Change Detection in heterogeneous remote sensing images plays an increasingly essential role in many real-world applications, e.g., urban growth tracking, land use monitoring, disaster evaluation and damage assessment. The objective of change detection is to identify changes of geo-graphical entities or phenomena through two or more bitemporal images. Researchers have invested a lot in the homologous change detection and yielded fruitful results. However, change detection between heterogenous remote sensing images is still a great challenge, especially for change detection of heterogenous remote sensing images obtained from satellites and Unmanned Aerial Vehicles (UAV). The main challenges in satellite-UAV change detection tasks lie in the intensive difference of color for the same ground objects, various resolutions, the parallax effect and image distortion caused by different shooting angles and platform altitudes. To address these issues, we propose a novel method based on dual-channel fully convolution network. First, in order to alleviate the influence of differences between heterogeneous images, we employ two different channels to map heterogeneous remote sensing images from satellite and UAV, respectively, to a mutual high dimension latent space for the downstream change detection task. Second, we adopt Hough method to extract the edge of ground objects as auxiliary information to help the change detection model to pay more attention to shapes and contours, instead of colors. Then, IoU-WCE loss is designed to deal with the problem of imbalanced samples in change detection task. Finally, we conduct extensive experiments to verify the proposed method using a new Satellite-UAV heterogeneous image data set, named HTCD, which is annotated by us and has been open to public. The experimental results show that our method significantly outperforms the state-of-the-art change detection methods.

Road networks play a significant role in modern city management. It is necessary to continually extract current road structure, as it changes rapidly with the development of the city. Due to the success of semantic segmentation based on deep learning in the application of computer vision, extracting road networks from VHR (Very High Resolution) imagery becomes a method of updating geographic databases. The major shortcoming of deep learning methods for road networks extraction is that they need a massive amount of high quality pixel-wise training datasets, which is hard to obtain. Meanwhile, a large amount of different types of VGI (volunteer geographic information) data including road centerline has been accumulated in the past few decades. However, most road centerlines in VGI data lack precise width information and, therefore, cannot be directly applied to conventional supervised deep learning models. In this paper, we propose a novel weakly supervised method to extract road networks from VHR images using only the OSM (OpenStreetMap) road centerline as training data instead of high quality pixel-wise road width label. Large amounts of paired Google Earth images and OSM data are used to validate the approach. The results show that the proposed method can extract road networks from the VHR images both accurately and effectively without using pixel-wise road training data.

Change detection (CD) is one of the important applications of remote sensing and plays an important role in disaster assessment, land use detection, and urban sprawl tracking. High-accuracy fully supervised methods are the main methods for CD tasks at present. However, these methods require a large amount of labeled data consisting of bi-temporal images and their change maps. Moreover, creating change maps takes a lot of labor and time. To address this limitation, a simple semi-supervised change detection method based on consistency regularization and strong augmentation is proposed in this paper. First, we construct a Siamese nested UNet with graph attention mechanism (SANet) and pre-train it with a small amount of labeled data. Then, we feed the unlabeled data into the pre-trained SANet and confidence threshold filter to obtain pseudo-labels with high confidence. At the same time, we produce distorted images by performing strong augmentation on unlabeled data. The model is trained to make the CD results of the distorted images consistent with the corresponding pseudo-label. Extensive experiments are conducted on two high-resolution remote sensing datasets. The results demonstrate that our method can effectively improve the performance of change detection under insufficient labels. Our methods can increase the IoU by more than 25% compared to the state-of-the-art methods.

Road networks play a fundamental role in our daily life. It is of importance to extract the road structure in a timely and precise manner with the rapid evolution of urban road structure. Recently, road network extraction using deep learning has become an effective and popular method. The main shortcoming of the road extraction using deep learning methods lies in the fact that there is a need for a large amount of training datasets. Additionally, the datasets need to be elaborately annotated, which is usually labor-intensive and time-consuming; thus, lots of weak annotations (such as the centerline from OpenStreetMap) have accumulated over the past a few decades. To make full use of the weak annotations, we propose a novel semi-weakly supervised method based on adversarial learning to extract road networks from remote sensing imagery. Our method uses a small set of pixel-wise annotated data and a large amount of weakly annotated data for training. The experimental results show that the proposed approach can achieve a maintained performance compared with the methods that use a large number of full pixel-wise annotations while using less fully annotated data.

Novel view synthesis of remote sensing scenes from satellite images is a meaningful but challenging task. Due to the wide temporal span of image acquisition, satellite image collections often exhibit significant appearance variations, such as seasonal changes and shadow movements, as well as transient objects, making it difficult to reconstruct the original scene accurately. Previous work has noted that a large amount of image variation in satellite images is caused by changing light conditions. To address this, researchers have proposed incorporating the direction of solar rays into neural radiance fields (NeRF) to model the amount of sunlight reaching each point in the scene. However, this approach fails to effectively account for seasonal variations and suffers from a long training time and slow rendering speeds due to the need to evaluate numerous samples from the radiance field for each pixel. To achieve fast, efficient, and high-quality novel view synthesis for multi-temporal satellite scenes, we propose SatGS, a novel method that leverages 3D Gaussian points for scene reconstruction with an appearance-adaptive adjustment strategy. This strategy enables our model to adaptively adjust the seasonal appearance features and shadow regions of the rendered images based on the appearance characteristics of the training images and solar angles. Additionally, the impact of transient objects is mitigated through the use of visibility maps and uncertainty optimization. Experiments conducted on WorldView-3 images demonstrate that SatGS not only renders superior image quality compared to existing State-of-the-Art methods but also surpasses them in rendering speed, showcasing its potential for practical applications in remote sensing.

With the development of unmanned aerial vehicle (UAV) techniques, UAV images are becoming more widely used. However, as an essential step of UAV image application, the computation of stitching remains time intensive, especially for emergency applications. Addressing this issue, we propose a novel approach to use the position and pose information of UAV images to speed up the process of image stitching, called FUIS (fast UAV image stitching). This stitches images by feature points. However, unlike traditional approaches, our approach rapidly finds several anchor-matches instead of a lot of feature matches to stitch the image. Firstly, from a large number of feature points, we design a method to select a small number of them that are more helpful for stitching as anchor points. Then, a method is proposed to more quickly and accurately match these anchor points, using position and pose information. Experiments show that our method significantly reduces the time consumption compared with the-state-of-art approaches with accuracy guaranteed.