CONF Villamizar_ECCV_2024/IDIAP Investigating Semantic Segmentation Models to Assist Visually Impaired People Villamizar, Michael Canévet, Olivier Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/papers/2024/Villamizar_ECCV_2024.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Villamizar_Idiap-RR-13-2024 Related documents European Conference on Computer Vision - Workshops 2024 In this work, we address the semantic segmentation task with the purpose of allowing visually impaired people to comprehend their environments. To this end, we study and leverage convolutional networks trained on public automotive datasets and a new egocentric infrared dataset collected in urban areas. Domain adaptation, efficiency and segmentation accuracy are the focus of our study. REPORT Villamizar_Idiap-RR-13-2024/IDIAP Investigating Semantic Segmentation Models to Assist Visually Impaired People Villamizar, Michael Canévet, Olivier Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/reports/2024/Villamizar_Idiap-RR-13-2024.pdf PUBLIC Idiap-RR-13-2024 2024 Idiap November 2024