Object Duplicate Detection

Péter Vajda
EPFL, 2011
Thèse EPFL

Résumé

With the technological evolution of digital acquisition and storage technologies, millions of images and video sequences are captured every day and shared in online services. One way of exploring this huge volume of images and videos is through searching a particular object depicted in images or videos by making use of object duplicate detection. Therefore, need of research on object duplicate detection is validated by several image and video retrieval applications, such as tag propagation, augmented reality, surveillance, mobile visual search, and television statistic measurement. Object duplicate detection is detecting visually same or very similar object to a query. Input is not restricted to an image, it can be several images from an object or even it can be a video. This dissertation describes the author's contribution to solve problems on object duplicate detection in computer vision. A novel graph-based approach is introduced for 2D and 3D object duplicate detection in still images. Graph model is used to represent the 3D spatial information of the object based on the local features extracted from training images so that an explicit and complex 3D object modeling is avoided. Therefore, improved performance can be achieved in comparison to existing methods in terms of both robustness and computational complexity. Our method is shown to be robust in detecting the same objects even when images containing the objects are taken from very different viewpoints or distances. Furthermore, we apply our object duplicate detection method to video, where the training images are added iteratively to the video sequence in order to compensate for 3D view variations, illumination changes and partial occlusions. Finally, we show several mobile applications for object duplicate detection, such as object recognition based museum guide, money recognition or flower recognition. General object duplicate detection may fail to detection chess figures, however considering context, like chess board position and height of the chess figure, detection can be more accurate. We show that user interaction further improves image retrieval compared to pure content-based methods through a game, called Epitome.

Official source

https://infoscience.epfl.ch/record/167916?ln=fr

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Péter Vajda
EPFL, 2011
Thèse EPFL

Résumé

Official source

https://infoscience.epfl.ch/record/167916?ln=fr

À propos de ce résultat

Concepts associés (19)

Concepts associés

Chargement

Publications associées (12)

Publications associées

Chargement

Object tracking and detection over a wide range of viewpoints is a long-standing problem in Computer Vision. Despite significant advance in wide-baseline sparse interest point matching and development of robust dense feature models, it remains a largely open problem. Moreover, abundance of low cost mobile platforms and novel application areas, such as real-time Augmented Reality, constantly push the performance limits of existing methods. There is a need to modify and adapt these to meet more stringent speed and capacity requirements. In this thesis, we aim to overcome the difficulties due to the multi-view nature of the object detection task. We significantly improve upon existing statistical keypoint matching algorithms to perform fast and robust recognition of image patches independently of object pose. We demonstrate this on various 2D and 3D datasets. The statistical keypoint matching approaches require massive amounts of training data covering a wide range of viewpoints. We have developed a weakly supervised algorithm to greatly simplify their training for 3D objects. We also integrate this algorithm in a 3D tracking-by-detection system to perform real-time Augmented Reality. Finally, we extend the use of a large training set with smooth viewpoint variation to category-level object detection. We introduce a new dataset with continuous pose annotations which we use to train pose estimators for objects of a single category. By using these estimators' output to select pose specific classifiers, our framework can simultaneously localize objects in an image and recover their pose. These decoupled pose estimation and classification steps yield improved detection rates. Overall, we rely on image and video sequences to train classifiers that can either operate independently of the object pose or recover the pose parameters explicitly. We show that in both cases our approaches mitigate the effects of viewpoint changes and improve the recognition performance.

EPFL2010

Chargement

Exploiting Recognition of Natural Visual Stimuli for Brain Computer Interfacing

Marija Uscumlic

Visual search is a good illustration about how the brain coordinates a variety of functions such as visual clues extraction from the scene, coordination of the eye-movements, accumu- lation of visual information and visual recognition. It has an important role in many daily life activities of people – the search of a familiar face in a crowd, a book in the library, or a building in a street. In all these scenarios, it represents a recognition of a specific target object in the presence of predominant task-irrelevant visual information. This thesis specifically addresses the visual search in context of brain-computer interaction (BCI) where the accent is on visually rich stimulation, approaching the real-world BCI applications. Different cognitive aspects of visual processing have been extensively studied using the Rapid Serial Visual Presentation (RSVP) protocol – a sequentially presentation of visual stimuli at the same location on a display. The main part of this thesis deals with the visual search under the RSVP protocol. In such a protocol, the electroencephalogram (EEG) reflects whether a subject recognize an image as a target. Our focus is on extracting and exploiting this informa- tion for the BCI application of image retrieval. We designed a framework for EEG-based image search which involves coupling of the EEG decoder with the computer vision technique for image retrieval. These two components of the system are seen as complementary – bringing in the semantic information and large scale computing, respectively. Our design is founded on an iterative coupling, which relaxes a performance requirement of the individual components. We report the results of the experimental evaluation, where natural color images were used as stimuli. This thesis also includes a comprehensive analysis of the EEG correlates of visual recogni- tion in the EEG-based image search task, addressing the effects of the less controllable stimuli to the EEG potentials’ attributes. To this end, our focus is on the spatio-temporal aspects of the EEG potentials, along with the modulation of the EEG-based cortical connectivity estimates. Finally, this thesis presents an exploratory research on active visual search in the context of BCI. An essential part of active searching of the visual scene represents eye movements. Hence, this type of task better reflects our natural behavior and as such extends the possibilities of BCI applications. We designed two experimental protocols to study the active visual search – guided and free-view visual search. We report the results of the combined study of eye tracking data and simultaneously recorded EEG.

EPFL2013

Chargement

Recent advances in Computer Vision are changing our way of living and enabling new applications for both leisure and professional use. Regrettably, in many industrial domains the spread of state-of-the-art technologies is made challenging by the abundance of nuisances that corrupt existing techniques beyond the required dependability. This is especially true for object localization and tracking, that is, the problem of detecting the presence of objects on images and videos and estimating their pose. This is a critical task for applications such as Augmented Reality (AR), robotic autonomous navigation, robotic object grasping, or production quality control; unfortunately, the reliability of existing techniques is harmed by visual features such as the abundance of specular and poorly textured objects, cluttered scenes, or artificial and in-homogeneous lighting. In this thesis, we propose two methods for robustly estimating the pose of a rigid object under the challenging conditions typical of industrial environments. Both methods rely on monocular images to handle metallic environments, on which depth cameras would fail; both are conceived with a limited computational and memory footprint, so that they are suitable for real-time applications such as AR. We test our methods on datasets issued from real user case scenarios, exhibiting challenging conditions. The first method is based on a global image alignment framework and a robust dense descriptor. Its global approach makes it robust in presence of local artifacts such as specularities appearing on metallic objects, ambiguous patterns like screws or wires, and poorly textured objects. Employing a global approach avoids the need of reliably detecting and matching local features across images, that become ill-conditioned tasks in the considered environments; on the other hand, current methods based on dense image alignment usually rely on luminous intensities for comparing the pixels, which is not robust in presence of challenging illumination artifacts. We show how the use of a dense descriptor computed as a non-linear function of luminous intensities, that we refer to as ``Descriptor Fields'', greatly enhances performances at a minimal computational overhead. Their low computational complexity and their ease of implementation make Descriptor Fields suitable for replacing intensities in a wide number of state-of-the-art techniques based on dense image alignment. Relying on a global approach is appropriate for overcoming local artifacts, but it can be un-effective when the target object undergoes extreme occlusions in cluttered environments. For this reason, we propose a second approach based on the detection of discriminative object parts. At the core of our approach is a novel representation for the 3D pose of the parts, that allows us to predict the 3D pose of the object even when only a single part is visible; when several parts are visible, we can easily combine them to compute a better pose of the object. The 3D pose we obtain is usually very accurate, even when only few parts are visible. We show how to use this representation in a robust 3D tracking framework. In addition to extensive comparisons with the state-of-the-art, we demonstrate our method on a practical Augmented Reality application for maintenance assistance in the ATLAS particle detector at CERN.

EPFL2016

Chargement

Exploiting Recognition of Natural Visual Stimuli for Brain Computer Interfacing

Marija Uscumlic

EPFL2013

EPFL2016