Filters








31,813 Hits in 4.4 sec

Design and Implementation of Real Time System for Object Detection and Classification on Parallel Virtual Machine

Tati Rajab Mengko, Trio Adiono, Handoko Setyawan, Rini Setiadarma, Donny A. Hudiansyah
1998 IAPR International Workshop on Machine Vision Applications  
This paper addresses the problem of implementing an object detection and classification system on a parallel virtual machine. Detection process was implemented using deformable template algorithm.  ...  Previous research proved, the system's speed-performance is proportional to the number of object detected and model-used.  ...  Included in this section are the algorithms used to detect the existence of the objects and to define search area for each object.  ... 
dblp:conf/mva/MengkoASSH98 fatcat:6623mf4g5zbwbl5dwxji3sdf7q

A multicore based parallel image registration method

Lin Yang, Leiguang Gong, Hong Zhang, J.L. Nosher, D.J. Foran
2009 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society  
The algorithm was shown to be effective and robust under conditions of large deformations.  ...  We introduced a nonregular data partition algorithm using the K-means clustering algorithm to group the landmarks based on the number of available processing cores.  ...  Automatic algorithms for landmark detection and matching have been developed [6, 7] , though the robustness of those methods has not been sufficiently demonstrated.  ... 
doi:10.1109/iembs.2009.5334782 pmid:19964921 pmcid:PMC3360576 fatcat:4h2oj2s35bdvtedwzzqtryotv4

A multi-core CPU pipeline architecture for virtual environments

Eric Acosta, Alan Liu, Jennifer Sieck, Gilbert Muniz, Mark Bowyer, Rocco Armonda
2009 Studies in Health Technology and Informatics  
The architecture enables development of VEs that leverage the computational resources of all CPU cores for VE simulation. A VE's workload is dynamically distributed across the available CPU cores.  ...  A VE can be developed once and scale efficiently with the number of cores. The described pipeline architecture makes it possible to develop complex physically-based VEs for medical simulations.  ...  An "object interaction pair" is used to model pair-wise interactions between objects by specifying the collision detection and response algorithms for an interaction.  ... 
pmid:19377102 fatcat:5mztch7iirgsdkd5abgyukah5a

Four-chamber heart modeling and automatic segmentation for 3D cardiac CT volumes

Yefeng Zheng, Bogdan Georgescu, Adrian Barbu, Michael Scheuering, Dorin Comaniciu, Joseph M. Reinhardt, Josien P. W. Pluim
2008 Medical Imaging 2008: Image Processing  
Multi-chamber heart segmentation is a prerequisite for quantification of the cardiac function. In this paper, we propose an automatic heart chamber segmentation system.  ...  These landmarks can be detected reliably to guide the automatic model fitting process.  ...  Two cusp points on the intersection are important landmarks, and an automatic detection algorithm should be able to detect them reliably.  ... 
doi:10.1117/12.770710 dblp:conf/miip/ZhengGBSC08 fatcat:ng6k3xi25be5fce4ma5yzoiqk4

First results and future developments of the MIBISOC Project in the IBISlab of the university of parma

Stefano Cagnoni, Oscar Cordón, Pablo Mesejo, Youssef S.G. Nashed, Roberto Ugolotti
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
In this paper, we describe the work which is being developed in the IBISlab, as well as its future developments and main objectives, within the framework of this ITN.  ...  The Intelligent Bio-Inpired Systems laboratory (IBISlab) in the University of Parma is one of the partners of this ITN.  ...  Model-based object detection and recognition Many object detection tasks, like the localization and segmentation of anatomical structures, can be reformulated as global optimization problems.  ... 
doi:10.1145/2330784.2330865 dblp:conf/gecco/CagnoniCMNU12 fatcat:rp3xgwwqyrafxn5myot2qo5jnq

DETECTION AND CORRECTION OF CHANGES IN EXTERIOR AND INTERIOR ORIENTATIONS WHILE ESTIMATING 3-D OBJECT DEFORMATIONS FROM MULTIPLE IMAGES WITH WEAK OR STRONG IMAGING GEOMETRY

O. Jokinen, H. Haggrén
2012 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Weak imaging geometry allows to detect smaller changes than the strong one. The closer an initial approximation of deformation is available, the higher is the probability of correct detection.  ...  Subsequent correction of changed orientations and estimation of deformation may provide a high accuracy of 1:140000 of the object dimensions for both weak and strong imaging geometries, when the noise  ...  For the second data, the algorithm convergences to a correct solution even from an initial approximation for the deformation of no deformation at all, but then the percentages of correctly detected changed  ... 
doi:10.5194/isprsannals-i-3-43-2012 fatcat:nxla3y6t4jebbpwz5ybizxr4v4

Object Detection in Autonomous Driving Scenarios Based on an Improved Faster-RCNN

Yan Zhou, Sijie Wen, Dongli Wang, Jinzhen Mu, Irampaye Richard
2021 Applied Sciences  
Object detection is one of the key algorithms in automatic driving systems.  ...  Aiming at addressing the problem of false detection and the missed detection of both small and occluded objects in automatic driving scenarios, an improved Faster-RCNN object detection algorithm is proposed  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app112411630 fatcat:kuf22eo6evfh7kjrwh2zo6f2wa

A Novel Vehicle Detection Framework Based on Parallel Vision

Ying Zhuo, Lan Yan, Wenbo Zheng, Yutian Zhang, Chao Gou, Ming Yan
2022 Wireless Communications and Mobile Computing  
Experimental results verify the effectiveness of our proposed framework, demonstrating that the combination of virtual and real data has better performance for training the vehicle detection model than  ...  Therefore, we present a novel vehicle detection framework based on the parallel vision to tackle the above issue, using the specially designed virtual data to help train the vehicle detection model.  ...  Deformable part model [15] is a classic object detection model, DPM for short. DPM models the object as a combination of several components.  ... 
doi:10.1155/2022/9667506 fatcat:32owsz4yt5exfmv7x7qgcgpw5i

A review of vessel extraction techniques and algorithms

Cemil Kirbas, Francis Quek
2004 ACM Computing Surveys  
While we have mainly targeted the extraction of blood vessels, neurosvascular structure in particular, we have also reviewed some of the segmentation methods for the tubular objects that show similar characteristics  ...  approaches, (5) neural network-based approaches, and (6) tube-like object detection approaches.  ...  The system employs several edge detection algorithms, for example, Canny and Sobel, for the extraction of vessel boundaries.  ... 
doi:10.1145/1031120.1031121 fatcat:7zms3avnjrfd7plwcitqx3cdiq

Mesh-based video objects tracking combining motion and luminance discontinuities criteria

Sébastien Valette, Isabelle Magnin, Rémy Prost
2004 Signal Processing  
The mesh is deformed under the minimization of an objective function. This function includes a motion energy, a spatial boundary energy and a temporal regularization energy.  ...  A new content-based mesh design algorithm for video objects segmentation and tracking is proposed.  ...  This work is in the scope of the scientiÿc topics of the PRC-GDR ISIS research group of the French National Center for Scientiÿc Research (CNRS).  ... 
doi:10.1016/j.sigpro.2004.04.003 fatcat:dtdmrn35c5fxhnlteei74u6y7i

The HUMANOID Environment for Interactive Animation of Multiple Deformable Human Characters

R. Boulic, T. Capin, Z. Huang, P. Kalra, B. Lintermann, N. Magnenat-Thalmann, L. Moccozet, T. Molet, I. Pandzic, K. Saar, A. Schmitt, J. Shen (+1 others)
1995 Computer graphics forum (Print)  
We present the design of the system and the integration of the various features: generic modeling of a large class of entities with the BODY data structure, realistic skin deformation for body and hands  ...  , facial animation, collision detection, integrated motion control and parallelization of computation intensive tasks.  ...  The authors are also indebted to Serge Rezzonico for the upgrade of the LIG 5D Toolkit and the Interface Builder.  ... 
doi:10.1111/j.1467-8659.1995.cgf143_0337.x fatcat:vo25ea5gczgrvpdooudhpyvnma

The HUMANOID Environment for Interactive Animation of Multiple Deformable Human Characters

R. Boulic, T. Capin, Z. Huang, P. Kalra, B. Lintermann, N. Magnenat-Thalmann, L. Moccozet, T. Molet, I. Pandzic, K. Saar, A. Schmitt, J. Shen (+1 others)
1995 Computer graphics forum (Print)  
We present the design of the system and the integration of the various features: generic modeling of a large class of entities with the BODY data structure, realistic skin deformation for body and hands  ...  , facial animation, collision detection, integrated motion control and parallelization of computation intensive tasks.  ...  The authors are also indebted to Serge Rezzonico for the upgrade of the LIG 5D Toolkit and the Interface Builder.  ... 
doi:10.1111/1467-8659.1430337 fatcat:u5duy7s5cfa7bntslgavkkqlbm

Automatic Detection and Recognition of Signs From Natural Scenes

X. Chen, J. Yang, J. Zhang, A. Waibel
2004 IEEE Transactions on Image Processing  
We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle.  ...  In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task.  ...  ACKNOWLEDGMENT The authors would like to thank the associate editor and anonymous reviewers for their invaluable comments and suggestions led to a great improvement on this manuscript.  ... 
doi:10.1109/tip.2003.819223 pmid:15376960 fatcat:lufark62cfbjlfaye6zs22c5ne

Focal-plane moving object segmentation for realtime video surveillance

David Lopez Vilarino, Piotr Dudek, Diego Cabello Ferrer
2008 2008 IEEE International Symposium on Circuits and Systems  
To illustrate the validity of the proposal some examples and results regarding the computation time achieved in the implementation of the proposed algorithm on a cellular processor array (SCAMP-3 vision  ...  In this paper a new technique for segmenting and tracking moving objects in a user-defined control area is presented.  ...  ACKNOWLEDGMENT The authors would like to thank to Xunta de Galicia, which has partly supported this work (PGIDIT06TIC10502PR).  ... 
doi:10.1109/iscas.2008.4541739 dblp:conf/iscas/VilarinoDC08 fatcat:rh3w2rn62nby3n5ic577a6ymnm

Detection of spatial orientation objects for automatic orientation of arbitrary arranged metric images

F. Boochs
2005 Journal sur l'enseignement des sciences et technologies de l'information et des systèmes  
The paper presents a new solution for the automatic orientation of metric images using spatial tie objects.  ...  Algorithms have been developed allowing to detect and localise such spatial tie objects automatically and will be presented here.  ...  In most cases, these are collected by means of algorithms, allowing to detect the imaged object points.  ... 
doi:10.1051/bib-j3ea:2005803 fatcat:jx22s5y4t5afngypx6gm4duqdy
« Previous Showing results 1 — 15 out of 31,813 results