Dissertation/ Thesis

Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions ; Analyse des mouvements et gestes des piétons via caméra embarquée pour la prédiction de leurs intentions

التفاصيل البيبلوغرافية
العنوان: Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions ; Analyse des mouvements et gestes des piétons via caméra embarquée pour la prédiction de leurs intentions
المؤلفون: Gesnouin, Joseph
المساهمون: Centre de Robotique (CAOR), Mines Paris - PSL (École nationale supérieure des mines de Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Université Paris sciences et lettres, Fabien Moutarde
المصدر: https://pastel.hal.science/tel-03813520 ; Robotics [cs.RO]. Université Paris sciences et lettres, 2022. English. ⟨NNT : 2022UPSLM023⟩.
بيانات النشر: HAL CCSD
سنة النشر: 2022
المجموعة: Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe)
مصطلحات موضوعية: Skeleton-based action prediction, Learning spatio-temporal representations, Predictive uncertainty estimation, Prédiction d’action basée sur le squelette, Apprentissage des représentations spatio-temporelles, Estimation de l’incertitude prédictive, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]
الوصف: The autonomous vehicle (AV) is a major challenge for the mobility of tomorrow. Progress is being made every day to achieve it; however, many problems remain to be solved to achieve a safe outcome for the most vulnerable road users (VRUs). One of the major challenge faced by AVs is the ability to efficiently drive in urban environments. Such a task requires interactions between autonomous vehicles and VRUs to resolve traffic ambiguities. In order to interact with VRUs, AVs must be able to understand their intentions and predict their incoming actions. In this dissertation, our work revolves around machine learning technology as a way to understand and predict human behaviour from visual signals and more specifically pose kinematics. Our goal is to propose an assistance system to the AV that is lightweight, scene-agnostic that could be easily implemented in any embedded devices with real-time constraints. Firstly, in the gesture and action recognition domain, we study and introduce different representations for pose kinematics, based on deep learning models as a way to efficiently leverage their spatial and temporal components while staying in an euclidean grid-space. Secondly, in the autonomous driving domain, we show that it is possible to link the posture, the walking attitude and the future behaviours of the protagonists of a scene without using the contextual information of the scene (zebra crossing, traffic light.). This allowed us to divide by a factor of 20 the inference speed of existing approaches for pedestrian intention prediction while keeping the same prediction robustness. Finally, we assess the generalization capabilities of pedestrian crossing predictors and show that the classical train-test sets evaluation for pedestrian crossing prediction, i.e., models being trained and tested on the same dataset, is not sufficient to efficiently compare nor conclude anything about their applicability in a real-world scenario. To make the research field more sustainable and representative of the real advances ...
نوع الوثيقة: doctoral or postdoctoral thesis
اللغة: English
Relation: NNT: 2022UPSLM023; tel-03813520; https://pastel.hal.science/tel-03813520; https://pastel.hal.science/tel-03813520/document; https://pastel.hal.science/tel-03813520/file/2022UPSLM023_archivage.pdf
الاتاحة: https://pastel.hal.science/tel-03813520
https://pastel.hal.science/tel-03813520/document
https://pastel.hal.science/tel-03813520/file/2022UPSLM023_archivage.pdf
Rights: info:eu-repo/semantics/OpenAccess
رقم الانضمام: edsbas.9B0DD97
قاعدة البيانات: BASE