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.
Depth camera has gained much more attention in applications of human computer interactivity. In this paper, we present an approach to tracking 3D human pose by constructing/estimating an articulated upper body joint model from depth data captured by Kinect camera. The system first calibrates the human pose parameters by processing the depth data of an initial pose. After that, the dynamic programming...
This work presents a robust method for realtime segmentation and tracking of moving objects using depth image sequences, which is insensitive to illumination changes. We propose a novel criterion in our quadtree split-and-merge framework and effectively solves the problem of segmenting objects in complex and cluttered scenes. We also introduce a plane estimation algorithm to cope with the indistinction...
In the human body tracking based on video sequences, the pose estimation of the upper/lower limbs is the most challenging task since the limbs possess most variations of motions and are easily occluded. In this work, we present a sophisticated scheme to track the human limbs. First, the tracking is formulated as a constrained optimization problem with multiple kernels. The color features of the upper/lower...
This paper presents a non-intrusive vision based system for eye blinks detection and fatigue level monitoring. It uses a web camera positioned in front of the face. A cascade of boosted classifiers based on Haar-like features is used for fast detection of the eyes region. The frames differencing in combination with the thresholding are applied to detect the eyes closure and opening. The frame processing...
This research presents a 3-D human arms tracking method with a monocular camera. In our previous work, multiple clues have been integrated by the multiple importance sampling particle filter to track the arms with arbitrary motion on the images. Due to the lack of depth information when using a monocular camera, an online sequential pose estimation based on the structure-from-motion is proposed here...
Virtual maps technology is one of many innovations of the past decade. Currently navigation with such maps is generally performed using keyboard and mouse inputs. For improved human social communication, there is a need for more effective and unobtrusive navigation methods. In this paper, we adopt a human-centric approach to reinvent the way in which users interact with virtual maps. The proposed...
In this paper, we develop face and hand activity detection for motion recognition system. In initial stage, a skin color segmentation method for the color image with complex background is presented, which is a mixed skin color segmentation model in both HSI and YCbCr color space constructed. After skin color segmentation, improved face feature extraction method is proposed. Then the improved CAMSHIFT...
When creating a ubiquitous service environment for humans, it is very important to be able to determine their location and movement. In this paper, we propose an algorithm that simultaneously estimates the number of humans and the movement locus for each human in a room, using only the binary sensing data obtained from infrared sensors attached to the ceiling. Compared to other camera-based systems,...
In this paper, we present a new approach dealing with mobile object tracking in a video sequence using primitive geometric forms in real time. Our system aims to reduce execution time while searching for correspondent region, by considering some strategical neighbors (in addition to the current position) to find the object of interest, while readapting search region's size to handle false detections.
Reliable and unobtrusive eye tracking remains a technical challenge for immersive virtual environment, especially when Head Mounted Displays (HMD) are used for visualization and users are allowed to move freely in the environment. In this work, we provide experimental evidence that gaze direction can be safely approximated by user head rotation, in HMD-based Virtual Reality (VR) applications, where...
Video summarization, which has a tremendous usage area that spreads from information retrieval to data compression, plays a crucial role in the multimedia understanding. In recent years, with the explosion of the number of videos and their area of use, video summarization became a must to signify. Therefore, this work introduces a novel approach for the summarization problem which is based on human...
This paper proposes an activity-specific 3D human pose tracking system from multiple camera views. Dimensionality reduction is used to represent a single activity in a hierarchy of low dimensional spaces. This hierarchy provides increasing independence between limbs by decoupling them, allowing higher flexibility and adaptability that result in improved accuracy. For every subspace, a deterministic...
Recently, fusion of low- and high-dimensional approaches shows its success in the generic human motion tracking. However, how to choose the trackers adaptively according to the motion types is still a challenging problem. This paper presents a trackers sampling approach for generic human motion tracking using both low- and high-dimensional trackers. Gaussian Process Dynamical Model(GPDM) is trained...
We propose a parallelized Annealed Particle Filter method via heterogeneous computing (P-APF), to implement real-time marker-less motion tracking based on OpenCL framework. The overall computing procedure in P-APF is decomposed into several computational tasks with corresponding granularity. According to the degree of parallelism, the tasks are assigned to standard and attached processors respectively,...
Networked robotic applications enable robots to operate in distant, hazardous, or otherwise inaccessible environments, such as search and rescue, surveillance, and exploration applications. The most difficult challenge which persists for such systems is that of supporting effective human-robot interaction, as this usually demands managing dynamic views, changeable interaction modalities, and adaptive...
Effective perimeter protection mechanisms for industrial sites and critical infrastructure must contend with a large variety of potential threats as well as with the fact that normal site activity can be both complex and diverse. This paper documents the development of a system level approach capable of functioning under such challenging conditions. A multi-view tracking system is used to provide...
This paper describes a tracking control system of human motion with Kinect on-board a mobile robot. In the proposed system, the 3D position information of human obtained from Kinect enables us to control the velocity and attitude of the mobile robot directly. Meanwhile, there are noises and occlusion effect on the information of Kinect, the Kalman filter is used to reduce the noise and estimate human's...
Flock Logic is an art and engineering project that explores how the feedback laws used to model flocking translate when applied by a group of dancers. The artistic goal is to create tools for choreography by leveraging dynamics of multiagent systems with designed feedback and interaction. The engineering goal is to develop insights and design principles for multi-agent systems, such as human crowds,...
We examine the use of visual navigation techniques for improving human navigation and localization in GPS-denied environments. While many advances have been made in navigation techniques using stereo and monocular motion estimation, significant hurdles exist for a practical system, including size, weight, power, and cost limitations. Humans often move and rotate faster and with more complex motions...
A novel framework for unsupervised multi-faces tracking and recognition is built on Detection-Tracking-Recognition (DTR) approach. This framework proposed a hybrid face detector for real-time face tracking which is robust to occlusions and posture changes. Faces acquired during unsupervised detection stage will be further processed by SIFT operator in order to cluster face sequence into certain groups...
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.