The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this work we address the problem of 3D shape based object class recognition directly from point cloud data obtained from RGB-D cameras like the Kinect sensor from Microsoft. A novel shape descriptor is presented, capable of classifying 'never before seen objects' at their first occurrence in a single view in a fast and robust manner. The classification task is stated as a matching problem, finding...
Person independent and pose invariant facial emotion classification is important for situation analysis and for automated video annotation. Shape and its changes are advantageous for these purposes. We estimated the potentials of shape measurements from the raw 2D shape data of the CK+ database. We used a simple Procrustes transformation and applied the multi-class SVM leave-one-out method. We found...
Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies, such as consumer-level range sensors, new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper, we introduce a novel, large dataset containing 18 categories of objects found in typical...
In this paper we present the UMB-DB 3D face database. The database has been built to test algorithms and systems for 3D face analysis in uncontrolled and challenging scenarios, in particular in those cases where faces are occluded. The database is composed of 1473 pairs of depth and color images of 143 subjects. Each subject has been acquired with different facial expressions, and with the face partially...
In this paper, we focus on discrete expression classification using dynamic 3D sequences (4D data) recording the facial movements. A robust approach for registering 4D data is proposed and a variant of local binary patterns on three orthogonal planes is used for feature extraction. We present a fully automatic facial expression recognition pipeline. The system was evaluated on the publicly available...
Subjective quality evaluation is the basis of quality evaluation of stereoscopic images. As the lack of a public and diverse testing database currently, in this paper, a symmetric stereoscopic images database is built. And then the subjective quality of stereoscopic images is analyzed from two aspects, one is the effects of JPEG, JPEG2000, H.264. The other is the comparisons between symmetric and...
Once the human vision system has seen a 3D object from a few different viewpoints, depending on the nature of the object, it can generally recognize that object from new arbitrary viewpoints. This useful interpolative skill relies on the highly complex pattern matching systems in the human brain, but the general idea can be applied to a computer vision recognition system using comparatively simple...
The biggest problem in transforming C/S MMOGs (Massively Multiplayer Online Games) into web games is how to load the game resources fluently without waiting for downloading during game time. Thus we propose following methods: 1) Reduce the response time of game resource server by using a shared memory database to buffer and manage the game resources; 2) Improve game resource download speed by cutting...
Virtual dressing rooms for the fashion industry and digital entertainment applications aim at creating an image or a video of a user in which he or she wears diffeerent garments than in the real world. Such images can be displayed, for example, in a magic mirror shopping application or in games and movies. Current solutions involve the error-prone task of body pose tracking. We suggest an approach...
Visualization of massively large datasets presents two significant problems. First, the dataset must be prepared for visualization, and traditional dataset manipulation methods fail due to lack of temporary storage or memory. The second problem is the presentation of the data in the visual media, particularly real-time visualization of streaming time series data. An ongoing research project addresses...
This paper presents a novel system for analyzing temporal changes in bloggers' activities and interests on a topic through a 3D visualization of dependency structures related to the topic. Having a dependency database built from a blog archive, our 3D visualization framework helps users to interactively exploring temporal changes in bloggers' activities and interests related to the topic.
In Museum, many testimonies of our cultural heritage can be found. But because of their high fragility, the public can not get too close to them. In this communication we will explain a project that deals with a physical mock-up of Nantes harbor; the mock-up has been built in 1899 and shown in 1900 for the World's Fair that took place in Paris, France. This heritage object is nowadays at the "Chateau...
We describe an augmented reality prototype for exploring a 3D urban environment on mobile devices. Our system utilizes the location and orientation sensors on the mobile platform as well as computer vision techniques to register the live view of the device with the 3D urban data. In particular, the system recognizes the buildings in the live video, tracks the camera pose, and augments the video with...
Self-localization in large environments is a vital task for accurately registered information visualization in outdoor Augmented Reality (AR) applications. In this work, we present a system for self-localization on mobile phones using a GPS prior and an online-generated panoramic view of the user's environment. The approach is suitable for executing entirely on current generation mobile devices, such...
We present a scale-invariant face detection approach based on boosted cascade classifiers using range images as input. The detector was developed to be employed as a preliminary stage for any real-time 3D face recognition system. The required computation time for this task was considerably reduced by eliminating the need for scanning an input image in multiple scales. Our experiments were performed...
Virtual dressing rooms for the fashion industry and digital entertainment applications aim at creating an image or a video of a user in which he or she wears different garments than in the real world. Such images can be displayed, for example, in a magic mirror shopping application or in games and movies. Current solutions involve the error-prone task of body pose tracking. We suggest an approach...
Self-localization in large environments is a vital task for accurately registered information visualization in outdoor Augmented Reality (AR) applications. In this work, we present a system for self-localization on mobile phones using a GPS prior and an online-generated panoramic view of the user's environment. The approach is suitable for executing entirely on current generation mobile devices, such...
Computer-based Multimedia instructional systems are ideal for e-learning in many domains. For applications such as sport instruction, the central issue is to capture motions accurately and correctly for further processing. Many gesture capturing techniques, including light, video and motion tracking, are employed in commercial products, research systems, and the game industry. A tennis e-learning...
In this work we present a new method for compacting data from 3D shapes by extracting a 3D characteristic curve that we call a 3D signature. The 3D signature obtained preserves almost all the morphological shape information but drastically reduces the number of points required for representing the shape. Furthermore, based on the 3D signature, we present a 2D signature that draws a closed contour...
In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. In a first stage, Hidden Markov Models of eleven different styles of gait are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.