Geospatial object segmentation, as a particular semantic segmentation task, always faces with larger-scale variation, larger intra-class variance of background, and foreground-background imbalance in the high spatial resolution (HSR) remote sensing imagery. However, general methods mainly focus on scale variation natural scene, inadequate consideration other two problems that usually happen large area earth observation scene. In this paper, we argue lie lack foreground modeling propose...

Road detection and centerline extraction from very high-resolution (VHR) remote sensing imagery are of great significance in various practical applications. operations depend on each other, to a certain extent. The road constrains the appearance centerline, enhances linear features detection. However, most previous works have addressed these two tasks separately not considered symbiotic relationship between them, making it difficult obtain smooth complete roads. In this paper, novel...

Deep learning approaches have shown promising results in remote sensing high spatial resolution (HSR) land-cover mapping. However, urban and rural scenes can show completely different geographical landscapes, the inadequate generalizability of these algorithms hinders city-level or national-level Most existing HSR datasets mainly promote research semantic representation, thereby ignoring model transferability. In this paper, we introduce Land-cOVEr Domain Adaptive segmentation (LoveDA)...

The small object semantic segmentation task is aimed at automatically extracting key objects from high-resolution remote sensing (HRS) imagery. Compared with the large-scale coverage areas for imagery, objects, such as cars and ships, in HRS imagery often contain only a few pixels. In this article, to tackle problem, foreground activation (FA)-driven (FactSeg) framework proposed perspectives of structure optimization. design, FA representation enhance awareness weak features objects. made up...

Planning a practical three-dimensional (3-D) flight path for unmanned aerial vehicles (UAVs) is key challenge the follow-up management and decision making in disaster emergency response. The ideal expected to balance total length terrain threat, shorten time reduce possibility of collision. However, traditional methods, tradeoff between these concerns difficult achieve, constraints are lacking optimized objective functions, which leads inaccurate modeling. In addition, methods based on...

The spatial resolution of land cover mapping has been increasing with the evolution Earth observation technology. However, higher makes it more laborious to collect training samples for efficient land-cover product updating. Fortunately, existing historical products a lower can be used as labels achieve cross-resolution latest images resolution. Although generate large number low-cost labels, noisy due mismatch or semantic errors. Furthermore, deep learning based classification models have...

Deep learning algorithms, especially convolutional neural networks (CNNs), have recently emerged as a dominant paradigm for high spatial resolution remote sensing (HRS) image recognition. A large amount of CNNs already been successfully applied to various HRS recognition tasks, such land-cover classification and scene classification. However, they are often modifications the existing derived from natural processing, in which network architecture is inherited without consideration complexity...

For high spatial resolution (HSR) remote sensing images, bitemporal supervised learning always dominates change detection using many pairwise labeled images. However, it is very expensive and time-consuming to label large-scale HSR In this paper, we propose single-temporal (STAR) for from a new perspective of exploiting object changes in unpaired images as supervisory signals. STAR enables us train high-accuracy detector only generalize real-world To evaluate the effectiveness STAR, design...

Building extraction based on high-resolution remote sensing imagery has been widely used in automatic surveying and mapping. However, few methods have developed for building instance extraction, i.e., extracting each building's footprint separately, which is required a number of applications, such as the smallest unit cadastral database. In there are two challenges: 1) buildings with various scales exist 2) precise footprints difficult to extract due blurry boundaries. this article, solve...

Geospatial object segmentation, a fundamental Earth vision task, always suffers from scale variation, the larger intra-class variance of background, and foreground-background imbalance in high spatial resolution (HSR) remote sensing imagery. Generic semantic segmentation methods mainly focus on variation natural scenarios. However, other two problems are insufficiently considered large area observation In this paper, we propose foreground-aware relation network (FarSeg++) perspectives...

Due to its inherent complexity, remote sensing image clustering is a challenging task. Recently, some spatial-based approaches have been proposed; however, one crucial factor with regard their quality that there usually parameter controls spatial information weight, which difficult determine. Meanwhile, the traditional optimization methods of objective functions for these often cannot function well because they simultaneously possess both local search capability and global capability....

Due to the intrinsic complexity of remote sensing images and lack prior knowledge, clustering for has always been one most challenging tasks in image processing. Recently, methods have often transformed into multiobjective optimization problems, making them more suitable complex clustering. However, performance is influenced by their capability. To resolve this problem, paper proposes an adaptive memetic fuzzy algorithm (AFCMOMA) imagery. In AFCMOMA, a framework devised optimize two...

Feature selection is an effective way to reduce the data dimensionality of hyperspectral imagery and obtain a better performance in subsequent applications, such as classification. The ideal approach optimal tradeoff between two criteria for image feature selection: 1) information preservation 2) redundancy reduction. However, constructing model above difficult due complexity imagery. Although evolutionary multiobjective optimization methods have been recently presented simultaneously...

The complementarity of synthetic aperture radar (SAR) and optical images allows remote sensing observations to "see" unprecedented discoveries. Image matching plays a fundamental role in the fusion application SAR images. However, both geometric imaging pattern physical radiation mechanism these two sensors are significantly different, so that show complex distortion nonlinear differences. This phenomenon brings great challenges image matching, which neither handcrafted descriptors nor deep...

Remote sensing image scene classification is a challenging task. With the development of deep learning, methods based on convolutional neural networks (CNNs) have made great achievements in remote classification. Since training CNN requires large number labeled samples, generative adversarial network (GAN) for sample generation represents new opportunity to solve problem limited samples. However, most existing GAN-based can only generate unlabeled instead samples with corresponding category....

Road extraction from very high-resolution (VHR) remote sensing imagery remains a huge challenge, due to the shadows and occlusions of trees buildings. Such complex backgrounds result in deep networks often producing fragmented roads with poor connectivity. has three typical tasks: road surface segmentation (SS), centerline (CE), edge detection (ED), which are conducted wide range real applications. Also, tasks have symbiotic relationship, i.e., SS determines location edges, CE ED can allow...