Publications by authors named "Alvaro Hernandez Saz"
Article Synopsis
- Understanding urban intersections is vital for self-driving cars and Advanced Driver Assistance Systems (ADAS) since these areas account for a significant percentage of road fatalities.
- The research investigates various methods for detecting and classifying intersection geometries using front-facing cameras, exploring both single-frame and temporal integration approaches with Deep Neural Networks (DNNs).
- A new dataset is created through data augmentation using Generative Adversarial Networks (GANs) to enhance training data quality and generalizability, highlighting the importance of camera field of view over other factors.
Anticipating pedestrian crossing behavior in urban scenarios is a challenging task for autonomous vehicles. Early this year, a benchmark comprising JAAD and PIE datasets have been released. In the benchmark, several state-of-the-art methods have been ranked.
View Article and Find Full Text PDF