Different imaging solutions have been proposed over the last few decades, aimed at three-dimensional (3D) space reconstruction and obstacle detection, either based on stereo-vision principles using active pixel sensors operating in the visible part of the spectra or based on active Near Infra-Red (NIR) illumination applying the time-of-flight principle, to mention just a few. If extremely low quantum efficiencies for NIR active illumination yielded by silicon-based detector solutions are considered together with the huge photon noise levels produced by the background illumination accompanied by Rayleigh scattering effects taking place in outdoor applications, the operating limitations of these systems under harsh weather conditions, especially if relatively low-power active illumination is used, are evident. If longer wavelengths for active illumination are applied to overcome these issues, indium gallium arsenide (InGaAs)-based photodetectors become the technology of choice, and for low-cost solutions, using a single InGaAs photodetector or an InGaAs line-sensor becomes a promising choice. In this case, the principles of Single-Pixel Imaging (SPI) and compressive sensing acquire a paramount importance. Thus, in this paper, we review and compare the different SPI developments reported. We cover a variety of SPI system architectures, modulation methods, pattern generation and reconstruction algorithms, embedded system approaches, and 2D/3D image reconstruction methods. In addition, we introduce a Near Infra-Red Single-Pixel Imaging (NIR-SPI) sensor aimed at detecting static and dynamic objects under outdoor conditions for unmanned aerial vehicle applications.

Nowadays unmanned aerial vehicles (UAV's) are increasingly considered in several engineering and safety applications to explore unknown environments. Forest environments are among these environments of interest where autonomous exploration and navigation is desirable with the caveat that GPS may not be accessible for localization of the drone. Motivated by the latter, in this paper we present a methodology for autonomous navigation of UAV in forest environments, paying particular attention to competences desired in autonomous navigation, namely detection and evasion of trees. Obstacle detection is performed using a deep neural network approach trained with a limited database but that exploits transferred learning from a well-known network architecture called Alexnet. In addition to the detection of a tree, a direction of avoidance is also recognized, this is, evasion to the left or to the right is obtained with the same learning scheme. Our approached was assessed in simulation by using the simulator Gazebo and also in a real outdoors scenario populated with trees.

Autonomous Drone Racing (ADR) was first proposed in IROS 2016. It called for the development of an autonomous drone capable of beating a human in a drone race. After almost five years, several teams have proposed different solutions with a common pipeline: gate detection; drone localization; and stable flight control. Recently, Deep Learning (DL) has been used for gate detection and localization of the drone regarding the gate. However, recent competitions such as the Game of Drones, held at NeurIPS 2019, called for solutions where DL played a more significant role. Motivated by the latter, in this work, we propose a CNN approach called DeepPilot that takes camera images as input and predicts flight commands as output. These flight commands represent: the angular position of the drone’s body frame in the roll and pitch angles, thus producing translation motion in those angles; rotational speed in the yaw angle; and vertical speed referred as altitude h. Values for these 4 flight commands, predicted by DeepPilot, are passed to the drone’s inner controller, thus enabling the drone to navigate autonomously through the gates in the racetrack. For this, we assume that the next gate becomes visible immediately after the current gate has been crossed. We present evaluations in simulated racetrack environments where DeepPilot is run several times successfully to prove repeatability. In average, DeepPilot runs at 25 frames per second (fps). We also present a thorough evaluation of what we called a temporal approach, which consists of creating a mosaic image, with consecutive camera frames, that is passed as input to the DeepPilot. We argue that this helps to learn the drone’s motion trend regarding the gate, thus acting as a local memory that leverages the prediction of the flight commands. Our results indicate that this purely DL-based artificial pilot is feasible to be used for the ADR challenge.