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.
A depth map represents three-dimensional (3D) scene information and is used to synthesize virtual views in 3D video. Since the quality of synthesized virtual views highly depends on the quality of depth map, efficient depth compression is crucial to realize the 3D video system. However compressing depth map using existing video coding techniques yields unacceptable distortions while rendering virtual...
In surveillance videos, cues such as head or body pose provide important information for analyzing people's behavior and interactions. In this paper we propose an approach that jointly estimates body location and body pose in monocular surveillance video. Our approach is based on tracks derived by multi-object tracking. First, body pose classification is conducted using sparse representation technique...
In this study the perception of crowds was investigated in urban environment. The images of crowds were viewed non-stereoscopically and stereoscopically with HMD (head-mounted display). The task of the participants was to count the number of persons in the crowds. The results clearly indicate that stereoscopic viewing enhances perception of crowds. The counting task was determined to be easiest with...
A typical video surveillance system consists of at least one camera, controlled by an operator. To decrease the human error rate and to generally lessen the burden of operators, many object tracking systems have been implemented, most of which work in 2D image space. If used centralized, this is a very expensive task. Furthermore, if several views are to be fused, large inaccuracies arise due to ground...
The work presented in this paper addresses a practical approach to the problem of 3D pose estimation. The proposed method extends a classical 2D dead reckoning system to a 3D pose estimation system by merging data from odometry and multiple low cost rate gyros and accelerometers. The localization problem is decomposed into two parts, i.e. attitude estimation followed by pose estimation. Based on the...
In this paper, we address the recovering from monocular images focusing on designing a novel image descriptor derived from the second generation Bandelet transformation, noted as Bandelet2, to tackle with estimation accuracy combined with state-of-art prediction methods. The proposed Bandelet2 image representation could boost the accuracy for the final 3D pose prediction in monocular video images...
In this paper, we explore the combined use of inertial sensors and the Kinect for applications on rehabilitation robotics and assistive devices. In view of the deficiencies of each individual system, a new method based on Kalman filtering was developed in order to perform online calibration of sensor errors automatically whenever measurements from Kinect are available. The method was evaluated on...
For radiotherapy planning, contouring of target volume and healthy structures at risk in CT volumes is essential. To automate this process, one of the available segmentation techniques can be used for many thoracic organs except the esophagus, which is very hard to segment due to low contrast. In this work we propose to initialize our previously introduced model based 3D level set esophagus segmentation...
The occlusion between real and virtual objects influences not only seamless merging of virtual and real environments but also users' visual perception of orientations & locations and spatial interactions in augmented reality. If there exist a large amount of video sequences for representing the real environment, and each video sequence utilizes computer vision algorithms to deal with all of occlusions...
In this paper, the problem of retrieving the three-dimensional reconstruction of the ground scene observed by a Synthetic Aperture Radar System is addressed. To obtain such result, Multi-Pass systems are considered jointly with two recently proposed estimation techniques: the Compressive Sensing and the SAR Statistical Tomography.
Geometrical features are widely used in the SAR ship recognition. Two-dimensional (2D) features are sometimes ambiguous and the three-dimensional (3D) ones are hence preferred. Most of the existing researches are based on the 3D coordinate estimation of the scattering centers. These techniques may lose efficiency when working with ocean ships, due to their complicated motion on the waves and the scattering...
On the 12th of January 2010, Haiti was struck by a M7.0 earthquake; the hypocenter (18.443°N, 72.571°W, Depth 13 km) was located very close to the capital Port-au-Prince, causing considerable damage to buildings and infrastructure in the city and its conurbation and a high number of human fatalities. For evaluation of the co-seismic surface shift caused by this earthquake, especially at the Enriquillo-Plantain...
The interest for advanced methods of full 3D SAR imaging of volumetric forest scatterers is rapidly increasing. In particular, multibaseline SAR tomographic elevation beamforming i.e. spatial spectral estimation is a promising technique. Recently, this concept has been integrated with the differential interferometry concept, producing the new differential tomography mode which yields ‘space-time’...
The typical local stereo matching for disparity estimation can deliver accurate disparity maps by a well-designed cost aggregation method, but usually suffers from natively high computational complexity due to its dense processing. To address it, we propose a fast algorithm with search point reduction on spatial and disparity domains to generate a sparse search map. The sparse search map guides the...
In this paper, a human detection and tracking system in a crowded environment is presented. The biggest challenge of the system is to detect occluded people from the captured video where visible information of the occluded people in a camera is reduced. Many researchers proposed to reconstruct the occluded information from other cameras which are installed in the same place with different viewing...
In this paper, we present a real time biologically motivated 3D motion classifier cells integrating the depth information generated from a stereo input implemented in an active vision system. The proposed approach is accurately able to detect and estimate multiple interfered 3D complex motions under the absence of predefined spatial coherence. Moreover, the system has ability to examine the response...
We evaluate the robustness of five regression techniques for monocular 3D pose estimation. While most of the discriminative pose estimation methods focus on overcoming the fundamental problem of insufficient training data, we are interested in characterizing performance improvement for increasingly large training sets. Commercially available rendering software allows us to efficiently generate large...
This paper presents a model-based hierarchical particle filtering algorithm to estimate the pose and anthropometric parameters of humans in multi-view environments. Our method incorporates a novel likelihood measurement approach consisting of an approximate partitioning of observations. Provided that a partitioning of the human body model has been defined and associates body parts to state space variables,...
Dead-reckoning navigation in the deep sea is subject to errors due to accumulation of sensor inaccuracies. As no global referencing method exists for the deep sea like, e.g., GNSS (global navigation satellite system) for land or airborne vehicles other referencing solutions need to be employed. SLAM (Simultaneous Localization And Mapping) is a technique that exploits significant environmental features...
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.