This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high-resolution (VHR) synthetic aperture radar (SAR) images. In this context, this paper has two major contributions. First, it presents a novel and generic workflow that initially classifies the spaceborne SAR tomography (TomoSAR) point clouds--generated by processing VHR SAR image stacks using advanced interferometric techniques known as TomoSAR--into buildings and nonbuildings with the aid of auxiliary information (i.e., either using openly available 2-D building footprints or adopting an optical image classification scheme) and later back project the extracted building points onto the SAR imaging coordinates to produce automatic large-scale benchmark labeled (buildings/nonbuildings) SAR data sets. Second, these labeled data sets (i.e., building masks) have been utilized to construct and train the state-of-the-art deep fully convolution neural networks with an additional conditional random field represented as a recurrent neural network to detect building regions in a single VHR SAR image. Such a cascaded formation has been successfully employed in computer vision and remote sensing fields for optical image classification but, to our knowledge, has not been applied to SAR images. The results of the building detection are illustrated and validated over a TerraSAR-X VHR spotlight SAR image covering approximately 39 km²--almost the whole city of Berlin-- with the mean pixel accuracies of around 93.84%.

In this article, we aim to explore the potential of using onboard cameras and pre-stored geo-referenced imagery for Unmanned Aerial Vehicle (UAV) localization. Such a vision-based localization enhancing system is of vital importance, particularly in situations where the integrity of the global positioning system (GPS) is in question (i.e., in the occurrence of GPS outages, jamming, etc.). To this end, we propose a complete trainable pipeline to localize an aerial image in a pre-stored orthomosaic map in the context of UAV localization. The proposed deep architecture extracts the features from the aerial imagery and localizes it in a pre-ordained, larger, and geotagged image. The idea is to train a deep learning model to find neighborhood consensus patterns that encapsulate the local patterns in the neighborhood of the established dense feature correspondences by introducing semi-local constraints. We qualitatively and quantitatively evaluate the performance of our approach on real UAV imagery. The training and testing data is acquired via multiple flights over different regions. The source code along with the entire dataset, including the annotations of the collected images has been made public. ¹¹ https://github.com/m-hamza-mughal/Aerial-Template-Matching. Up-to our knowledge, such a dataset is novel and first of its kind which consists of 2052 high-resolution aerial images acquired at different times over three different areas in Pakistan spanning a total area of around 2 km ² .

Change detection using satellite/aerial images is used to quantify the impacts of many natural and man-made disasters. At the occurrence of such events, both prechange optical and synthetic aperture radar (SAR) images can be obtained by going back in time. However, the availability of the postchange optical image is often hindered by the presence of artifacts like clouds. To circumnavigate this, we propose a novel change detection data setting that uses both optical and SAR images prechange, yet only SAR imagery postchange. For this challenging scenario, we propose a Siamese network that processes the prechange and postchange SAR inputs using a shared set of weights, while the prechange optical input is processed using a network that do not share the weights with the SAR inputs. The encoded weights from the three networks are fused and finally decoded using a common decoder to obtain the change map. Our model effectively fuses multisensor information and can obtain satisfactory result despite the absence of the postchange optical image. Experimental results on a multisensor urban dataset demonstrate the effectiveness of the proposed approach.

Emotion recognition via gait analysis is an active and key area of research because of its significant academic and commercial potential. With recent developments in hardware technology, the use of inertial sensors allows researchers to effectively capture the human motion data for gait analysis. To this end, the aim of this paper is to identify emotions from the inertial signals of human gait recorded by means of body mounted smartphones. We extracted a manually-crafted set of features computed from the human inertial gait data which are used to train and precisely predict the human emotions. Specifically, we collected the inertial gait data of 40 volunteers by means of smartphone’s on-board inertial measurement units (3D accelerometer, 3D gyroscope) attached at the chest in six basic emotions including sad, happy, anger, surprise, disgust and fear. Using stride based segmentation, the raw signals are first decomposed into individual strides. For each stride, a set of 296 spectro-temporal features are computed, which are fed into two supervised learning predictors namely Support Vector Machines and Random Forest. The classification results obtained with the proposed methodology and validated with k-fold validation procedure show classification accuracy of 95% for binary emotions and 86% for all six categories of emotions.