temporal remote sensing image semantic segmentation model.

For a large collection of satellite images,because of the differences in season,light,atmospheric conditions and so on,adjacent satellite images may have different color and there will be obviously "seam-line" in mosaic satellite image.In this paper,a method of satellite image color normalization was proposed,it was implemented to correct the color of image automatically based on better color low resolution satellite imagery which covered the mapping area.We selected a large collection and long time interval GF-1 satellite images as experiment data,results show that the mosaic image have a good visual effect,the color transition of two images smoothly,statistical indicators of overlap area obviously improved,all of those verified the validity and reliability of the algorithm.

Due to advantages such as ease of interpretation, completeness through mitigation of occluding areas, as well as system accessibility, the aerial oblique images have found their place in numerous civil applications. However, for these applications high quality orientation data are essential. A fully automatic tie-point extraction procedure is developed to precisely orient the large block of oblique aerial images, in which a refined ASIFT algorithm and a window-based multiple-viewing image matching (WMVM) method are combined. In this approach, the WMVM method is based on the concept of multi-image matching guided from object space and allows reconstruction of 3D objects by matching all available images simultaneously, and a square correlation window in the reference image can be correlated with windows of different size, shape and orientation in the search images.Then another key algorithms, i.e. the combined bundle adjustment method with gross-error detection & removal algorithm, which can be used for simultaneously orient the oblique and nearly-vertical images will be presented. Finally, through the experiments by using real oblique images over several test areas, the performance and accuracy of the proposed method is studied and presented.

A method of fast and intelligent seamline detection is presented that based on minimum spanning tree for high resolution orthoimage mosaicking. The image gradient and difference of homonymy pixels in the overlap area are calculated to build the differential image, which is deemed as a weighted undirected graph. According to the Bottleneck model, the optimal seamline is detected on the differential image by finding the minimum spanning tree of the weighted undirected graph. This method discards the conventional iterative process, thus achieves high speed. Experiment results illustrate the value of the proposed method which achieves great efficiency and guarantees the quality of the seamlines at the same time.