Centre de documentation
scientifique

LU-Net, An efficient network for 3D LiDAR point cloud semantic segmentation based on end-to-end-learned 3D features and U-Net / Pierre Biasutti (2019)  

Public Titre : LU-Net, An efficient network for 3D LiDAR point cloud semantic segmentation based on end-to-end-learned 3D features and U-Net Type de document : Article/Communication Auteurs : Pierre Biasutti , Auteur ; Vincent Lepetit, Auteur ; Mathieu Brédif , Auteur ; Jean-François Aujol, Auteur ; Aurélie Bugeau, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2019 Projets : 1-Pas de projet / Conférence : ICCVW 2019, IEEE/CVF International Conference on Computer Vision Workshop 27/10/2019 28/10/2019 Seoul Corée du sud Proceedings Importance : pp 942 - 950 Format : 21 x 30 cm Note générale : Bibliographie préprint dans HAL https://hal.archives-ouvertes.fr/hal-02269915v1 avec titre un peu différent - version finale dans HAL https://hal.archives-ouvertes.fr/hal-02269915v2 This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 777826. Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] extraction de traits caractéristiques [Termes IGN] segmentation sémantique [Termes IGN] semis de points Résumé : (Auteur) We propose LU-Net (for LiDAR U-Net), for the semantic segmentation of a 3D LiDAR point cloud. Instead of applying some global 3D segmentation method such as Point-Net, we propose an end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem. First, a high-level 3D feature extraction module is used to compute 3D local features for each point given its neighbors. Then, these features are projected into a 2D multichannel range-image by considering the topology of the sensor. This range-image later serves as the input to a U-Net segmentation network, which is a simple architecture yet enough for our purpose. In this way, we can exploit both the 3D nature of the data and the specificity of the LiDAR sensor. This approach efficiently bridges between 3D point cloud processing and image processing as it outperforms the state-of-the-art by a large margin on the KITTI dataset, as our experiments show. Moreover, this approach operates at 24fps on a single GPU. This is above the acquisition rate of common LiDAR sensors which makes it suitable for real-time applications. Numéro de notice : C2019-037 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Autre URL associée : vers HAL Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/ICCVW.2019.00123 Date de publication en ligne : 05/03/2020 En ligne : https://doi.org/10.1109/ICCVW.2019.00123 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93282

Vision-based detection of aircrafts and UAVs / Artem Rozantsev (2017)  

Public Titre : Vision-based detection of aircrafts and UAVs Type de document : Thèse/HDR Auteurs : Artem Rozantsev, Auteur ; Pascal Fua, Directeur de thèse ; Vincent Lepetit, Directeur de thèse Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2017 Importance : 117 p. Format : 21 x 30 cm Note générale : bibliographie Thèse présentée à l'Ecole Polytechnique Fédérale de Lausanne pour l'obtention du grade de Docteur ès Sciences Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Télédétection [Termes IGN] apprentissage automatique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] cube espace-temps [Termes IGN] détection d'objet [Termes IGN] drone [Termes IGN] image aérienne [Termes IGN] objet mobile [Termes IGN] régression [Termes IGN] vision par ordinateur Résumé : (auteur) Unmanned Aerial Vehicles are becoming increasingly popular for a broad variety of tasks ranging from aerial imagery to objects delivery. With the expansion of the areas, where drones can be efficiently used, the collision risk with other flying objects increases. Avoiding such collisions would be a relatively easy task, if all the aircrafts in the neighboring airspace could communicate with each other and share their location information. However, it is often the case that either location information is unavailable (e.g. flying in GPS-denied environments) or communication is not possible (e.g. different communication channels or non-cooperative flight scenario). To ensure flight safety in this kind of situations drones need a way to autonomously detect other objects that are intruding the neighboring airspace. Visual-based collision avoidance is of particular interest as cameras generally consume less power and are more lightweight than active sensor alternatives such as radars and lasers. We have therefore developed a set of increasingly sophisticated algorithms to provide drones with a visual collision avoidance capability. First, we present a novel method for detecting flying objects such as drones and planes that occupy a small part of the camera field of view, possibly move in front of complex backgrounds, and are filmed by a moving camera. In order to be solved this problem requires combining motion and appearance information, as neither of the two alone is capable of providing reliable enough detections. We therefore propose a machine learning technique that operates on spatiotemporal cubes of image intensities where individual patches are aligned using an object-centric regression-based motion stabilization algorithm. Second, in order to reduce the need to collect a large training dataset and to manual annotate it, we introduce a way to generate realistic synthetic images. Given only a small set of real examples and a coarse 3D model of the object, synthetic data can be generated in arbitrary quantities and further used to supplement real examples for training a detector. The key ingredient of our method is that the synthetically generated images need to be as close as possible to the real ones not in terms of image quality, but according to the features, used by a machine learning algorithm. Third, though the aforementioned approach yields a substantial increase in performance when using Adaboost and DPM detectors, it does not generalize well to Convolutional Neural Networks, which have become the state-of-the-art. This happens because, as we add more and more synthetic data, the CNNs begin to overfit to the synthetic images at the expense of the real ones. We therefore propose a novel deep domain adaptation technique that allows efficiently combining real and synthetic images without overfitting to either of the two. While most of the adaptation techniques aim at learning features that are invariant to the possible difference of the images, coming from different sources (real and synthetic). Unlike those methods, we suggest modeling this difference with a special two-stream architecture. We evaluate our approach on three different datasets and show its effectiveness for various classification and regression tasks. Note de contenu : Introduction 1- Flying Objects Detection 2- Synthetic Data Generation 3- Domain Adaption for Deep Networks 4- Concluding Remarks Numéro de notice : 25870 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Sciences : Lausanne : Suisse : 2017 En ligne : https://infoscience.epfl.ch/record/227934?ln=fr Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95538