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.
We present an approach to add true fine-scale spatio-temporal shape detail to dynamic scene geometry captured from multi-view video footage. Our approach exploits shading information to recover the millimeter-scale surface structure, but in contrast to related approaches succeeds under general unconstrained lighting conditions. Our method starts off from a set of multi-view video frames and an initial...
Hand tracking is a fundamental task in a gesture recognition system. Most previous works tracked the hand position on color images and relied heavily on skin color information. However, color information is very vulnerable to lighting variations and skin color varies across difference human races. Furthermore, one can not effectively discriminate faces or other skin-color-like objects from hands when...
This paper presents a novel method for generating multi-view video. The video can be viewed without wearing a pair of glasses which is more suitable for outdoor bulletin board of kiosk applications. One of the major aspects of the new method is that the depth estimation is not required. Hence, no depth warp induced holes will be introduced. Our method first extracts feature correspondence from a Left/Right...
The development of ultra low power wireless sensors for customized wearable medical devices requires patient specific information for the evaluation of the on-body communication channel. Direct measurements on human subjects are impractical for many applications. In such cases, numerical techniques for electromagnetic analysis, such as Finite Differences in Time Domain (FDTD), is an attractive alternative...
Active vision systems are usually limited to either partial or static scene reconstructions. In this paper, we propose to acquire the entire 3D shape of a dynamic scene. This is performed using a multiple projectors and cameras system, that allows to recover the entire shape of the object within a single scan at each frame. Like previous approaches, a static and simple pattern is used to avoid interferences...
The visual perception of semi-transparent objects, such as drinking glasses, is an open challenging problem. Unlike opaque objects, semi-transparent objects violate many of the standard vision assumptions, among them that figure-ground segmentation contains salient boundaries. More specifically, reliable motion and stereo cues for segmenting semi-transparent objects are not present because of the...
Recent proliferation of a cheap but quality depth sensor, the Microsoft Kinect, has brought the need for a challenging category-level 3D object detection dataset to the fore. We review current 3D datasets and find them lacking in variation of scenes, categories, instances, and viewpoints. Here we present our dataset of color and depth image pairs, gathered in real domestic and office environments...
We propose a method for learning shape models enabling accurate articulated human pose estimation from a single image. Where previous work has typically employed simple geometric models of human limbs e.g. cylinders which lead to rectangular projections, we propose to learn a generative model of limb shape which can capture the wide variation in shape due to varying anatomy and pose. The model is...
This work tackles the problem of recovering the structure of a scene from a single image. The goal is to interpret automatically the image to obtain the spatial layout of the scene. In essence, the method proposed classifies the environment as floor or walls and their relative positions. Instead of using standard cameras for solving this particular task, our work is novel in using omnidirectional...
Accurate initial pose is a kind of crucial information when localizing shape features or recognizing car models in a real-time intelligent transportation system. However, obtaining a sufficiently accurate initial pose is generally difficult because very little prior information is available when the vehicle is first time captured by the camera. This paper proposes an algorithm that can provide a sufficiently...
There are many papers published on the use of 2D images for object representation. The fundamental issue with these approaches lies in the fact that a conventional image maps 3D real world objects into a 2D plane. This causes loss of 3D information - which means loss of 3D features as well for further analysis. There have been attempts using 3D and 2.5D scanners in order to access range data from...
Recovering the 3D surface of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. It has been shown that preventing the surface from either shrinking or stretching is an effective way to resolve the ambiguities inherent to this problem. State-of-the-art solutions to nonrigid 3D shape recovery rely on the fact that distances between adjacent surface points must...
In this paper we propose 3-D object reconstruction algorithm by combining two different algorithms. We review two common methods for 3-D object reconstruction. Visual hull is derived from multiple images and then refine visual hull by stereo matching .Then voxel color is another method that uses the measure of color consistency to build 3-D object reconstruction. Our propose algorithm is based on...
Cerebral aneurysm is a weak spot in a blood vessel that usually enlarges. Nowadays, cerebral aneurysm detection method is still being done manually by visually observing 2D or 3D medical images (CTA). The main purpose of this paper is to design a method of cerebral aneurysm detection and classify different vascular geometry with color indicator. The method developed was based on curvature analysis...
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...
In this paper we introduce a novel real-time method to track weakly textured planar objects and to simultaneously estimate their 3D pose. The basic idea is to adapt the classic tracking-by-detection approach, which seeks for the object to be tracked independently in each frame, for tracking non-textured objects. In order to robustly estimate the 3D pose of such objects in each frame, we have to tackle...
With the increasing volumes of digital image data and the rapid development of internet technologies, it becomes vital to efficiently and accurately retrieve inquired images from the vast available data resources. In this context, content-based image retrieval has been intensively researched in the past decades. In this work, we propose to use contrast and luminance distribution, abbreviated as CoLD,...
This paper presents a novel approach that can efficiently synthesize a virtual frontal view, given only a single non-frontal face image. A non-frontal face image is separated into shape and shape-free texture, and Neighbor Embedding (NE) is applied to them respectively. The virtual frontal face can be generated by warping the shape-free texture to the shape and enforcing local compatibility and smoothness...
Bayon, the well-known Khmer temple at Angkor in Cambodia, is famous for its numerous massive stone face towers. Researchers believe that these facial sculptures can be divided into several meaningful categories. Unlike previous studies, in this paper, each face tower is treated as a basic unit in the classification procedure, as we find that faces located on the same tower have a higher similarity...
Purpose of this research is to find correlations between Indonesian Traditional 'Wayang Kulit' Puppet shapes and their roles in the story. However, the information needed to achieve this purpose is not digitally archived yet. Consequently the research to find the way of archiving the regarding information needs to be carried out. The methodology proposed here is using the 3D model to recognize the...
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.