Following an avalanche, one of the factors that affect victims’ chance of survival is the speed with which they are located and dug out. Rescue teams use techniques like trained rescue dogs and electronic transceivers to locate victims. However, the resources and time required to deploy rescue teams are major bottlenecks that decrease a victim’s chance of survival. Advances in the field of Unmanned Aerial Vehicles (UAVs) have enabled the use of flying robots equipped with sensors like optical cameras to assess the damage caused by natural or manmade disasters and locate victims in the debris. In this paper, we propose assisting avalanche search and rescue (SAR) operations with UAVs fitted with vision cameras. The sequence of images of the avalanche debris captured by the UAV is processed with a pre-trained Convolutional Neural Network (CNN) to extract discriminative features. A trained linear Support Vector Machine (SVM) is integrated at the top of the CNN to detect objects of interest. Moreover, we introduce a pre-processing method to increase the detection rate and a post-processing method based on a Hidden Markov Model to improve the prediction performance of the classifier. Experimental results conducted on two different datasets at different levels of resolution show that the detection performance increases with an increase in resolution, while the computation time increases. Additionally, they also suggest that a significant decrease in processing time can be achieved thanks to the pre-processing step.

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

Recent advances in Convolutional Neural Networks (CNNs) have attracted great attention in remote sensing due to their high capability to model high-level semantic content of Remote Sensing (RS) images. However, CNNs do not explicitly retain the relative position of objects in an image and, thus, the effectiveness of the obtained features is limited in the framework of the complex object detection problems. To address this problem, in this paper we introduce Capsule Networks (CapsNets) for object detection in Unmanned Aerial Vehicle-acquired images. Unlike CNNs, CapsNets extract and exploit the information content about objects’ relative position across several layers, which enables parsing crowded scenes with overlapping objects. Experimental results obtained on two datasets for car and solar panel detection problems show that CapsNets provide similar object detection accuracies when compared to state-of-the-art deep models with significantly reduced computational time. This is due to the fact that CapsNets emphasize dynamic routine instead of the depth.

A recent work on retro-remote sensing (converting ancient text descriptions into images) was proposed using a multilabel encoding scheme in which an input text description is represented by a binary vector indicating the presence or absence of specific objects. However, this kind of encoding disregards information such as object attributes and spatial relationship between multiple objects in a description, resulting in images that do not semantically (fully) conform to the input description. In this letter, we propose an improved text-encoding mechanism that takes into account different levels of information available from an input text. The encoded text is then used as conditional information to guide the image synthesis process using generative adversarial networks (GANs). Besides, we present a modified GAN architecture intending to improve the semantic content of the generated images. Both the qualitative and quantitative results obtained indicate that the proposed method is particularly promising.