Filters








83 Hits in 5.9 sec

Marker-based human pose tracking using adaptive annealed particle swarm optimization with search space partitioning

Ashraf Sharifi, Ahad Harati, Abedin Vahedian
2017 Image and Vision Computing  
In this paper, a marker-based human pose tracking algorithm from multi view video sequences is proposed.  ...  Experimental results on Pose Estimation and Action Recognition (PEAR) database indicate that the proposed algorithm achieves lower estimation error in tracking human motion compared with Annealed Particle  ...  Conclusions In this paper a combination of annealed PSO algorithm with search space partitioning is presented for marker-based pose estimation.  ... 
doi:10.1016/j.imavis.2017.03.003 fatcat:26vnhhh6cfbvzfz34amvdrcyky

A Review on Particle Swarm Optimization Algorithm and Its Variants to Human Motion Tracking

Sanjay Saini, Dayang Rohaya Bt Awang Rambli, M. Nordin B. Zakaria, Suziah Bt Sulaiman
2014 Mathematical Problems in Engineering  
Particle swarm optimization (PSO) is a population-based globalized search algorithm which has been successfully applied to address human motion tracking problem and produced better results in high-dimensional  ...  search space.  ...  The authors would like to thank Leonid Sigal for many useful discussions regarding Brown University framework and also for maintaining the online evaluation for the HumanEva (Lee walk sequence) dataset  ... 
doi:10.1155/2014/704861 fatcat:dnsqiwgluzcdrgixpruopuxsui

Markerless human articulated tracking using hierarchical particle swarm optimisation

Vijay John, Emanuele Trucco, Spela Ivekovic
2010 Image and Vision Computing  
We compare experimentally HPSO with particle filter (PF), annealed particle filter (APF) and partitioned sampling annealed particle filter (PSAPF) using the computational framework provided by Balan et  ...  The tracking is formulated as a multi-dimensional non-linear optimisation and solved using particle swarm optimisation (PSO), a swarm-intelligence algorithm which has gained popularity in recent years  ...  Adrian Hilton and his group for providing us with the test sequences and for many useful discussions, and Alexandru Balan from Brown University for kindly sharing the evaluation software.  ... 
doi:10.1016/j.imavis.2010.03.008 fatcat:avmgdp2dwvbarm6ywuceram2fa

Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture

Enrique Yeguas-Bolivar, Rafael Muñoz-Salinas, Rafael Medina-Carnicer, Angel Carmona-Poyato
2014 Applied Soft Computing  
., with and without partitioning the search space.  ...  Optimization -with two of the most relevant particle filters proposed in the literature namely, the Annealed Particle Filter, and the Partitioned Sampling Annealed Particle Filter.  ...  Acknowledgements This work has been developed with the support of the Research Projects called "TIN2012-32952" and "BROCA", both financed by Science and Technology Ministry of Spain and FEDER.  ... 
doi:10.1016/j.asoc.2014.01.007 fatcat:st4r6m457rcjlmaqid7ajcquue

Reconstruction of 3D human motion in real-time using particle swarm optimization with GPU-accelerated fitness function

Bogdan Kwolek, Boguslaw Rymut
2018 Journal of Real-Time Image Processing  
observations and to perform particle swarm optimization-based tracking.  ...  We demonstrate effective parallelization of the particle swarm optimization on GPU.  ...  The discussed results were obtained using a soft partitioning PSO, which is a variant of particle swarm optimization [22] .  ... 
doi:10.1007/s11554-018-0825-5 fatcat:kbiehvqcxjg3xhakhpdiyykeuu

Coupling Top-down and Bottom-up Methods for 3D Human Pose and Shape Estimation from Monocular Image Sequences [article]

Atul Kanaujia
2014 arXiv   pre-print
Additionally, these learned priors can be actively adapted to the test data using a likelihood based feedback mechanism.  ...  However, recovery of pose and shape of humans in such monocular videos is inherently an ill-posed problem, marked by frequent depth and view based ambiguities due to self-occlusion, foreshortening and  ...  The tracked 3D pose are then used to estimate 3D human shapes using simulated annealing.  ... 
arXiv:1410.0117v2 fatcat:db73dqqopjabbiuphnv2gk5hhi

Distributed Vision Networks for Human Pose Analysis [chapter]

Hamid Aghajan, Chen Wu, Richard Kleihorst
2008 Signal Processing Techniques for Knowledge Extraction and Information Fusion  
In this chapter collaborative processing and data fusion mechanisms are examined in the context of a human pose estimation framework.  ...  The human body model also allows the cameras to interact with one another on the initialization of feature extraction parameters, or to evaluate the relative value of their derived features.  ...  The complexity of the top-down approach lies in the searching technique. A number of methods such as partitioned sampling, annealing, particle swarm filtering, etc., have been adopted.  ... 
doi:10.1007/978-0-387-74367-7_10 fatcat:t5ucgnj6xvhllemjl2ed46gyhy

Parallelization strategies for markerless human motion capture

Alberto Cano, Enrique Yeguas-Bolivar, Rafael Muñoz-Salinas, Rafael Medina-Carnicer, Sebastián Ventura
2014 Journal of Real-Time Image Processing  
Markerless Motion Capture (MMOCAP) is the problem of determining the pose of a person from images captured by one or several cameras simultaneously without using markers on the subject.  ...  Our proposal is experimentally compared on six sequences of the HumanEva-I dataset using the CMAES algorithm.  ...  proposed the Partitioned Sampling Annealed Particle Filter (PSAPF) [1] as an attempt to combine the strengths of PS and the Annealed Search.  ... 
doi:10.1007/s11554-014-0467-1 fatcat:wjmqqlbsxrhw3ncac72evkznwy

Model-based hand pose estimation via spatial-temporal hand parsing and 3D fingertip localization

Hui Liang, Junsong Yuan, Daniel Thalmann, Zhengyou Zhang
2013 The Visual Computer  
In this paper we present a novel vision-based markerless hand pose estimation scheme with the input of depth image sequences.  ...  The detected 3D fingertip locations are finally used for hand pose estimation with an inverse kinematics solver.  ...  [8] presents another modelbased framework, and minimization of the difference between the input and model projection is solved using a variant of particle swarm optimization (PSO) algorithm.  ... 
doi:10.1007/s00371-013-0822-4 fatcat:nfp6wbvv6nacvd6dwr3tcxg2ce

Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations [article]

Sk Aziz Ali and Kerem Kahraman and Christian Theobalt and Didier Stricker and Vladislav Golyanik
2020 arXiv   pre-print
In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field.  ...  The optimal alignment is obtained by explicit modeling of forces acting on the particles as well as their velocities and displacements with second-order ordinary differential equations of motion.  ...  Simulated annealing [71] and particle swarm optimization [72] are prominent examples of them.  ... 
arXiv:2009.14005v1 fatcat:elj3loqcpzcvteu5ingv66ttr4

Automatic Framework for Spectral–Spatial Classification Based on Supervised Feature Extraction and Morphological Attribute Profiles

Pedram Ghamisi, Jon Atli Benediktsson, Gabriele Cavallaro, Antonio Plaza
2014 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
This way, by using a combination of training followed by classification, maps are produced from imagery.  ...  Thanks to the detailed spectral information provided by hyperspectral sensors, the possibility of accurately discriminating materials of interest with an increased classification accuracy is increased.  ...  The authors are with the Faculty of Electrical and Computer Engineering, University of Iceland, 107 Reykjavik, Iceland (e-mail: peg6@hi.is).  ... 
doi:10.1109/jstars.2014.2298876 fatcat:nxj4xswdlvc3bb47wujib2lahi

Designing the Characteristics of Design Teams via Cognitively Ins.pdf

Christopher McComb
2018 Figshare  
This work creates a computational framework that efficiently emulates human design teams, thus facilitating the derivation of a theory linking the properties of design problems to optimized team characteristics  ...  Although teams have the potential to search effectively for solutions, they are also prone to a number of pitfalls.  ...  The MSA algorithms utilize principles of differential evolution and particle swarm optimization to accomplish interaction between agents [180, 181] .  ... 
doi:10.6084/m9.figshare.5830824.v1 fatcat:47cdi6usi5ef7nnkb4fg5bc7fm

Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations

Sk Aziz Ali, Kerem Kahraman, Christian Theobalt, Didier Stricker, Vladislav Golyanik
2021 IEEE Access  
The construction of τ θ is a method of hierarchical space partitioning and grouping of particles as described in Alg. 1 [30] .  ...  ., tracked marker locations) over multiple frames [82] can also increase the correspondence reliability during the registration.  ...  Selecting best FGA parameters with a grid search method on G, and η (slices for η = 0.1, 0.2, 0.3, 0.4 and 0.5).  ... 
doi:10.1109/access.2021.3084505 fatcat:yi53mry6mje3vilzglsucealnm

Table of contents

2009 2009 17th Mediterranean Conference on Control and Automation  
Ant colony optimization (ACO) is one of the swarm intelligence (SI) techniques.  ...  Hamzaoui, Abdelaziz IUT of Troyes This paper deals with the design of a robust adaptive fuzzy tracking control for a class of uncertain and disturbed nonlinear systems.  ...  Target tracking and vehicle pose are obtained using a Laser Vision System (LVS).  ... 
doi:10.1109/med.2009.5164498 fatcat:bi37lbkbhfaihj7lbc64vvplo4

An Evolutionary Game-Based Mechanism for Routing P2P Network Flow among Selfish Peers

Fang Zuo, Wei Zhang
2014 Journal of Networks  
Telecommunication networks need to support a wide range of services and functionalities with capability of autonomy, scalability and adaptability for managing applications to meet business needs.  ...  The DAIM model uses a group of standard switches, databases, and corresponding between them by using DAIM agents.  ...  Improved Multiple Swarm PSO Algorithm Particle swarm algorithm can effectively optimize the deployment of wireless sensor networks, but when the standard particle swarm was flying in the search space,  ... 
doi:10.4304/jnw.9.01.10-17 fatcat:tbmafdamk5am7a6ba26gsxzydq
« Previous Showing results 1 — 15 out of 83 results