The Experts below are selected from a list of 175983 Experts worldwide ranked by ideXlab platform
Yanshun Han - One of the best experts on this subject based on the ideXlab platform.
-
an efficient parallel multi scale Segmentation Method for remote sensing imagery
Remote Sensing, 2018Co-Authors: Yanshun Han, Yi Yang, Zhengjun Liu, Uwe Soergel, Thomas Blaschke, Shiyong CuiAbstract:Remote sensing (RS) image Segmentation is an essential step in geographic object-based image analysis (GEOBIA) to ultimately derive “meaningful objects”. While many Segmentation Methods exist, most of them are not efficient for large data sets. Thus, the goal of this research is to develop an efficient parallel multi-scale Segmentation Method for RS imagery by combining graph theory and the fractal net evolution approach (FNEA). Specifically, a minimum spanning tree (MST) algorithm in graph theory is proposed to be combined with a minimum heterogeneity rule (MHR) algorithm that is used in FNEA. The MST algorithm is used for the initial Segmentation while the MHR algorithm is used for object merging. An efficient implementation of the Segmentation strategy is presented using data partition and the “reverse searching-forward processing” chain based on message passing interface (MPI) parallel technology. Segmentation results of the proposed Method using images from multiple sensors (airborne, SPECIM AISA EAGLE II, WorldView-2, RADARSAT-2) and different selected landscapes (residential/industrial, residential/agriculture) covering four test sites indicated its efficiency in accuracy and speed. We conclude that the proposed Method is applicable and efficient for the Segmentation of a variety of RS imagery (airborne optical, satellite optical, SAR, high-spectral), while the accuracy is comparable with that of the FNEA Method.
-
an efficient multiscale srmmhr statistical region merging and minimum heterogeneity rule Segmentation Method for high resolution remote sensing imagery
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2009Co-Authors: Yanshun Han, Jinghui YangAbstract:Multiscale Segmentation is an essential step for higher level image processing in remote sensing. This paper presents a new multiscale SRMMHR Segmentation Method integrating the advantages of Statistical Region Merging (SRM) for initial Segmentation and the Minimum Heterogeneity Rule (MHR) for object merging. The high-resolution (HR) QuickBird imageries are used to demonstrate the SRMMHR Segmentation Method. The SRM Segmentation Method not only considers spectral, shape, and scale information, but also has the ability to cope with significant noise corruption and handle occlusions. The MHR used for merging objects takes advantage of its spectral, shape, scale information, and the local and global information. Compared with the Fractal Net Evolution Approach (FNEA) that eCognition adopted and SRM Methods, the results show that the proposed Method wipes off small redundant objects existed in traditional SRM Methods, avoids the phenomena where the big homogeneity region has lots of small similar regions existed in the FNEA Method, and gets more integrated and accurate objects. Therefore, the proposed SRMMHR Segmentation Method is an efficient multiscale Segmentation Method for HR imagery.
Jinghui Yang - One of the best experts on this subject based on the ideXlab platform.
-
an efficient multiscale srmmhr statistical region merging and minimum heterogeneity rule Segmentation Method for high resolution remote sensing imagery
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2009Co-Authors: Yanshun Han, Jinghui YangAbstract:Multiscale Segmentation is an essential step for higher level image processing in remote sensing. This paper presents a new multiscale SRMMHR Segmentation Method integrating the advantages of Statistical Region Merging (SRM) for initial Segmentation and the Minimum Heterogeneity Rule (MHR) for object merging. The high-resolution (HR) QuickBird imageries are used to demonstrate the SRMMHR Segmentation Method. The SRM Segmentation Method not only considers spectral, shape, and scale information, but also has the ability to cope with significant noise corruption and handle occlusions. The MHR used for merging objects takes advantage of its spectral, shape, scale information, and the local and global information. Compared with the Fractal Net Evolution Approach (FNEA) that eCognition adopted and SRM Methods, the results show that the proposed Method wipes off small redundant objects existed in traditional SRM Methods, avoids the phenomena where the big homogeneity region has lots of small similar regions existed in the FNEA Method, and gets more integrated and accurate objects. Therefore, the proposed SRMMHR Segmentation Method is an efficient multiscale Segmentation Method for HR imagery.
Richard Kijowski - One of the best experts on this subject based on the ideXlab platform.
-
deep convolutional neural network and 3d deformable approach for tissue Segmentation in musculoskeletal magnetic resonance imaging
Magnetic Resonance in Medicine, 2018Co-Authors: Fang Liu, Zhaoye Zhou, Hyungseok Jang, Alexey Samsonov, Gengya Zhao, Richard KijowskiAbstract:Purpose To describe and evaluate a new fully automated musculoskeletal tissue Segmentation Method using deep convolutional neural network (CNN) and three-dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone Segmentation within the knee joint. Methods A fully automated Segmentation pipeline was built by combining a semantic Segmentation CNN and 3D simplex deformable modeling. A CNN technique called SegNet was applied as the core of the Segmentation Method to perform high resolution pixel-wise multi-class tissue classification. The 3D simplex deformable modeling refined the output from SegNet to preserve the overall shape and maintain a desirable smooth surface for musculoskeletal structure. The fully automated Segmentation Method was tested using a publicly available knee image data set to compare with currently used state-of-the-art Segmentation Methods. The fully automated Method was also evaluated on two different data sets, which include morphological and quantitative MR images with different tissue contrasts. Results The proposed fully automated Segmentation Method provided good Segmentation performance with Segmentation accuracy superior to most of state-of-the-art Methods in the publicly available knee image data set. The Method also demonstrated versatile Segmentation performance on both morphological and quantitative musculoskeletal MR images with different tissue contrasts and spatial resolutions. Conclusion The study demonstrates that the combined CNN and 3D deformable modeling approach is useful for performing rapid and accurate cartilage and bone Segmentation within the knee joint. The CNN has promising potential applications in musculoskeletal imaging. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine.
Joungho Kim - One of the best experts on this subject based on the ideXlab platform.
-
interposer power distribution network pdn modeling using a Segmentation Method for 3 d ics with tsvs
IEEE Transactions on Components Packaging and Manufacturing Technology, 2013Co-Authors: Kiyeong Kim, Jun Ho Lee, Jong Min Yook, Junchul Kim, Heegon Kim, Kunwoo Park, Joungho KimAbstract:In this paper, we propose models for large-sized silicon interposer power distribution networks (PDNs) and through silicon via (TSV)-based stacked grid-type PDNs using a Segmentation Method. We model the PDNs as distributed scalable resistance (R), inductance (L), conductance (G), and capacitance (C)-lumped models for an accurate estimation of the PDN impedance, including PDN inductance and wave phenomena such as the mode resonance at the high end of the frequency range. For this estimation, it is necessary to accurately model all transmission line (TL) sections that form the PDNs using a conformal mapping Method and a phenomenological loss equivalence Method (PEM). After modeling the individual TL sections, all the TL sections are connected based on a Segmentation Method, which is a matrix calculation Method. The Segmentation Method accelerates the calculation speed for the PDN impedance estimation. The proposed models are successfully validated by simulations and measurements in the frequency range 0.1-20 GHz. Using the proposed models, we estimate and analyze the impedance curves of the interposer PDN and TSV-based stacked grid-type PDN with respect to the variations in the horizontal area of the interposer PDN and the number of power/ground TSVs in TSV-based stacked grid-type PDNs, respectively.
-
chip package hierarchical power distribution network modeling and analysis based on a Segmentation Method
IEEE Transactions on Advanced Packaging, 2010Co-Authors: Jaemi Kim, Jongjoo Shim, Kiyeong Kim, Wooji Lee, Yujeong Shim, Jun So Pak, Joungho KimAbstract:In this paper, a new modeling Method for estimating the impedance properties in a chip-package hierarchical power distribution network (PDN) is proposed. The key ideas of the proposed modeling Method are to decompose the chip-package hierarchical PDN into several structures, independently calculate the decomposed structures, and extract the whole structure's impedance by using a Segmentation Method. For the impedance calculations of the independently decomposed structures, a new Method based on proposed analytic expressions is introduced for a chip level PDN, a resonant cavity model is used for a package level PDN, and equivalent circuit models are used for interconnections. The proposed Method has been successfully verified by comparisons with measurements using a fabricated test vehicle in the frequency domain range up to 20 GHz, and it shows improved accuracy as well as computational superiority compared to EM simulations. Finally, the impedance properties in a chip-package hierarchical PDN are thoroughly investigated and analyzed.
-
modeling and measurement of interlevel electromagnetic coupling and fringing effect in a hierarchical power distribution network using Segmentation Method with resonant cavity model
IEEE Transactions on Advanced Packaging, 2008Co-Authors: Jaemin Kim, Youchul Jeong, Jingook Kim, Jun Ho Lee, Chunghyun Ryu, Jongjoo Shim, Minchul Shin, Joungho KimAbstract:A hierarchical power distribution network (PDN) consists of chip, package, and printed circuit board (PCB) level PDNs, as well as various structures such as via, ball, and wire bond interconnections, which connect the different level PDNs. When estimating the simultaneous switching noise (SSN) generation and evaluating PDN designs, PDN impedance calculation is an efficient criterion. In this paper, we introduce two new kinds of modeling approaches that are exceptionally suited to improving the accuracy of the PDN impedance estimation, especially for hierarchical PDN. First, we propose a modeling procedure to add an interlevel electromagnetic coupling effect between PDNs of different levels, based on the resonant cavity model and Segmentation Method. In order to effectively consider the interlevel electromagnetic coupling effect, we introduce a new concept of interlevel PDN, which is, for example, composed of a metal plate in the package-level PDN and a metal plate in the PCB-level PDN. Next, we present a modeling procedure to include the fringing field effect at the edge of small-size PDN structure, which causes a considerable shift of cavity resonance frequencies in the PDN impedance profile. In order to verify the proposed modeling approaches, we have fabricated a series of test vehicles by combining two package-level PDN designs with a PCB-level PDN design. Finally, we have successfully validated the proposed modeling approaches with a series of frequency-domain measurements in a frequency range up to 5 GHz.
Baowei Fei - One of the best experts on this subject based on the ideXlab platform.
-
3d prostate Segmentation of ultrasound images combining longitudinal image registration and machine learning
Proceedings of SPIE, 2012Co-Authors: Xiaofeng Yang, Baowei FeiAbstract:We developed a three-dimensional (3D) Segmentation Method for transrectal ultrasound (TRUS) images, which is based on longitudinal image registration and machine learning. Using longitudinal images of each individual patient, we register previously acquired images to the new images of the same subject. Three orthogonal Gabor filter banks were used to extract texture features from each registered image. Patient-specific Gabor features from the registered images are used to train kernel support vector machines (KSVMs) and then to segment the newly acquired prostate image. The Segmentation Method was tested in TRUS data from five patients. The average surface distance between our and manual Segmentation is 1.18 ± 0.31 mm, indicating that our automatic Segmentation Method based on longitudinal image registration is feasible for segmenting the prostate in TRUS images.
-
a new 3d model based minimal path Segmentation Method for kidney mr images
International Conference on Bioinformatics and Biomedical Engineering, 2008Co-Authors: Baowei FeiAbstract:We present a robust, automated, model-based Segmentation Method for kidney MR Images. We used dynamic programming and a minimal path approach to detect the optimal path within a weighted graph between two end points. We used an energy function to combine distance and gradient information to guide the marching curve and thus evaluate the best path and span a broken edge. We developed an algorithm to automate the placement of initial end points. Dynamic programming was used to automatically optimize and update end points in the procedure for searching curves. A deformable 3D model was generated using principle component analysis (PCA) and it was used as the prior knowledge for the selection of initial end points and for the evaluation of the best path. We used our minimal path Method with surface models to segment mouse kidneys slice-by-slice. The Method has been tested for kidney MR images of 44 mice. To quantitatively assess the automatic Segmentation Method, we compared the automatic Segmentation results with manual Segmentation. The average and standard deviation of the overlap ratios is 0.93 + 0.05. The distance error between the automatic and manual Segmentation is 0.85 plusmn 0.41 pixel. The 3D automatic minimal path Segmentation Method is fast, accurate, and robust. It provides a useful tool for quantification and characterization of kidney MR images.
-
a deformable model based minimal path Segmentation Method for kidney mr images
Proceedings of SPIE--the International Society for Optical Engineering, 2008Co-Authors: Baowei FeiAbstract:We developed a new minimal path Segmentation Method for mouse kidney MR images. We used dynamic programming and a minimal path Segmentation approach to detect the optimal path within a weighted graph between two end points. The energy function combines distance and gradient information to guide the marching curve and thus to evaluate the best path and to span a broken edge. An algorithm was developed to automatically place initial end points. Dynamic programming was used to automatically optimize and update end points during the searching procedure. Principle component analysis (PCA) was used to generate a deformable model, which serves as the prior knowledge for the selection of initial end points and for the evaluation of the best path. The Method has been tested for kidney MR images acquired from 44 mice. To quantitatively assess the automatic Segmentation Method, we compared the results with manual Segmentation. The mean and standard deviation of the overlap ratios are 95.19%±0.03%. The distance error between the automatic and manual Segmentation is 0.82±0.41 pixel. The automatic minimal path Segmentation Method is fast, accurate, and robust and it can be applied not only for kidney images but also for other organs.