Human trajectory prediction is a quite challenging task mainly due to numerous social interactions and plausible paths in complex crowed scenarios and varying environments. Data-driven machine learning approaches based on Recurrent Neural Networks (RNNs) have, recently, achieved significant results in modelling human-human interactions in a scene. However, information-sharing pooling modules across RNN Encoders which operate on a local spatial context fail to model long-term scene level correlations, while other that adopt a more global approach are restricted to a rather simplistic formulations due to high computational costs. In this work, we introduce a novel pooling mechanism designed to perform trajectory pooling on a higher semantic level. We have developed a novel multi-layer network architecture based on a new Edge Convolutional operator acting on irregular data which is able to generalize local human-human interactions on a semantic social context. To assess the performance of the proposed social pooling with edge convolutions, we have integrated it into a state-of-the-art trajectory prediction framework based on Generative Adversarial Networks (GANs). Our module managed to overall outperform, by a significant margin, several state-of-the-art pooling modules in real-world challenging benchmark datasets.

Data association is a crucial component for any multiple object tracking (MOT) method that follows the tracking-by-detection paradigm. To generate complete trajectories such methods employ a data association process to establish assignments between detections and existing targets during each timestep. Recent data association approaches try to solve a multi-dimensional linear assignment task or a network flow minimization problem or either tackle it via multiple hypotheses tracking. However, during inference an optimization step that computes optimal assignments is required for every sequence frame adding significant computational complexity in any given solution. To this end, in the context of this work we introduce Transformer-based Assignment Decision Network (TADN) that tackles data association without the need of any explicit optimization during inference. In particular, TADN can directly infer assignment pairs between detections and active targets in a single forward pass of the network. We have integrated TADN in a rather simple MOT framework, we designed a novel training strategy for efficient end-to-end training and demonstrate the high potential of our approach for online visual tracking-by-detection MOT on two popular benchmarks, i.e. MOT17 and UA-DETRAC. Our proposed approach outperforms the state-of-the-art in most evaluation metrics despite its simple nature as a tracker which lacks significant auxiliary components such as occlusion handling or re-identification. The implementation of our method is publicly available at https://github.com/psaltaath/tadn-mot.

The Harmonized LandSat-Sentinel (HLS) dataset has significantly advanced Earth Observation by integrating data from Landsat and Sentinel satellites. However, challenges persist in achieving spectral band parity between LandSat and Sentinel-derived HLS products. This paper presents an extended investigation aimed at enhancing spatial reconstruction accuracy to enable spectral band parity within HLS products. Building upon our previous work, which utilized generative neural networks to address partial feature mismatches between S30 and L30 products, we introduce a refined approach that fully integrates a Self-Supervised Learning (SSL)-pretrained encoder into a U-Net architecture. This method aims to access multi-scale features and improve spatial reconstruction accuracy, addressing the limitations in spatial resolution observed in our earlier study. Our methodology incorporates a comprehensive ablation study to assess various SSL-pretrained backbone architectures. Preliminary results demonstrate significant improvements in spatial reconstruction accuracy compared to our previous work. The adapted U-Net architecture, leveraging SSL-pretrained encoders, shows enhanced capability in capturing intricate spatial features within the HLS dataset. Our experiments demonstrate a substantial improvement in spatial resolution and feature reconstruction for L30 products, particularly in bands not natively present in Landsat data, paving the way for more accurate multi-sensor analyses.

Driver behaviour in the dilemma zone critically influences red-light violations and intersection safety. This study presents a scalable Vision-AI and deep

The sustainability of apiculture within Mediterranean forest ecosystems is contingent upon the extent and health of melliferous tree habitats. This study outlines a five-year initiative (2020–2024) aimed at mapping and monitoring four principal honey-producing tree species—pine (Pinus halepensis and Pinus nigra), Greek fir (Abies cephalonica), oak (Quercus ithaburensis subsp. macrolepis), and chestnut (Castanea sativa)—across Evia, Greece. This is achieved through the utilization of high-resolution Sentinel-2 satellite imagery in conjunction with a hierarchical deep learning framework. Distinct from prior vegetation mapping endeavors, this research introduces an innovative application of a hierarchical framework for species-level semantic segmentation of apicultural flora, employing a U-Net convolutional neural network to capture fine-scale spatial and temporal dynamics. The proposed framework first stratifies forests into broadleaf and coniferous types using Copernicus DLT data, and subsequently applies two specialized U-Net models trained on Sentinel-2 NDVI time series and DEM-derived topographic variables to (i) discriminate pine from fir within coniferous forests and (ii) distinguish oak from chestnut within broadleaf stands. This hierarchical decomposition reduces spectral confusion among structurally similar species and enables fine-scale semantic segmentation of apicultural flora. Our hierarchical framework achieves 92.1% overall accuracy, significantly outperforming traditional multiclass approaches (89.5%) and classical ML methods (76.9%). The results demonstrate the framework’s efficacy in accurately delineating species distributions, quantifying the ecological and economic impacts of the catastrophic 2021 forest fires, and projecting long-term habitat recovery trajectories. The integration of a novel hierarchical approach with Deep Learning-driven monitoring of climate- and disturbance-driven changes in honey-producing habitats marks a significant step towards more effective assessment and management of four major beekeeping tree species. These findings highlight the significance of such methodologies in guiding conservation, restoration, and adaptive management strategies, ultimately supporting resilient apiculture and safeguarding ecosystem services in fire-prone Mediterranean landscapes.