1,720,983 research outputs found
BEYOND MULTI-TARGET TRACKING: STATISTICAL PATTERN ANALYSIS OF PEOPLE AND GROUPS
Full text linkOgni giorno milioni e milioni di videocamere monitorano la vita quotidiana delle persone, registrando e collezionando una grande quantità di dati. Questi dati possono essere molto utili per scopi di video-sorveglianza: dalla rilevazione di comportamenti anomali all'analisi del traffico urbano nelle strade. Tuttavia i dati collezionati vengono usati raramente, in quanto non è pensabile che un operatore umano riesca a esaminare manualmente e prestare attenzione a una tale quantità di dati simultaneamente.
Per questo motivo, negli ultimi anni si è verificato un incremento della richiesta di strumenti per l'analisi automatica di dati acquisiti da sistemi di video-sorveglianza in modo da estrarre informazione di più alto livello (per esempio, John, Sam e Anne stanno camminando in gruppo al parco giochi vicino alla stazione) a partire dai dati a disposizione che sono solitamente a basso livello e ridondati (per esempio, una sequenza di immagini). L'obiettivo principale di questa tesi è quello di proporre soluzioni e algoritmi automatici che permettono di estrarre informazione ad alto livello da una zona di interesse che viene monitorata da telecamere. Così i dati sono rappresentati in modo da essere facilmente interpretabili e analizzabili da qualsiasi persona. In particolare, questo lavoro è focalizzato sull'analisi di persone e i loro comportamenti sociali collettivi.
Il titolo della tesi, beyond multi-target tracking, evidenzia lo scopo del lavoro: tutti i metodi proposti in questa tesi che si andranno ad analizzare hanno come comune denominatore il target tracking. Inoltre andremo oltre le tecniche standard per arrivare a una rappresentazione del dato a più alto livello. Per prima cosa, analizzeremo il problema del target tracking in quanto è alle basi di questo lavoro. In pratica, target tracking significa stimare la posizione di ogni oggetto di interesse in un immagine e la sua traiettoria nel tempo. Analizzeremo il problema da due prospettive complementari: 1) il punto di vista ingegneristico, dove l'obiettivo è quello di creare algoritmi che ottengono i risultati migliori per il problema in esame. 2) Il punto di vista della neuroscienza: motivati dalle teorie che cercano di spiegare il funzionamento del sistema percettivo umano, proporremo in modello attenzionale per tracking e il riconoscimento di oggetti e persone.
Il secondo problema che andremo a esplorare sarà l'estensione del tracking alla situazione dove più telecamere sono disponibili. L'obiettivo è quello di mantenere un identificatore univoco per ogni persona nell'intera rete di telecamere. In altre parole, si vuole riconoscere gli individui che vengono monitorati in posizioni e telecamere diverse considerando un database di candidati. Tale problema è chiamato in letteratura re-indetificazione di persone. In questa tesi, proporremo un modello standard di come affrontare il problema. In questo modello, presenteremo dei nuovi descrittori di aspetto degli individui, in quanto giocano un ruolo importante allo scopo di ottenere i risultati migliori.
Infine raggiungeremo il livello più alto di rappresentazione dei dati che viene affrontato in questa tesi, che è l'analisi di interazioni sociali tra persone. In particolare, ci focalizzeremo in un tipo specifico di interazione: il raggruppamento di persone. Proporremo dei metodi di visione computazionale che sfruttano nozioni di psicologia sociale per rilevare gruppi di persone. Inoltre, analizzeremo due modelli probabilistici che affrontano il problema di tracking (congiunto) di gruppi e individui.Every day millions and millions of surveillance cameras monitor the world, recording and collecting huge amount of data. The collected data can be extremely useful: from the behavior analysis to prevent unpleasant events, to the analysis of the traffic. However, these valuable data is seldom used, because of the amount of information that the human operator has to manually attend and examine. It would be like looking for a needle in the haystack.
The automatic analysis of data is becoming mandatory for extracting summarized high-level information (e.g., John, Sam and Anne are walking together in group at the playground near the station) from the available redundant low-level data (e.g., an image sequence).
The main goal of this thesis is to propose solutions and automatic algorithms that perform high-level analysis of a camera-monitored environment. In this way, the data are summarized in a high-level representation for a better understanding.
In particular, this work is focused on the analysis of moving people and their collective behaviors.
The title of the thesis, beyond multi-target tracking, mirrors the purpose of the work: we will propose methods that have the target tracking as common denominator, and go beyond the standard techniques in order to provide a high-level description of the data.
First, we investigate the target tracking problem as it is the basis of all the next work. Target tracking estimates the position of each target in the image and its trajectory over time. We analyze the problem from two complementary perspectives: 1) the engineering point of view, where we deal with problem in order to obtain the best results in terms of accuracy and performance. 2) The neuroscience point of view, where we propose an attentional model for tracking and recognition of objects and people, motivated by theories of the human perceptual system.
Second, target tracking is extended to the camera network case, where the goal is to keep a unique identifier for each person in the whole network, i.e., to perform person re-identification. The goal is to recognize individuals in diverse locations over different non-overlapping camera views or also the same camera, considering a large set of candidates.
In this context, we propose a pipeline and appearance-based descriptors that enable us to define in a proper way the problem and to reach the-state-of-the-art results.
Finally, the higher level of description investigated in this thesis is the analysis (discovery and tracking) of social interaction between people. In particular, we focus on finding small groups of people. We introduce methods that embed notions of social psychology into computer vision algorithms. Then, we extend the detection of social interaction over time, proposing novel probabilistic models that deal with (joint) individual-group tracking
Chapter 3 - Group Detection and Tracking Using Sociological Features
No full textThis chapter describes the most common features and definitions from the sociological science used to detect and track groups of people that are interacting. The necessity of having reliable algorithms to cope with these problems is gaining increasing interest, especially in the fields related to security and video surveillance. Answering the question of “who is present and with whom he/she is interacting in a scene?” is nowadays of utmost importance. Other domains require having good algorithms to face these problems, for example, activity recognition, social robotics, and automatic behavior analysis. The success of detection and tracking algorithms relies on the engineering of the features. In this context, the literature of sociological sciences gives us a set of well-established assumptions and constraints to create more reliable and plausible features and detection algorithms. In this chapter we will describe the existing features of the following two categories: the low-level category used to determine the spatial properties of each person in a scene (person position and head/body orientation), and the high-level category that agglomerates or uses the low-level features to implement sociological and biological definitions (frustum of visual attention). We will see how these features are used by the popular methods of group detection, such as game theory-based and probabilistic approaches. Finally, we will analyze a tracking model that can be integrated with the analyzed features and the described detection methods. The experimental part provides a comprehensive comparison of the performances of different algorithms to detect and track groups on standard and publicly available benchmarks
IEdit: Localised Text-guided Image Editing with Weak Supervision
No full textDiffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability on the generated images. We introduce iEdit, a novel method for text-guided image editing conditioned on a source image and textual prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving source image fidelity. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images and descriptive edit prompts. The dataset allows us to incorporate a weakly-supervised loss function, generating the pseudo-target image from the source image's latent noise conditioned on the edit prompt. To encourage localised editing we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Trained with limited GPU resources on the constructed dataset, our model outperforms counterparts in image fidelity, CLIP alignment score, and qualitatively for both generated and real images
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
