Centre de documentation
scientifique

Exploring data fusion for multi-object detection for intelligent transportation systems using deep learning / Amira Mimouna (2022)  

Public Titre : Exploring data fusion for multi-object detection for intelligent transportation systems using deep learning Type de document : Thèse/HDR Auteurs : Amira Mimouna, Auteur ; Abdelmalik Taleb-Ahmed, Directeur de thèse ; Najoua Essoukri Ben Amara, Directeur de thèse Editeur : Valenciennes : Université polytechnique Hauts-de-France Année de publication : 2022 Note générale : bibliographie Thèse de doctorat pour obtenir le grade de Docteur de l'Université polytechnique Hauts-de-France et l'INSA Hauts-de-France et l'Université de Sousse, spécialité Electronique, Acoustique et Télécommunications Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] détection d'objet [Termes IGN] données publiques [Termes IGN] entropie [Termes IGN] profil d'obstacle [Termes IGN] segmentation d'image [Termes IGN] système de transport intelligent [Termes IGN] trafic urbain [Termes IGN] transformation en ondelettes [Termes IGN] vision par ordinateur [Termes IGN] zone d'intérêt Index. décimale : THESE Thèses et HDR Résumé : (auteur) Building reliable environment perception systems is a crucial task for autonomous driving, especially in dense traffic areas. Researching in this field is evolving increasingly. However, we are at the beginning of a research pathway towards a future generation of intelligent transportation systems. In fact, challenging conditions in real-world driving circumstances, infrastructure monitoring, and accurate real-time system response, are the predominant concerns when developing such systems. Recent improvements and breakthroughs in scene understanding for intelligent transportation systems have been mainly based on deep learning and the fusion of different modalities. In this context, firstly, we introduce OLIMP : A heterOgeneous MuLtimodal Dataset for Advanced EnvIronMent Perception . This is the first public, multimodal and synchronized dataset that includes Ultra Wide-Band (UWB) radar data, acoustic data, narrowband radar data and images. OLIMP comprises 407 scenes and 47,354 synchronized frames, including four categories: pedestrians, cyclists, cars and trams. The dataset presents various challenges related to dense urban traffic such as cluttered environments and differentweather conditions. To demonstrate the usefulness of the introduced dataset, we propose, afterwards, a fusion framework that combines the four modalities for multi object detection. The obtained results are promising and spur for future research. In short range settings, UWB radars represent a promising technology for building reliable obstacle detection systems as they are robust to environmental conditions. However, UWB radars suffer from a segmentation challenge: localizing relevant Regions Of Interests (ROIs) within its signals. Therefore, we put froward a segmentation approach to detect ROIs in an environment perception-dedicated UWB radar as a third contribution. Specifically, we implement a differential entropy analysis to detect ROIs. The obtained results show higher performance in terms of obstacle detection compared to state-of-theart techniques, as well as stable robustness even with low amplitude signals. Subsequently, we propose a novel framework that exploits Recurrent Neural Networks (RNNs) with UWB signals for multiple road obstacle detection as a deep learning-based approach. Features are extracted from the time-frequency domain using the discrete wavelet transform and are forwarded to the Long short-term memory (LSTM) network. The obtained results show that the LSTM-based system outperforms the other implemented related techniques in terms of obstacle detection. Note de contenu : 1- Introduction 2- Environment perception system: State of the art 3- OLIMP: A heterogeneous multimodal dataset for advanced environment perception 4- Multiple object detectors using UWB signals 5- Conclusions and perspectives Numéro de notice : 15289 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Electronique, Acoustique et Télécommunications : Université polytechnique Hauts-de-France : 2022 Organisme de stage : Institut d'électronique, de microélectronique et de nanotechnologie DOI : sans En ligne : https://hal.science/tel-03522730 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101520