ISEP - DM – Engenharia de Inteligência Artificial
URI permanente para esta coleção:
Navegar
Percorrer ISEP - DM – Engenharia de Inteligência Artificial por orientador "Dias, André Miguel Pinheiro"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Deep learning for monocular visual odometry: From sequential pose regression to self-attention learningPublication . DATSENKO, DARYNA; Dias, André Miguel PinheiroMonocular visual odometry (VO) estimates the position and orientation of a moving system using images from a single camera. It is widely used in robotics, autonomous driving, and UAVs. Compared to stereo or LiDAR systems, monocular VO avoids extra hardware, but it faces challenges such as scale ambiguity, sensitivity to lighting changes, and poor generalization to new environments. Deep learning has recently become a promising approach, as it allows networks to learn motion and geometry directly from images. This thesis studies deep learning methods for monocular VO. First, a simple CNN–LSTM baseline inspired by DeepVO is evaluated. This model works well on KITTI with Absolute Trajectory Error(ATE): 37.14 m; scale recovery: 0.998) and trains relatively fast, but it fails to converge on more dynamic or indoor datasets like TartanAir and EuRoC MAV, showing the limitations of learning pose from images alone. To improve performance, the model is gradually extended with self-attention and an auxiliary depth prediction branch, forming a multi-task framework that jointly learns pose and depth. This adds geometric constraints that reduce scale drift and improve trajectory consistency. The training strategy combines synthetic pretraining on TartanAir, using perfect depth supervision, with fine-tuning on EuRoC MAV using pseudo-depth maps. Experiments show significant improvements: on EuRoC V102, the multi-task model achieves an ATE of 0.825 m over a 42.53 m path, closely matching the ground truth (40.12 m) with a scale recovery of 1.059. These results outperform classical methods like ORB-SLAM3 and approach state-of-the-art learning-based approaches. The two main contributions of this work are: first, proposing and testing a framework that gradually moves from simple CNN–LSTM pose regression to a multi-task model with depth and self-attention; second, analyzing the benefits and limitations of this approach. The results show that depth supervision, even if not perfect, stabilizes motion estimation and improves consistency, pointing to promising directions for learning-based pose estimation in complex environments.
- Solar panels issues and failures identificationPublication . Pinto, Augusto Manuel dos Inocentes Rodrigues; Dias, André Miguel PinheiroRecent push for the use of photovoltaic panels due to the focus on the green transition as created an inspection problem, a problem that cannot be avoided because these inspections are critical to guarantee the maximum efficiency of the photovoltaic panels and their longevity. At the same time, drone technology and machine learning technologies had significant advances, that allowed these areas to work together in order to solve the automatic panel inspection tasks more efficiently than recurring to manual processes of inspection. Detection of hotspots represent a dominant problem over solar plants energy yield, as well as over the possibility of downtime and interruptions on the grid. This project focus on automatic detection of photovoltaic panel specific failures, using thermal images collected by infrared cameras transported on UAV vehicles. It intends to prove the efficiency of the use of artificial neural networks detecting failures on thermographic images recollected by sensors mounted on Unmanned Aerial Vehicles.