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.
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,...
Conventional human detection is mostly done in images taken by visible-light cameras. These methods imitate the detection process that human use. They use features based on gradients, such as histograms of oriented gradients (HOG), or extract interest points in the image, such as scale-invariant feature transform (SIFT), etc. In this paper, we present a novel human detection method using depth information...
In this study we want to address the question to what extent the visual and the haptic modalities contribute to the final formation of a complex multisensory perceptual space. By varying three shape parameters a physical shape space of shell-like objects was generated. Participants were allowed to either see or touch the objects or use both senses to explore the objects. Similarity ratings were performed...
In this paper an algorithmic framework for posture analysis using a single view 3D TOF camera is presented. The 3D human posture parameters are recovered automatically from range data without the usage of body markers. A topological approach is investigated in order to define descriptors suitable to estimate location of body parts and orientation of body articulations. Two Morse function are exploited,...
Salient features help identify objects. However, they can also influence subsequent comparison between objects. In this study, we investigate the influence of edges on perception of the shape of 3D objects. We tested two conditions in which subjects were asked to indicate the orientation of a block by exploring it either statically without touching the edges or freely. When edges were excluded, the...
The main objective of this paper is to design and develop a novel hybrid human motion tracking system for gait and dynamic balance training program based on virtual reality games for children with motor impairments. The whole training program comprises of a novel human motion tracking system and a VR game system that enables objective monitoring of a child's progress, improves consistency between...
An embedded 3D body motion capture system for an assistive walking robot is presented in this paper. A 3D camera and infrared sensors are installed on a wheeled walker. We compare the positions of the human articular joints computed with our embedded system and the ones obtained with an other accurate system using embodied markers, the Codamotion. The obtained results valid our approach.
This paper introduces a novel link-driven, 1 DOF, three phalanges robotic finger. In order to improve the grasping performance of BHG-1 hand which is driven by tendon system, a link-driven finger is proposed. First, the design requirements of new finger are given on the basis of the new grasping scheme of BHG-1 hand. Then, the analysis and optimization design procedure of the linkage for the robotic...
Human Motion Capture (HMC) is an active topic of research with applications in diverse domains. The robotics community is in particular interested in methods which allow the tracking of human movements on autonomous robotic systems with their constrained perception and processing capabilities. One approach for such a tracking is based on the Iterative Closest Points (ICP) algorithm. A specific problem...
Many innovative ideas in robotics have been inspired by neuroscience and, in particular, by the investigation of how intelligence and perception work. In this paper we explore an approach for semantic robot grasping, which combines programming by demonstration, automatic 3D shape segmentation and manipulation planning by parts. Neuro-psychology studies have evidenced the influence of shape decomposition...
In many scenarios, domestic robot will regularly encounter unknown objects. In such cases, top-down knowledge about the object for detection, recognition, and classification cannot be used. To learn about the object, or to be able to grasp it, bottom-up object segmentation is an important competence for the robot. Also when there is top-down knowledge, prior segmentation of the object can improve...
The ability of a perception system to discern what is important in a scene and what is not is an invaluable asset, with multiple applications in object recognition, people detection and SLAM, among others. In this paper, we aim to analyze all sensory data available to separate a scene into a few physically meaningful parts, which we term structure, while discarding background clutter. In particular,...
This article introduces a method called SLAC (Simultaneous Localization And Capture) to track the spatial location of a human using wearable inertia sensors without additional external assistive global sensing device (e.g., camera, ultrasound, IR, etc.) The method uses multiple wearable inertia sensors to determine the orientation of the body segments and lower limb joint motions. At the same time,...
People detection and tracking is a key component for robots and autonomous vehicles in human environments. While prior work mainly employed image or 2D range data for this task, in this paper, we address the problem using 3D range data. In our approach, a top-down classifier selects hypotheses from a bottom-up detector, both based on sets of boosted features. The bottom-up detector learns a layered...
The procedure of manually generating a 3D model of an object is very time consuming for a human operator. Next-best- view (NBV) planning is an important aspect for automation of this procedure in a robotic environment. We propose a surface-based NBV approach, which creates a triangle surface from a real-time data stream and determines viewpoints similar to human intuition. Thereby, the boundaries...
Recently, laser-based people-tracking systems have received increasing attention for their ability to localize human subjects precisely in crowded situations. However, in a real environment, there exist many kinds of moving objects other than people, and previous methods have focused only on humans. To design a more sophisticated system, it is necessary to distinguish humans from observed objects...
The outdoor perception problem is a major challenge for driver-assistance and autonomous vehicle systems. While these systems can often employ active sensors such as sonar, radar, and lidar to perceive their surroundings, the state of standard traffic lights can only be perceived visually. By using a prior map, a perception system can anticipate and predict the locations of traffic lights and improve...
We propose a natural 3D scene generation method using a TOF camera and real light information. We can generate 3D human actor by capturing a depth and color image of human actor using a TOF camera which uses the IR sensor. But the acquisition is processed in an indoor environment due to the time and space constraints of capturing environments. In practice, a composition using a 3D human actor with...
We propose a novel 2D to 3D scheme by considering perceived 3D experience caused by occlusion and visual attention. In this scheme, initial depth model, the saliency map of visual attention and occlusion analysis are integrated in depth calculation. Mean-while, characteristics of human visual system are also considered as weight factors. Then, depth normalization and refining are implemented. 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.