EXCLUSIVE: New satellite imagery obtained by Fox News shows that China, for the first time, has deployed a drone with stealth technology to a contested island in the South China Sea, in another sign of escalating tensions in the region. The new development comes as President Obama visits Japan. He lifted an arms embargo against Vietnam while visiting Hanoi earlier this week, drawing criticism from the Chinese government about stoking tensions in the region. The newly obtained satellite images from ImageSat International (ISI) show a Chinese Harbin BZK-005 long range reconnaissance drone on Woody Island in the South China Sea. The Chinese drone did not appear armed in the satellite image taken last month.

The 2016 IEEE GRSS Data Fusion Contest, organized by the IADF TC, was opened on January 3, 2016. The submission deadline was April 29, 2016. Participants submitted open topic manuscripts using the VHR and video-from-space data released for the competition. Evaluation and ranking were conducted by the Award Committee. The winners are reported below along with the abstracts of the submitted papers.

The lack of reliable data in developing countries is a major obstacle to sustainable development, food security, and disaster relief. Poverty data, for example, is typically scarce, sparse in coverage, and labor-intensive to obtain. Remote sensing data such as high-resolution satellite imagery, on the other hand, is becoming increasingly available and inexpensive. Unfortunately, such data is highly unstructured and currently no techniques exist to automatically extract useful insights to inform policy decisions and help direct humanitarian efforts. We propose a novel machine learning approach to extract large-scale socioeconomic indicators from high-resolution satellite imagery. The main challenge is that training data is very scarce, making it difficult to apply modern techniques such as Convolutional Neural Networks (CNN). We therefore propose a transfer learning approach where nighttime light intensities are used as a data-rich proxy. We train a fully convolutional CNN model to predict nighttime lights from daytime imagery, simultaneously learning features that are useful for poverty prediction. The model learns filters identifying different terrains and man-made structures, including roads, buildings, and farmlands, without any supervision beyond nighttime lights. We demonstrate that these learned features are highly informative for poverty mapping, even approaching the predictive performance of survey data collected in the field.

According to the United Nations (UN), more than 12 million people--including 5.6 million children--have fled Syria to escape the horrors of the country's ongoing civil war and invasion by ISIS. Worldwide, the UN reports an unprecedented 59.5 million people are displaced by crisis. The flow of refugees toward Europe from Syria and other war-torn nations has caused the continent's greatest refugee crisis since World War II. Finland-based Lucify, which creates interactive data visualizations to help organizations analyze and communicate important data, recently tackled the refugee migration to Europe. Using UN data from 2012 through December 2015, its interactive map offers a time-lapse view of refugee migration and country-by-country statistics.

When used for structured regression, powerful Conditional Random Fields (CRFs) are typically restricted to modeling effects of interactions among examples in local neighborhoods. Using more expressive representation would result in dense graphs, making these methods impractical for large-scale applications. To address this issue, we propose an effective CRF model with linear scale-up properties regarding approximate learning and inference for structured regression on large, fully connected graphs. The proposed method is validated on real-world large-scale problems of image de-noising and remote sensing. In conducted experiments, we demonstrated that dense connectivity provides an improvement in prediction accuracy. Inference time of less than ten seconds on graphs with millions of nodes and trillions of edges makes the proposed model an attractive tool for large-scale, structured regression problems.

This work is motivated by the problem of image mis-registration in remote sensing and we are interested in determining the resulting loss in the accuracy of pattern classification. A statistical formulation is given where we propose to use data contamination to model and understand the phenomenon of image mis-registration. This model is widely applicable to many other types of errors as well, for example, measurement errors and gross errors etc. The impact of data contamination on classification is studied under a statistical learning theoretical framework. A closed-form asymptotic bound is established for the resulting loss in classification accuracy, which is less than $\epsilon/(1-\epsilon)$ for data contamination of an amount of $\epsilon$. Our bound is sharper than similar bounds in the domain adaptation literature and, unlike such bounds, it applies to classifiers with an infinite Vapnik-Chervonekis (VC) dimension. Extensive simulations have been conducted on both synthetic and real datasets under various types of data contamination, including label flipping, feature swapping and the replacement of feature values with data generated from a random source such as a Gaussian or Cauchy distribution. Our simulation results show that the bound we derive is fairly tight.

The creation of high fidelity scenarios for disaster simulation is a major challenge for a number of reasons. First, the maps supplied by existing map providers tend to provide only road or building shapes and do not accurately model open spaces which people use to evacuate buildings, homes, or industrial facilities. Secondly, even if some of the data about evacuation routes is available, the real-world connection points between these spaces and roads and buildings is usually not well defined unless data from buildings’ owners can be obtained. Finally, in order to augment current maps with accurate spatial data, it would require either a good set of training data for a computer vision algorithm to define evacuation routes using pictures or a significant amount of manpower to directly survey a vast area. Against this background, we develop a novel model of geospatial data creation, called CollabMap, that relies on human computation. CollabMap is a crowdsourcing tool to get users contracted via Amazon Mechanical Turk or a similar service to perform micro-tasks that involve augmenting existing maps by drawing evacuation routes, using satellite imagery from Google Maps and panoramic views from Google Street-View. We use human computation to complete tasks that are hard for a computer vision algorithm to perform or to generate training data that could be used by a computer vision algorithm to automatically define evacuation routes.

This paper addresses one of the key components of the mining process: the geological prediction of natural resources from spatially distributed measurements. We present a novel approach combining undirected graphical models with ensemble classifiers to provide 3D geological models from multiple sensors installed in an autonomous drill rig. Drill sensor measurements used for drilling automation, known as measurement-while-drilling (MWD) data, have the potential to provide an estimate of the geological properties of the rocks being drilled. The proposed method maps MWD parameters to rock types while considering spatial relationships, i.e., associating measurements obtained from neighboring regions. We use a conditional random field with local information provided by boosted decision trees to jointly reason about the rock categories of neighboring measurements. To validate the approach, MWD data was collected from a drill rig operating at an iron ore mine. Graphical models of the 3D structure present in real data sets possess a high number of nodes, edges and cycles, making them intractable for exact inference. We provide a comparison of three approximate inference methods to calculate the most probable distribution of class labels. The empirical results demonstrate the benefits of spatial modeling through graphical models to improve classification performance.

Prediction models for multivariate spatio-temporal functions in geosciences are typically developed using supervised learning from attributes collected by remote sensing instruments collocated with the outcome variable provided at sparsely located sites. In such collocated data there are often large temporal gaps due to missing attribute values at sites where outcome labels are available. Our objective is to develop more accurate spatio-temporal predictors by using enlarged collocated data obtained by imputing missing attributes at time and locations where outcome labels are available. The proposed method for large gaps estimation in space and time (called LarGEST) exploits temporal correlation of attributes, correlations among multiple attributes collected at the same time and space, and spatial correlations among attributes from multiple sites. LarGEST outperformed alternative methods in imputing up to 80% of randomly missing observations at a synthetic spatio-temporal signal and at a model of fluoride content in a water distribution system. LarGEST was also applied for imputing 80% of nonrandom missing values in data from one of the most challenging Earth science problems related to aerosol properties. Using such enlarged data a predictor of aerosol optical depth is developed that was much more accurate than predictors based on alternative imputation methods when tested rigorously over entire continental US in year 2005.

The Canadian Traveler Problem (CTP) is a navigation problem where a graph is initially known,  but some edges may be blocked with a known probability.  The task is to minimize travel effort of reaching the goal. We generalize CTP to allow for remote sensing actions, now requiring minimization  of the sum of the travel cost and the remote sensing cost. Finding optimal policies for both versions is intractable. We provide optimal solutions for special case graphs. We then develop a framework that utilizes heuristics to determine when and where to sense the environment in order to minimize total costs. Several such heuristics, based on the expected total cost are introduced.  Empirical evaluations show the benefits of our heuristics and support some of the theoretical results.