Filters








324 Hits in 5.8 sec

A New Profile Shape Matching Stereovision Algorithm for Real-time Human Pose and Hand Gesture Recognition

Dong Zhang, Dah-Jye Lee, Yung-Ping Chang
2014 International Journal of Advanced Robotic Systems  
This paper presents a new profile shape matching stereovision algorithm that is designed to extract 3D information in real time.  ...  To demonstrate its performance, the proposed algorithm is tested for human pose and hand gesture recognition to control a smart phone and an entertainment system.  ...  The essential part of body structure analysis is pose estimation, which can be split into model-based and model-free, depending upon whether a priori information about the object shape is provided.  ... 
doi:10.5772/57515 fatcat:ngjrsdoyrbhblbhbh5hsw6sa2u

Person following and mobile robot via arm-posture driving using color and stereovision

Bogdan K Wolek
2003 IFAC Proceedings Volumes  
Color image processing and labeling techniques are used to detect candidates of face, hands and shirt.  ...  Using heuristics for the size and spatial relations we can locate the tracked person as well as the person's face and hands.  ...  Fig. 2 . 2 Geometrical model of arm-postures and respectively on the right side of the head.  ... 
doi:10.1016/s1474-6670(17)33389-x fatcat:sd22ja5rvfgdxap2vc2docu34a

Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score

Jean-Philippe Pons, Renaud Keriven, Olivier Faugeras
2006 International Journal of Computer Vision  
We present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences.  ...  Our stereovision algorithm yields very good results on a variety of datasets including specularities and translucency.  ...  Kyros Kutulakos for providing us with the "Cactus" and "Gargoyle" datasets, and Dr. Jan Neumann for his support on the "Yiannis" dataset.  ... 
doi:10.1007/s11263-006-8671-5 fatcat:dojtygyk4zb5vb6tvajqg4m62y

A Real-time 3D Pose Based Visual Servoing Implementation for an Autonomous Mobile Robot Manipulator

Jose R. Sanchez-Lopez, Antonio Marin-Hernandez, Elvia R. Palacios-Hernandez, Homero V. Rios-Figueroa, Luis F. Marin-Urias
2013 Procedia Technology - Elsevier  
The methodology proposed consists of three steps: a) beginning with a fast monocular image segmentation, followed by b) 3D model reconstruction and finally c) pose estimation to feedback fine tuning manipulation  ...  Objects and end-effector are colored in different colors and their models are supposed to be known.  ...  The first scheme uses measures in image space to control the robot, while pose-based visual servoing uses real pose estimation to feedback control loop.  ... 
doi:10.1016/j.protcy.2013.04.052 fatcat:rkfetidz3nc5vp4deyj3urbke4

Visual Guided Approach-to-Grasp for Humanoid Robots [chapter]

Yang Shen, De Xu, Min Tan, Ze-Min Jiang
2007 Humanoid Robots, Human-like Machines  
When the structure or the model of the object is prior known, it can be taken to estimate the pose of the object by means of matching.  ...  The Cartesian coordinates of the valve can be obtained with the stereovision algorithm using the pixel coordinates of the image feature.  ...  How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Yang Shen, De Xu, Min Tan and Ze-Min Jiang (2007) .  ... 
doi:10.5772/4817 fatcat:zmgx3bxodnamrovikfqex3ssce

3D Model-based Reconstruction of the Proximal Femur from Low-dose Biplanar X-Ray Images

Haithem Boussaid, Samuel Kadoury, Iasonas Kokkinos, Jean-Yves Lazennec, Guoyan Zheng, Nikos Paragios
2011 Procedings of the British Machine Vision Conference 2011  
The use of computed tomography is the most prominent modality to visualize bones both in terms of resolution as well as in term of bone/tissue separation.  ...  The 3D modeling of the proximal femur is a valuable diagnostic tool for orthopedic surgery planning.  ...  Future work includes analyzing a larger dataset of models and integrating the representation of the prior model using graphical models and the use of global pose-free parameters prior model and objective  ... 
doi:10.5244/c.25.35 dblp:conf/bmvc/BoussaidKKLZP11 fatcat:ifih7elzu5gqllaxkijnimli6a

Fusing Monocular Information in Multicamera SLAM

J. Sola, A. Monin, M. Devy, T. Vidal-Calleja
2008 IEEE Transactions on robotics  
free-moving cameras in an outdoor setting.  ...  This paper explores the possibilities of using monocular simultaneous localization and mapping (SLAM) algorithms in systems with more than one camera.  ...  free-moving cameras in an outdoor setting.  ... 
doi:10.1109/tro.2008.2004640 fatcat:lksdgrk3rbfzbkxcnws3a225du

SYSTEM DESIGN, CALIBRATION AND PERFORMANCE ANALYSIS OF A NOVEL 360° STEREO PANORAMIC MOBILE MAPPING SYSTEM

S. Blaser, S. Nebiker, S. Cavegn
2017 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The result is a very high detailed and almost complete 3D city model of the street environment.  ...  By using two 360° panorama cameras tilted forward and backward in combination with conventional forward and backward looking stereo camera systems, we achieve a full 360° multi-stereo coverage.  ...  The parameters were estimated using bundle adjustment incorporating the previously determined IOP and ROP.  ... 
doi:10.5194/isprs-annals-iv-1-w1-207-2017 fatcat:hamhvhd5knhtxbr5zeg3rf3cpu

Real time UAV altitude, attitude and motion estimation from hybrid stereovision

Damien Eynard, Pascal Vasseur, Cédric Demonceaux, Vincent Frémont
2012 Autonomous Robots  
Rotation and translation are then estimated by decoupling: the fisheye camera contributes to evaluating attitude, while the perspective camera contributes to estimating the scale of the translation.  ...  A plane-sweeping approach is proposed for estimating altitude and detecting the ground plane.  ...  Caron and Eynard (2011) simultaneously estimate the projection parameters and relative poses between N cameras of N models composing the stereo rig.  ... 
doi:10.1007/s10514-012-9285-0 fatcat:i7ugzmes4zcmdnwq4tjvr5gucm

Efficacy of thigh volume ratios assessed via stereovision body imaging as a predictor of visceral adipose tissue measured by magnetic resonance imaging

Jane J. Lee, Jeanne H. Freeland-Graves, M. Reese Pepper, Wurong Yu, Bugao Xu
2015 American Journal of Human Biology  
Objectives-The research examined the efficacy of regional volumes of thigh ratios assessed by stereovision body imaging (SBI) as a predictor of visceral adipose tissue measured by magnetic resonance imaging  ...  Wurong Yu and Bugao Xu developed the three-dimensional stereovision imaging  ...  These prediction equations were based on measurements of body volume and body mass to estimate fat and fat-free mass.  ... 
doi:10.1002/ajhb.22663 pmid:25645428 pmcid:PMC4478126 fatcat:npb2vifsxbggtdqjwnwojmpcnq

Generic Dynamic Environment Perception Using Smart Mobile Devices

Radu Danescu, Razvan Itu, Andra Petrovai
2016 Sensors  
Several driving assistance application are available for mobile devices, but they are mostly targeted for simple scenarios and a limited range of obstacle shapes and poses.  ...  in real time from the smart mobile device's camera are processed by removing the perspective effect and segmenting the resulted bird-eye view image to identify candidate obstacle areas, which are then used  ...  The detection method uses a simple and fast segmentation technique, followed by free-form tracking of the obstacle areas using the particle based occupancy grid.  ... 
doi:10.3390/s16101721 pmid:27763501 pmcid:PMC5087508 fatcat:owfh5ge7sbg3fd5wc4twqbahnm

An approach of visual motion analysis

Alberto Sanfeliu, Juan J. Villanueva
2005 Pattern Recognition Letters  
We explain techniques of motion analysis using single and multiple cues, describing in the last case several cue integration techniques for robust tracking.  ...  By using the information of the previous state about the position on the image and the scale of the head (modelled as an ellipse), the system computes the position of the head in the new image.  ...  The Kalman filter is used for estimating the 3-D position of the object to track (in this case a human face) and colour and stereovision are the cues.  ... 
doi:10.1016/j.patrec.2004.10.024 fatcat:op76o66kfzgdfmlc7d4ofvc2z4

A Feature-Level Fusion of Appearance and Passive Depth Information for Face Recognition [chapter]

Jian-Gang Wang, Kar Ann, Eric Sung, Wei-Yun Yau
2007 Face Recognition  
Head/Face tracking Pose estimation As we are using stereo camera, we can compute the pose from the 3D coordinates of the feature points directly, like that by (Matsumoto & Zelinsky, 2000) .  ...  Using the calibrated parameters of the vision system, the head pose can be estimated using a EM enhanced vanishing point, formed by the eye lines and mouth line, based method (Wang & Sung, 2007) .  ...  They should give the reader a general idea where the current research efforts are heading, both within the face recognition area itself and in interdisciplinary approaches.  ... 
doi:10.5772/4855 fatcat:v3nd5b22mbhx7dlvwk7b67cczu

Vehicle following with obstacle avoidance capabilities in natural environments

Teck Chew Ng, J. Ibanez-Guzman, Jian Shen, Zhiming Gong, Han Wang, Chen Cheng
2004 IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004  
The algorithm estimates the desired heading for the vehicle following by using the MDT, and modifies this heading by using the VFH. The end result eliminates the oscillation phenomena. IV.  ...  The modelling of the leader vehicle velocity estimation based on visual data is reconstructed, and odometry measurements were simulated.  ... 
doi:10.1109/robot.2004.1302391 dblp:conf/icra/NgGSGWC04 fatcat:kduqcolhubc3xnpthg7iil35fq

Head Pose Estimation on Top of Haar-Like Face Detection: A Study Using the Kinect Sensor

Anwar Saeed, Ayoub Al-Hamadi, Ahmed Ghoneim
2015 Sensors  
It is clearly shown through this work that using the depth data, we improve the accuracy of the head pose estimation.  ...  Using a concatenation of the aforementioned feature types, we achieved a head pose estimation with average errors not exceeding 5.1 • , 4.6 • , 4.2 • for pitch, yaw and roll angles, respectively.  ...  [17] propose a model free approach to estimate the head pose using stereovision. They utilize the reconstructed face plane along with the eye locations to estimate each instance of pose.  ... 
doi:10.3390/s150920945 pmid:26343651 pmcid:PMC4610497 fatcat:ss6s724gpzf65imgrz6l2yjj2u
« Previous Showing results 1 — 15 out of 324 results