As a fundamental and profound task in remote sensing, change detection from very-high-resolution (VHR) images plays a vital role in a wide range of applications and attracts considerable attention. Current methods generally focus on the research of simultaneously modeling and discriminating the changed and unchanged features. In practice, for bi-temporal VHR optical remote sensing images, the temporal spectral variability tends to exist in all bands throughout the entire paired images, making it difficult to distinguish none-changes and changes with a single model. In this paper, motivated by this observation, we propose a novel hybrid end-to-end framework named dual learning-based Siamese framework (DLSF) for change detection. The framework comprises two parallel streams which are dual learning-based domain transfer and Siamese-based change decision. The former stream is aimed at reducing the domain differences of two paired images and retaining the intrinsic information by translating them into each other’s domain. While the latter stream is aimed at learning a decision strategy to decide the changes in two domains, respectively. By training our proposed framework with certain change map references, this method learns a cross-domain translation in order to suppress the differences of unchanged regions and highlight the differences of changed regions in two domains, respectively, then focus on the detection of changed regions. To the best of our knowledge, the idea of incorporating dual learning framework and Siamese network for change detection is novel. The experimental results on two datasets and the comparison with other state-of-the-art methods verify the efficiency and superiority of our proposed DLSF.

Since manually labeling aerial images for pixel-level classification is expensive and time-consuming, developing strategies for land cover mapping without reference labels is essential and meaningful. As an efficient solution for this issue, domain adaptation has been widely utilized in numerous semantic labeling-based applications. However, current approaches generally pursue the marginal distribution alignment between the source and target features and ignore the category-level alignment. Therefore, directly applying them to land cover mapping leads to unsatisfactory performance in the target domain. In our research, to address this problem, we embed a geometry-consistent generative adversarial network (GcGAN) into a co-training adversarial learning network (CtALN), and then develop a category-sensitive domain adaptation (CsDA) method for land cover mapping using very-high-resolution (VHR) optical aerial images. The GcGAN aims to eliminate the domain discrepancies between labeled and unlabeled images while retaining their intrinsic land cover information by translating the features of the labeled images from the source domain to the target domain. Meanwhile, the CtALN aims to learn a semantic labeling model in the target domain with the translated features and corresponding reference labels. By training this hybrid framework, our method learns to distill knowledge from the source domain and transfers it to the target domain, while preserving not only global domain consistency, but also category-level consistency between labeled and unlabeled images in the feature space. The experimental results between two airborne benchmark datasets and the comparison with other state-of-the-art methods verify the robustness and superiority of our proposed CsDA.

Effectively identifying an airport from satellite and aerial imagery is a challenging task. Traditional methods mainly focus on the use of multiple features for the detection of runways and some also adapt knowledge of airports, but the results are unsatisfactory and the usage limited. A new method is proposed to recognize airports from high-resolution optical images. This method involves the analysis of the saliency distribution and the use of fuzzy rule-based classification. First, a number of images with and without airports are segmented into multiple scales to obtain a saliency distribution map that best highlights the saliency distinction between airports and other objects. Then, on the basis of the segmentation result and the structural information of airports, we analyze the segmentation result to extract and represent the semantic information of each image via the bag-of-visual-words (BOVW) model. The image correlation degree is combined with the BOVW model and fractal dimension calculation to make a more complete description of the airports and to carry out preliminary classification. Finally, the support vector machine (SVM) is adopted for detailed classification to classify the remaining imagery. The experiment shows that the proposed method achieves a precision of 89.47% and a recall of 90.67% and performs better than other state of the art methods on precision and recall.

Harbours are very important objects in civil and military fields. To detect them from high resolution remote sensing imagery is important in various fields and also a challenging task. Traditional methods of detecting harbours mainly focus on the segmentation of water and land and the manual selection of knowledge. They do not make enough use of other features of remote sensing imagery and often fail to describe the harbours completely. In order to improve the detection, a new method is proposed. First, the image is transformed to Hue, Saturation, Value (HSV) colour space and saliency analysis is processed via the generation and enhancement of the co-occurrence histogram to help detect and locate the regions of interest (ROIs) that is salient and may be parts of the harbour. Next, SIFT features are extracted and feature learning is processed to help represent the ROIs. Then, by using classified feature of the harbour, a classifier is trained and used to check the ROIs to find whether they belong to the harbour. Finally, if the ROIs belong to the harbour, a minimum bounding rectangle is formed to include all the harbour ROIs and detect and locate the harbour. The experiment on high resolution remote sensing imagery shows that the proposed method performs better than other methods in precision of classifying ROIs and accuracy of completely detecting and locating harbours.