Javier Antonio Gonzalez-Trejo

Hector Tovanche-Picon, Javier Gonzalez-Trejo, Angel Flores-Abad et al.

Safe autonomous landing for Unmanned Aerial Vehicles (UAVs) in populated areas is a crucial aspect for successful urban deployment, particularly in emergency landing situations. Nonetheless, validating autonomous landing in real scenarios is a challenging task involving a high risk of injuring people. In this work, we propose a framework for real-time safe and thorough evaluation of vision-based autonomous landing in populated scenarios, using photo-realistic virtual environments. We propose to use the Unreal graphics engine coupled with the AirSim plugin for drone's simulation, and evaluate autonomous landing strategies based on visual detection of Safe Landing Zones (SLZ) in populated scenarios. Then, we study two different criteria for selecting the "best" SLZ, and evaluate them during autonomous landing of a virtual drone in different scenarios and conditions, under different distributions of people in urban scenes, including moving people. We evaluate different metrics to quantify the performance of the landing strategies, establishing a baseline for comparison with future works in this challenging task, and analyze them through an important number of randomized iterations. The study suggests that the use of the autonomous landing algorithms considerably helps to prevent accidents involving humans, which may allow to unleash the full potential of drones in urban environments near to people.

Javier González-Trejo, Diego Mercado-Ravell, Israel Becerra et al.

Autonomous landing of Unmanned Aerial Vehicles (UAVs) in crowded scenarios is crucial for successful deployment of UAVs in populated areas, particularly in emergency landing situations where the highest priority is to avoid hurting people. In this work, a new visual-based algorithm for identifying Safe Landing Zones (SLZ) in crowded scenarios is proposed, considering a camera mounted on an UAV, where the people in the scene move with unknown dynamics. To do so, a density map is generated for each image frame using a Deep Neural Network, from where a binary occupancy map is obtained aiming to overestimate the people's location for security reasons. Then, the occupancy map is projected to the head's plane, and the SLZ candidates are obtained as circular regions in the head's plane with a minimum security radius. Finally, to keep track of the SLZ candidates, a multiple instance tracking algorithm is implemented using Kalman Filters along with the Hungarian algorithm for data association. Several scenarios were studied to prove the validity of the proposed strategy, including public datasets and real uncontrolled scenarios with people moving in public squares, taken from an UAV in flight. The study showed promising results in the search of preventing the UAV from hurting people during emergency landing.

Javier Antonio Gonzalez-Trejo, Diego Alberto Mercado-Ravell

In the context of crowd counting, most of the works have focused on improving the accuracy without regard to the performance leading to algorithms that are not suitable for embedded applications. In this paper, we propose a lightweight convolutional neural network architecture to perform crowd detection and counting using fewer computer resources without a significant loss on count accuracy. The architecture was trained using the Bayes loss function to further improve its accuracy and then pruned to further reduce the computational resources used. The proposed architecture was tested over the USF-QNRF achieving a competitive Mean Average Error of 154.07 and a superior Mean Square Error of 241.77 while maintaining a competitive number of parameters of 0.067 Million. The obtained results suggest that the Bayes loss can be used with other architectures to further improve them and also the last convolutional layer provides no significant information and even encourage over-fitting at training.