Approches de Deep Learning pour la segmentation d’image en temps réel dans la conduite autonome

dc.contributor.author	BOUFADES, Hind
dc.contributor.author	SLIMANE, Djihane
dc.date.accessioned	2026-01-18T09:43:59Z
dc.date.available	2026-01-18T09:43:59Z
dc.date.issued	2025
dc.description	Spécialité : ELECTRONIQUE DES SYSTEMES EMBARQUES	en_US
dc.description.abstract	Real-time semantic segmentation is a key task in computer vision, especially for autonomous driving systems where quick and accurate perception is essential. This thesis explores deep learning techniques for this task using the U-Net architecture, applied to the Cityscapes dataset of urban driving scenes. To enhance performance, we replaced the original U-Net encoder with EfficientNet-B0, aiming to achieve both high segmentation accuracy and real-time inference speed. The proposed model reached over 61.8% mean IoU and 128 FPS, making it highly suitable for real-time applications. The work was developed using Google Colab and benefited from an internship at CRTI, which provided technical support and valuable resources. Despite certain challenges such as limited annotation in the test set, the final results demonstrate the model’s efficiency and robustness.	en_US
dc.identifier.uri	http://dspace.univ-chlef.dz/handle/123456789/2238
dc.publisher	BAHI AZZOUOUM Ahmed / BENYAHIA Ahmed	en_US
dc.subject	Deep learning	en_US
dc.subject	semantic segmentation	en_US
dc.subject	U-Net	en_US
dc.title	Approches de Deep Learning pour la segmentation d’image en temps réel dans la conduite autonome	en_US
dc.type	Thesis	en_US

Files

Now showing 1 - 1 of 1

Name:: Approches de deep lerning pour la segmentation d'image en temps réél dans la conduite autonome..pdf
Size:: 5.7 MB
Format:: Adobe Portable Document Format
Description:

Now showing 1 - 1 of 1