Aircraft detection in remote sensing images using centre-based proposal regions and invariant features

ABSTRACT

Aircraft detection in remote sensing imagery has drawn much attention in recent years, which plays an important role in various military and civil applications. While many advanced works have been developed with powerful learning algorithms in natural images, there still lacks an effective one to detect aircraft precisely in remote sensing images, especially in some complicated conditions. In this paper, a novel method is designed to detect aircraft precisely, named aircraft detection using Centre-based Proposal regions and Invariant Features (CPIF), which can handle some difficult image deformations, especially rotations. Our framework mainly contains three steps. Firstly, we propose an algorithm to extract proposal regions from remote sensing imagery. Secondly, an ensemble learning classifier with the rotation-invariant HOG is trained for aircraft classification. Lastly, we detect aircraft in remote sensing images by combining the products of the above steps. The proposed method is evaluated on a public dataset RSOD and the results are performed to demonstrate the superiority and effectiveness in comparison with the state-of-the-art methods.     

Deep multi-feature fusion network for remote sensing images

ABSTRACT

Learning discriminative and robust features is crucial in remote sensing image processing. Many of the currently used approaches are based on Convolutional Neural Networks (CNNs). However, such approaches may not effectively capture various different semantic objects of remote sensing images. To overcome this limitation, we propose a novel end-to-end deep multi-feature fusion network (DMFN). DMFN combines two different deep architecture branches for feature representations; the global and local branch. The global branch, which consists of three losses, is used to learn discriminative features from the whole image. The local branch is then used in the partitioning of the entire image into multiple strips in order to obtain local features. The two branches are then combined, used to learn fusion feature representations for the image. The proposed method is an end-to-end framework during training. Comprehensive validation experiments on two public datasets indicate that relative to existing deep learning approaches, this strategy is superior for both retrieval and classification tasks.     

Rapid retrieval strategy for massive remote sensing metadata based on GeoHash coding

With the rapid development of Earth observation technology, satellite data centres have accumulated large amounts of remote sensing data from different spaceborne and airborne sensors. The efficient management and quick retrieval of multisource, massive and heterogeneous remote sensing data in the Big Data age have become increasingly important. In this paper, a spatio-temporal organization model based on GeoHash coding is proposed. First, based on the ISO (International Organization for Standardization) standard, the heterogeneous remote sensing metadata can be converted into a unified format, and the differences in the multisource remote sensing metadata are screened. Then, the GeoHash algorithm is used to encode and convert the latitude and longitude coordinates of the remote sensing metadata to reduce the remote sensing metadata dimensions under space retrieval conditions. Finally, by building an HBase key value model based on GeoHash, a primary key is used to realize the rapid retrieval of massive remote sensing metadata through the simulation of 1500 million remote sensing metadata retrieval experiments; by comparing with the traditional multi-conditional filtering retrievals, the results show that a spatio-temporal organization strategy for remote sensing metadata based on GeoHash coding can effectively improve the efficiency of remote sensing data retrievals.     

Change detection based on Faster R-CNN for high-resolution remote sensing images

Change detection is of great significance in remote sensing. The advent of high-resolution remote sensing images has greatly increased our ability to monitor land use and land cover changes from space. At the same time, high-resolution remote sensing images present a new challenge over other satellite systems, in which time-consuming and tiresome manual procedures must be needed to identify the land use and land cover changes. In recent years, deep learning (DL) has been widely used in the fields of natural image target detection, speech recognition, face recognition, etc., and has achieved great success. Some scholars have applied DL to remote sensing image classification and change detection, but seldomly to high-resolution remote sensing images change detection. In this letter, faster region-based convolutional neural networks (Faster R-CNN) is applied to the detection of high-resolution remote sensing image change. Compared with several traditional and other DL-based change detection methods, our proposed methods based on Faster R-CNN achieve higher overall accuracy and Kappa coefficient in our experiments. In particular, our methods can reduce a large number of false changes.     

Rapid retrieval strategy for massive remote sensing metadata based on GeoHash coding

With the rapid development of Earth observation technology, satellite data centres have accumulated large amounts of remote sensing data from different spaceborne and airborne sensors. The efficient management and quick retrieval of multisource, massive and heterogeneous remote sensing data in the Big Data age have become increasingly important. In this paper, a spatio-temporal organization model based on GeoHash coding is proposed. First, based on the ISO standard, the heterogeneous remote sensing metadata can be converted into a unified format, and the differences in the multisource remote sensing metadata are screened. Then, the GeoHash algorithm is used to encode and convert the latitude and longitude coordinates of the remote sensing metadata to reduce the remote sensing metadata dimensions under space retrieval conditions. Finally, by building an HBase key value model based on GeoHash, a primary key is used to realize the rapid retrieval of massive remote sensing metadata through the simulation of 1500 million remote sensing metadata retrieval experiments; by comparing with the traditional multi-conditional filtering retrievals, the results show that a spatio-temporal organization strategy for remote sensing metadata based on GeoHash coding can effectively improve the efficiency of remote sensing data retrievals.     

Latent topic-based super-resolution for remote sensing

This letter presents a novel single-image Super-Resolution (SR) approach based on latent topics specially designed to remote sensing imagery. The proposed approach pursues to super-resolve topics uncovered from low-resolution images instead of super-resolving image patches themselves. An experimental comparison is conducted using nine different SR methods over four aerial image datasets. Experiments revealed the potential of latent topics in remote sensing SR by reporting that the proposed approach is able to provide a competitive advantage especially in low noise conditions.     

A method for detecting the atmospheric refraction effect using satellite remote sensing

The atmospheric refraction effect seriously restricts the precision of satellite measurements. Various atmospheric refraction models have been proposed to solve the bending effect due to refraction. But the atmosphere shows a complicated spatio-temporal distribution due to turbulences, which affects the precision of the atmosphere models. In this study, we proposed a novel method to detect the atmospheric refraction effect according to the dispersion of the electromagnetic wave. Depending on one satellite image only, we can invert the displacement of atmospheric refraction effect. And this method makes it a reality without constructing the atmosphere model and monitoring a series of meteorological data. In the experiment, two high-resolution images were used to validate the method, an inclined shooting scene at zenith angle of 30° and a vertical shooting scene as a control. The result is close to the value calculated by the atmospheric refraction model. So the proposed method is effective to detect the atmospheric refraction effect using satellite remote sensing.     

Mutual information based multi-modal remote sensing image registration using adaptive feature weight

Multi-module images registration is a challenging task in image processing, and more especially in the field of remote sensing. In this letter, we strive to present a novel mutual information scheme for image registration in remote sensing scenario based on feature map technique. We firstly take saliency detection advantages to extract geographic pattern, and then utilize the efficient Laplacian of Gaussian(LOG) and Guided Filter methods to construct a new feature map based on different characteristic of multi-channel images. To avoid practical traps of sub-optimization, we propose an novel mutual information(MI) algorithm based on an adapted weight strategy. The proposed model divides an image into patches and assigns weighted values according to patch similarities in order to solve the optimization problem, improve accuracy and enhance performance. Note that, our proposed method incorporates the LOG and Guided Filter methods into image registration for the first time to construct a new feature map based on differences and similarities strategy. Experiments are conducted over island and coastline scenes, and reveal that our hybrid model has a significant performance and outperforms the state-of-the-art methods in remote sensing image registration.     

Scene classification in remote sensing images using a two-stage neural network ensemble model

Scene classification has long been a challenging task in the remote sensing field. Conventional approaches based on hand-crafted features are not suitable in large scale remote sensing images. Convolutional Neural Network (CNN) achieves great success in computer vision field by learning hierarchical features automatically from mass data. However, the shortage of labeled dataset in remote sensing field results in severe overfitting and the ensemble of several networks have better generalization ability than one single network. In this letter, we propose a novel Two-Stage Neural Network Ensemble Model to solve the problems mentioned above. Firstly, to overcome overfitting, we pre-train a CNN using the ImageNet dataset and fine tune the network by labeled remote sensing images. Then, the output features are fed to a Restricted Boltzmann Machine (RBM) Retrained Network to get better feature representations. Finally, in testing stage, a method based on Ensemble Inference Network (EIN) is introduced to enhance the generalization ability by combining the classification results of several networks. Experimental results on the UC Merced Land Use (UCML) dataset demonstrate the effectiveness of our proposed method.     

Combining transductive and active learning to improve object-based classification of remote sensing images

In this letter, we propose a new active transductive learning (ATL) framework for object-based classification of satellite images. The framework couples graph-based label propagation with active learning (AL) to exploit positive aspects of the two learning settings. The transductive approach considers both labelled and unlabelled image objects to perform its classification as they are all available at training time while the AL strategy smartly guides the construction of the training set employed by the learner. The proposed framework was tested in the context of a land cover classification task using RapidEye optical imagery. A reference land cover map was elaborated over the whole study area in order to get reliable information about the performance of the ATL framework. The experimental evaluation underlines that, with a reasonable amount of training data, our framework outperforms state of the art classification methods usually employed in the field of remote sensing.     

Selective convolutional neural networks and cascade classifiers for remote sensing image classification

Training convolutional neural network (CNN) architecture fully, using pretrained CNNs as feature extractors, and fine-tuning pretrained CNNs on target datasets are three popular strategies used in state-of-the-art methods for remote sensing image classification. The full training strategy requires large-scale training dataset, whereas the fine-tuning strategy requires a pretrained model to resume network learning. In this study, we propose a new strategy based on selective CNNs and cascade classifiers to improve the classification accuracy of remote sensing images relative to single CNN. First, we conduct a comparative study of existing pretrained CNNs in terms of data augmentation and the use of fully connected layers. Second, selective CNNs, which based on class separability criterion, are presented to obtain an optimal combination from multiple pretrained models. Finally, classification accuracy is improved by introducing two-stage cascade linear classifiers, the prediction probability of which in the first stage is used as input for the second stage. Experiments on three public remote sensing datasets demonstrate the effectiveness of the proposed method in comparison with state-of-the-art methods.     

Fast orientation prediction-based discrete wavelet transform for remote sensing image compression

In this letter, a fast orientation prediction-based discrete wavelet transform (DWT) is introduced for high-spatial-resolution remote sensing image compression. The proposed fast orientation prediction-based approach is designed to improve coding performance and reduce computational complexity of the previous adaptive directional lifting method. The main contribution of the proposed approach consists of three parts: a new orientation map is designed to achieve a better transform coding performance; an orientation prediction model is presented to fast obtain the optimal transform orientation; the new fast orientation prediction-based DWT is introduced. Experimental results show that the proposed fast orientation prediction-based high-spatial-resolution remote sensing image coding technique outperforms the traditional lifting wavelet and the method based on adaptive directional lifting in coding performance, and the computational complexity of the proposed transform is far lower than that of adaptive directional lifting method.     

Active learning for training sample selection in remote sensing image classification using spatial information

Collection of training samples for remote sensing image classification is always time-consuming and expensive. In this context, active learning (AL) that aims at using limited training samples to achieve promising classification performances is developed. Recently, integration of spatial information into AL exhibits new potential for image classification. In this letter, an AL approach with two-stage spatial computation (AL-2SC) is proposed to improve the selection of training samples. The spatial features derived from remote sensing image and the probability outputs from the neighboring pixels are introduced in AL process. Moreover, we compare several AL approaches which take spatial information into account. In experiments, random sampling (RS) and four AL methods, including AL using breaking ties heuristic (BT), AL with spatial feature (AL-SF), AL with neighbouring responses (AL-NR), and AL-2SC, are considered. Three remote sensing datasets, including one hyperspectral and two multispectral images, are used to compare the performance of different methods. It is illustrated that, the utilization of spatial information is very important for the improvement of AL performance, and the proposed AL-2SC shows the most satisfactory result.     

Spatial contextual classification of remote sensing images using a Gaussian process

Gaussian process (GP) classifiers represent a powerful and interesting theoretical framework for the Bayesian classification of remote sensing images. However, the integration of spatial information in GP classifier is still an open question, while researches have demonstrated that the classification results could be improved when the spatial information is used. In this context, in order to improve the performance of the traditional GP classifier, we propose to use Markov random fields (MRFs) to refine the classification results with the neighbourhood information in the images. In the proposed method (denoted as GP-MRF), the MRF model is used as a post-processing step to the pixelwise results with GP classifier which classifies each pixel in the image separately. Therefore, the proposed GP-MRF approach promotes solutions in which adjacent pixels are likely to belong to the same class. Experimental results show that the GP-MRF could achieve better classification accuracy compared to the original GP classifier and the state-of-the-art spatial contextual classification methods.     

A segmented particle swarm optimization convolutional neural network for land cover and land use classification of remote sensing images

ABSTRACT

The development of automatic classification methods in neural networks is an important topic in the field of land cover and land use (LULC) classification of remote sensing images. Here, we proposed a new segmented particle swarm convolutional neural network model (SPSO-CNN) by combining the subsection particle swarm algorithm with a convolutional neural network. The SPSO-CNN was applied to experiment of LULC classification of GF-1 high resolution remote sensing image. The results showed that SPSO-CNN achieved high precision, recall, F1 score and total precision in the LULC classification of remote sensing image with high spatial resolution, demonstrating the advantage and potential of applying SPSO-CNN to the LULC classification of remote sensing images.     

An improved unsupervised representation learning generative adversarial network for remote sensing image scene classification

ABSTRACT

Unsupervised representation learning plays an important role in remote sensing image applications. Generative adversarial network (GAN) is the most popular unsupervised learning method in recent years. However, due to poor data augmentation, many GAN-based methods are often dif?cult to carry out. In this paper, we propose an improved unsupervised representation learning model called multi-layer feature fusion Wasserstein GAN (MF-WGANs) which considers extracting the feature information for remote sensing scene classification from unlabelled samples. First, we introduced a multi-feature fusion layer behind the discriminator to extract the high-level and mid-level feature information. Second, we combined the loss of multi-feature fusion layer and WGAN-GP to generate more stable and high-quality remote sensing images with a resolution of 256 × 256. Finally, the multi-layer perceptron classifier (MLP-classifier) is used to classify the features extracted from the multi-feature fusion layer and evaluated with the UC Merced Land-Use, AID and NWPU-RESISC45 data sets. Experiments show that MF-WGANs has richer data augmentation and better classification performance than other unsupervised representation learning classification models (e.g., MARTA GANs).     

A method based on the adaptive cuckoo search algorithm for endmember extraction from hyperspectral remote sensing images

In this letter, an endmember extraction approach based on an adaptive cuckoo search (ACS) algorithm (ACSEE) is proposed for hyperspectral remote sensing imagery. In the proposed algorithm, the problem of endmember extraction is transformed into combinatorial optimization of the candidate endmembers. The effectiveness of the cuckoo search algorithm is demonstrated by its good balance between exploitation of Lévy flights and random walk, which leads the algorithm to effectively explore the solution space and locate potential solutions to avoid falling into local optima. Furthermore, to improve the convergence characteristics of the original cuckoo search algorithm, a new strategy combined with historical information is proposed to accelerate the search process by adjusting the step size of the Lévy flights. The results of experiments conducted using simulated data and well-known hyperspectral remote sensing data indicate that the proposed ACS algorithm can be used as an alternative tool to solve the problem of endmember extraction on account of its robust stability and guarantee of optimal performance.     

A generally applicable noise-estimating method for remote sensing images

Local mean and local standard deviations (LMLSD), which is one of the most widely used methods for estimating noise in remote sensing images, is suitable only for the images with many homogeneous regions. For those composed of heterogeneous features and textures, it may cause overestimation of noise. Edge-extracted local standard deviations (EELSD) method performs better than LMLSD in most instances, but it still cannot work out the accurate noise estimation in most heterogeneous images. Spectral and spatial de-correlation (SSDC) is an effective noise-estimation method for hyperspectral images. However, it cannot be applied to single-band or multispectral images because of the use of pixel spectral information in the calculation process. In this article, a new noise-estimating method for remote sensing images, which is based on the principle of LMLSD and has made improvements in three aspects, is proposed. The new method has been tested with several Airborne Visible Infrared Imaging Spectrometer images with different degrees of uniformity. Compared with LMLSD and EELSD, the results of the improved method are more accurate, stable, and applicable in terms of complex land cover types. Furthermore, in contrast to SSDC, this method is suitable not only for hyperspectral images but also for single-band and multispectral images.     

Consumers' proposed solutions to barriers to access of rural and remote speech pathology services

Barriers inhibiting the equitable delivery of health services to rural and remote areas of Australia have been well documented. Yet the literature has not discussed health care consumers' proposed solutions to these barriers. This is especially the case when considering rural and remote speech pathology services. This paper reports on a study that investigated potential solutions to perceived barriers experienced by consumers when attempting to access paediatric speech pathology services in rural and remote New South Wales (NSW). The study consisted of a self-administered questionnaire mailed to members of the NSW branch of the Isolated Children's and Parents' Association (ICPA). Key findings from this study suggest consumer-based solutions to barriers to access in an attempt to maximize the effectiveness of sparse rural and remote speech pathology services, by matching the beliefs and expectations of consumers with the characteristics of services provided.