Centre dedocumentation
scientifique

Ensemble methods for pedestrian detection in dense crowds / Jennifer Vandoni (2019)  

Public Titre : Ensemble methods for pedestrian detection in dense crowds Type de document : Thèse/HDR Auteurs : Jennifer Vandoni, Auteur ; Sylvie Le Hégarat-Mascle, Directeur de thèse Editeur : Paris-Orsay : Université de Paris 11 Paris-Sud Centre d'Orsay Année de publication : 2019 Importance : 182 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université Paris-Saclay, Sciences et technologies de l’information et de la communication (STIC), Spécialité : Traitement du Signal et des Images Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] apprentissage dirigé [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] comportement [Termes descripteurs IGN] densité de population [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] données multicapteurs [Termes descripteurs IGN] étalonnage [Termes descripteurs IGN] fusion de données [Termes descripteurs IGN] taxinomie [Termes descripteurs IGN] théorie de Dempster-Shafer Index. décimale : THESE Thèses et HDR Résumé : (auteur) The interest surrounding the study of crowd phenomena spanned during the last decade across multiple fields, including computer vision, physics, sociology, simulation and visualization. There are different levels of granularity at which crowd studies can be performed, namely a finer microanalysis, aimed to detect and then track each pedestrian individually; and a coarser macro-analysis, aimed to model the crowd as a whole. One of the most difficult challenges when working with human crowds is that usual pedestrian detection methodologies do not scale well to the case where only heads are visible, for a number of reasons such as absence of background, high visual homogeneity, small size of the objects, and heavy occlusions. For this reason, most micro-analysis studies by means of pedestrian detection and tracking methodologies are performed in low to medium-density crowds, whereas macro-analysis through density estimation and people counting is more suited in presence of high-density crowds, where the exact position of each individual is not necessary. Nevertheless, in order to analyze specific events involving high-density crowds for monitoring the flow and preventing disasters such as stampedes, a complete understanding of the scene must be reached. This study deals with pedestrian detection in high-density crowds from a monocamera system, striving to obtain localized detections of all the individuals which are part of an extremely dense crowd. The detections can be then used both to obtain robust density estimation, and to initialize a tracking algorithm. In presence of difficult problems such as our application, supervised learning techniques are well suited. However, two different questions arise, namely which classifier is the most adapted for the considered environment, and which data to use to learn from. We cast the detection problem as a Multiple Classifier System (MCS), composed by two different ensembles of classifiers, the first one based on SVM (SVM-ensemble) and the second one based on CNN (CNN-ensemble), combined relying on the Belief Function Theory (BFT) designing a fusion method which is able to exploit their strengths for pixel-wise classification. SVM-ensemble is composed by several SVM detectors based on different gradient, texture and orientation descriptors, able to tackle the problem from different perspectives. BFT allows us to take into account the imprecision in addition to the uncertainty value provided by each classifier, which we consider coming from possible errors in the calibration procedure and from pixel neighbor’s heterogeneity in the image space due to the close resolution of the target (head) and descriptor respectively. However, scarcity of labeled data for specific dense crowd contexts reflects in the impossibility to easily obtain robust training and validation sets. By exploiting belief functions directly derived from the classifiers’ combination, we therefore propose an evidential Query-by-Committee (QBC) active learning algorithm to automatically select the most informative training samples. On the other side, we explore deep learning techniques by casting the problem as a segmentation task in presence of soft labels, with a fully convolutional network architecture designed to recover small objects (heads) thanks to a tailored use of dilated convolutions. In order to obtain a pixel-wise measure of reliability about the network’s predictions, we create a CNN-ensemble by means of dropout at inference time, and we combine the different obtained realizations in the context of BFT. To conclude, we show that the dense output map given by the MCS can be employed not only for pedestrian detection at microscopic level, but also to perform macroscopic analysis, bridging the gap between the two levels of granularity. We therefore finally focus our attention to people counting, proposing an evaluation method that can be applied at every scale, resulting to be more precise in the error and uncertainty evaluation (disregarding possible compensations) as well as more useful for the modeling community that could use it to improve and validate local density estimation. Note de contenu : 1- Crowd understanding 2- Supervised learning and classifier combination 3- SVM descriptors for pedestrian detection in high-density crowds 4- Taking into account imprecision with Belief Function Framework 5- Evidential QBC Active Learning 6- CNNs for pedestrian detection in high-density crowds 7- CNN-ensemble and evidential Multiple Classifier System 8- Density Estimation Conclusion Numéro de notice : 25704 Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Sciences et technologies de l’information et de la communication : Spécialité : Traitement du Signal et des Images : Paris 11 : 2019 Organisme de stage : Systèmes et applications des technologies de l'information et de l'énergie (Paris) En ligne : http://www.theses.fr/2019SACLS116 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94838

Spatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data / Michalis A. Savelonas in Computer Vision and image understanding, vol 171 (June 2018)  

Public [article]  inComputer Vision and image understanding > vol 171 (June 2018) . - pp 1 - 9 Titre : Spatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data Type de document : Article/Communication Auteurs : Michalis A. Savelonas, Auteur ; Ioannis Pratikakis, Auteur ; Theoharis Theoharis, Auteur ; Georgios Thanellas, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 1 - 9 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] analyse de sensibilité [Termes descripteurs IGN] analyse spatiale [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] codage [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] discrétisation spatiale [Termes descripteurs IGN] distribution de Fisher [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] reconnaissance de formes Résumé : (auteur) Range-based pedestrian recognition is instrumental towards the development of autonomous driving and driving assistance systems. This work introduces encoding methods for pedestrian recognition, based on statistical shape analysis of 3D LIDAR data. The proposed approach has two variants, based on the encoding of local shape descriptors either in a spatially agnostic or spatially sensitive fashion. The latter method derives more detailed cues, by enriching the ‘gross’ information reflected by overall statistics of local shape descriptors, with ‘fine-grained’ information reflected by statistics associated with spatial clusters. Experiments on artificial LIDAR datasets, which include challenging samples, as well as on a large scale dataset of real LIDAR data, lead to the conclusion that both variants of the proposed approach (i) obtain high recognition accuracy, (ii) are robust against low-resolution sampling, (iii) are robust against increasing distance, and (iv) are robust against non-standard shapes and poses. On the other hand, the spatially-sensitive variant is more robust against partial occlusion and bad clustering. Numéro de notice : A2018-586 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.cviu.2018.06.001 date de publication en ligne : 15/06/2018 En ligne : https://www.sciencedirect.com/science/article/pii/S1077314218300766 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92439 [article]

Generating a hazard map of dynamic objects using lidar mobile mapping / Alexander Schlichting in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 12 (December 2016)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 82 n° 12 (December 2016) . - pp 967 - 972 Titre : Generating a hazard map of dynamic objects using lidar mobile mapping Type de document : Article/Communication Auteurs : Alexander Schlichting, Auteur ; Claus Brenner, Auteur Année de publication : 2016 Article en page(s) : pp 967 - 972 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes descripteurs IGN] aléa [Termes descripteurs IGN] cartographie cadastrale [Termes descripteurs IGN] cartographie des risques [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] processus [Termes descripteurs IGN] système de numérisation mobile [Termes descripteurs IGN] véhicule sans pilote Résumé : (auteur) One of the hardest problems for future self-driving cars is to predict hazardous situations involving pedestrians and cyclists. Human drivers solve this problem typically by having a deeper understanding of the scene. The technical equivalent of this is to provide a hazard map, which serves as a prior for self-driving cars, enabling them to adjust driving speed and processing thresholds. In this paper, we present a method to derive such a hazard map using lidar mobile mapping. Pedestrians and cyclists are obtained from a sequence of point clouds by segmentation and classification. Their locations are then accumulated in a grid map, which serves as a "heat map" for possible hazardous situations. To demonstrate our approach, we generated a map using lidar mobile mapping, obtained by twelve measurement campaigns in Hanover (Germany). Our results show different outcomes for the city center, residential areas, busy roads, and road junctions. Numéro de notice : A2016-985 Thématique : IMAGERIE Nature : Article En ligne : https://doi.org/10.14358/PERS.82.12.967 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83701 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2016121	SL	Revue	Centre de documentation	Revues en salle	Disponible

Simultaneous detection and tracking of pedestrian from panoramic laser scanning data / Wen Xiao in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, III-3 (July 2016)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > III-3 (July 2016) . - pp 295 - 302 Titre : Simultaneous detection and tracking of pedestrian from panoramic laser scanning data Type de document : Article/Communication Auteurs : Wen Xiao, Auteur ; Bruno Vallet , Auteur ; Konrad Schindler, Auteur ; Nicolas Paparoditis , Auteur Année de publication : 2016 Article en page(s) : pp 295 - 302 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] cible mobile [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] objet mobile [Termes descripteurs IGN] piéton [Termes descripteurs IGN] trafic [Termes descripteurs IGN] trajet Résumé : (auteur) Pedestrian traffic flow estimation is essential for public place design and construction planning. Traditional data collection by human investigation is tedious, inefficient and expensive. Panoramic laser scanners, e.g. Velodyne HDL-64E, which scan surroundings repetitively at a high frequency, have been increasingly used for 3D object tracking. In this paper, a simultaneous detection and tracking (SDAT) method is proposed for precise and automatic pedestrian trajectory recovery. First, the dynamic environment is detected using two different methods, Nearest-point and Max-distance. Then, all the points on moving objects are transferred into a space-time (x, y, t) coordinate system. The pedestrian detection and tracking amounts to assign the points belonging to pedestrians into continuous trajectories in space-time. We formulate the point assignment task as an energy function which incorporates the point evidence, trajectory number, pedestrian shape and motion. A low energy trajectory will well explain the point observations, and have plausible trajectory trend and length. The method inherently filters out points from other moving objects and false detections. The energy function is solved by a two-step optimization process: tracklet detection in a short temporal window; and global tracklet association through the whole time span. Results demonstrate that the proposed method can automatically recover the pedestrians trajectories with accurate positions and low false detections and mismatches. Numéro de notice : A2016-818 Thématique : IMAGERIE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-III-3-295-2016 date de publication en ligne : 06/06/2016 En ligne : http://dx.doi.org/10.5194/isprs-annals-III-3-295-2016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82619 [article]

Personal mobility pattern mining and anomaly detection in the GPS era / Dong-He Shih in Cartography and Geographic Information Science, Vol 43 n° 1 (January 2016)  

Public [article]  inCartography and Geographic Information Science > Vol 43 n° 1 (January 2016) . - pp 55 - 67 Titre : Personal mobility pattern mining and anomaly detection in the GPS era Type de document : Article/Communication Auteurs : Dong-He Shih, Auteur ; Ming-Hung Shih, Auteur ; David C. Yen, Auteur ; Jai-Hung Hsu, Auteur Année de publication : 2016 Article en page(s) : pp 55 - 67 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes descripteurs IGN] comportement [Termes descripteurs IGN] détection d'anomalie [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] itinéraire [Termes descripteurs IGN] positionnement par GPS [Termes descripteurs IGN] santé [Termes descripteurs IGN] surveillance Résumé : (Auteur) Suffering from Alzheimer’s disease has become one of the critical health issues today. If an abnormal time–space pattern of such patients can be detected earlier, it will help the families to prevent some dangerous situations in advance. We have proposed a method in this study to uncover personal mobility patterns and detect abnormal behavior patterns from mobility data obtained with global position system (GPS). Experimental results showed that our proposed method is far better than other alternatives available. This proposed approach may thus render great assistance in identifying abnormal behavior, thus providing critical remedy actions in advance in this GPS era. Numéro de notice : A2016-110 Thématique : POSITIONNEMENT Nature : Article DOI : 10.1080/15230406.2015.1010585 En ligne : https://doi.org/10.1080/15230406.2015.1010585 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79929 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2016011	SL	Revue	Centre de documentation	Revues en salle	Disponible

Probabilistic multi-person localisation and tracking / Tobias Klinger (2016) 

Permalink

A multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification / Z. Wang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)

Permalink

User-side adaptive protection of location privacy in participatory sensing / Becker Agir in Geoinformatica, vol 18 n° 1 (January 2014)  

Permalink

Automatic detection and tracking of pedestrians from a moving stereo rig / Konrad Schindler in ISPRS Journal of photogrammetry and remote sensing, vol 65 n° 6 (November - December 2010)

Permalink

Face blurring for privacy in street-level geoviewers combining face, body and skin detectors / Alexandre Devaux (20/05/2009)  

Permalink