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.
Camera pose estimation is a fundamental problem of Augmented Reality and 3D reconstruction systems. Recently, despite the new better performing direct methods being developed, state-of-the-art methods are still estimating erroneous poses due to sensor noise, environmental conditions and challenging trajectories. Adding a back-end mapping process, SLAM systems achieve better performance and are more...
We present a novel approach to 6DOF pose estimation and segmentation of rigid 3D objects using a single monocular RGB camera based on temporally consistent, local color histograms. We show that this approach outperforms previous methods in cases of cluttered backgrounds, heterogenous objects, and occlusions. The proposed histograms can be used as statistical object descriptors within a template matching...
This paper describes the design and implementation of a multiple view stereoscopic 3D vision system and a supporting infant tracker pipeline to track limb movement in natural play environments and identify potential metrics to quantify movement behavior. So far, human pose estimation and tracking with 3D cameras has been focused primarily on adults and cannot be directly extended to infants because...
3D reconstruction of human faces is of high importance in applications like forensics, facial features based human tracking and realistic reconstruction of human faces in virtual reality applications. The published algorithms so far require either a large number of views of a human face or a 3D facial reference model. This paper proposes a technique for 3D human face reconstruction using only five...
This paper presents a method for extracting a non-rigid moving object from a video sequence. In order to actualize object extraction with minimal user interaction, we combine alpha matting and seed-line tracking. In the proposed method, the object region is separated from background based on seed lines given by user as a cue, and then the seed lines are automatically tracked to the next frames to...
This paper presents an evaluation of the Tango tablet regarding its motion tracking and depth perception capabilities. A methodology for performing such kind of evaluation is proposed. Motion tracking error is assessed in both small workspace and large environments. In the small workspace scenario, the distances reported by the motion tracking system are compared with values measured with the aid...
In this paper, we design and implement an effective framework for interaction simulation based on real shadows and virtual shadows. Within the specified depth range, we firstly identify different physical objects with the method of HSV. And then in order to get the position of interaction tool, we use central moment to find the centroid of the physical object. In addition, the gesture recognition...
In recent years, many systems for motion analysis of infants have been developed which either use markers or lack 3D information. We propose a system that can be trained fast and flexibly to fit the requirements of markerless 3D movement analysis of infants. Random Ferns are used as an efficient and robust alternative to Random Forests to find the 3D positions of body joints in single depth images...
While the problem of tracking 3D human motion has been widely studied, the top view is never taken into consideration. However, for the video surveillance, the camera is most of the time placed above the persons. This is due to the human shape is more discriminative in the front view. We propose in this paper a markerless 3D human tracking on the top view. To do this we use the depth and color image...
This paper proposes a marker-free motion capture system to track articulated human motion using a new sum-of-Gaussian particle filter (SOG-PF) algorithm. The proposed motion capture system records multi-view color image sequences of human motion with synchronized multiple cameras. Then, the new SOG-PF algorithm that effectively combines 3D and 2D SOG models with a particle filter algorithm is adopted...
An important aspect of collision avoidance and driver assistance systems, as well as autonomous vehicles, is the tracking of vehicle taillights and the detection of alert signals (turns and brakes). In this paper, we present the design and implementation of a robust and computationally lightweight algorithm for a real-time vision system, capable of detecting and tracking vehicle taillights, recognizing...
This paper proposes a low-complexity design for 3D hand tracking, which can provide depth information and is able to work under critical backgrounds. This paper also proposes an effective way to segment hands out of entire image and also facilitates depth estimation of tracked hands in real-time by dualcamera systems. Multithreading and several techniques are applied to reduce computational complexity...
Hand tracking is a common task in a gesture recognition system. Many techniques have been introduced to make successful hand tracking. In hand tracking system, most of previous works tracked the hand position using attached marker on hands. Several researchers have used a color image for skin color detection. However, using marker based need to attach marker on hands or wear gloves to make hand can...
We present RGB-D Fusion, a framework which robustly tracks and reconstructs dense textured surfaces of scenes and objects by integrating both color and depth images streamed from a RGB-D sensor into a global colored volume in real-time. To handle failure of the ICP-based tracking approach, KinectFusion, due to the lack of sufficient geometric information, we propose a novel approach which registers...
In this paper, we introduce a new method for background subtraction for freely moving cameras and arbitrary scene geometry. Instead of relying on frame-to-frame estimation, we simultaneously estimate the epipolar geometries induced by a moving camera in a temporally consistent manner for a number of frames using the temporal fundamental matrix (TFM). The TFM is robustly estimated from the track lets...
This paper focuses on the issue of estimating the complete 3D pose of the camera with respect to a complex object, in a potentially highly dynamic scene, through modelbased tracking. We propose to robustly combine complementary geometrical edge and point features with color based features in the minimization process. A Kalman filtering and pose prediction process is also suggested to handle potential...
In this paper, we introduce a system to capture the enhanced 3D structure of a room-sized dynamic scene with commodity depth cameras such as Microsoft Kinects. It is challenging to capture the entire dynamic room. First, the raw data from depth cameras are noisy due to the conflicts of the room's large volume and cameras' limited optimal working distance. Second, the severe occlusions between objects...
In this paper, we present a system to acquire 3D vision by motion parallax on web-based platforms using head tracking. We employ the camshift algorithm to perform color-based head tracking. Using the position of the head, we can render a 3D scene from the viewpoint of the viewer, thus acquiring motion parallax, a strong cue for 3D vision. We employed web technologies to allow the adoption of our method...
Tracking human pose is attractive to many applications such as Human Robot Interface (HRI), motion capture system, video surveillance, action recognition, etc. Though various methods were introduced during last decades, including both color and depth camera based, it is still considered that feature sets for them are not discriminative enough. In this paper, we propose a human pose tracking method...
In this paper, the key technologies of human motion reconstruction Based on multi-view video are discussed. A more robust motion reconstruction method with markers is presented, which includes camera calibration, markers extraction, markers tracking and 3D reconstruction. In the procedure of markers tracking, we propose a novel multi-view tracking algorithm. This algorithm is made up of two steps,...
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.