Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassificatio...Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.展开更多
We propose a high-performance path planning algorithm for automatic target tracking in the applications of real-time simulation and visualization of large-scale terrain datasets, with a large number of moving objects ...We propose a high-performance path planning algorithm for automatic target tracking in the applications of real-time simulation and visualization of large-scale terrain datasets, with a large number of moving objects （such as vehicles） tracking multiple moving targets. By using a modified Dijkstra＇s algorithm, an optimal path between each vehicle-target pair over a weighted grid-presented terrain is computed and updated to eliminate the problem of local minima and losing of tracking. Then, a dynamic path re-planning strategy using multi-resolution representation of a dynamic updating region is proposed to achieve high-performance by trading-off precision for efficiency, while guaranteeing accuracy. Primary experimental results showed that our algorithm successfully achieved l0 to 96 frames per second interactive path-replanning rates during a terrain simulation scenario with 10 to 100 vehicles and multiple moving targets.展开更多
To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov rand...To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov random field(MRMRF)model.The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales.The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm,and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation.The results are then segmented by the improved MRMRF model.In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model,it is proposed to introduce variable weight parameters in the segmentation process of each scale.Furthermore,the final segmentation results are optimized.We name this algorithm the variable-weight multi-resolution Markov random field(VWMRMRF).The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness,and can accurately and stably achieve low signal-to-noise ratio,weak boundary MR image segmentation.展开更多
为了规范和统一多分辨率模型的描述方法、建模步骤和活动,提出一种基于BOM(Base Object Model)和FEDEP(Federation Development and Execution Process)的多分辨率建模框架.该框架包括3种基于BOM的多分辨率建模方法和基于FEDEP的多分辨...为了规范和统一多分辨率模型的描述方法、建模步骤和活动,提出一种基于BOM(Base Object Model)和FEDEP(Federation Development and Execution Process)的多分辨率建模框架.该框架包括3种基于BOM的多分辨率建模方法和基于FEDEP的多分辨率建模过程.简要介绍这3种方法,重点分析FEDEP中与BOM和多分辨率建模相关的基本活动,将基于BOM的多分辨率建模过程与FEDEP集成在一起.该框架可以实现多分辨率模型描述的形式化和通用性、建模步骤和过程的规范化,促进多分辨率模型的重用、互操作和组合,保证模型的一致性和多分辨率建模的有效性.展开更多
In object detection, detecting an object with 100 pixels is substantially different from detecting an object with 10 pixels. Many object detection algorithms assume that the pedestrian scale is fixed during detection,...In object detection, detecting an object with 100 pixels is substantially different from detecting an object with 10 pixels. Many object detection algorithms assume that the pedestrian scale is fixed during detection, such as the DPM detector. However, detectors often give rise to different detection effects under the circumstance of different scales. If a detector is used to perform pedestrian detection in different scales, the accuracy of pedestrian detection could be improved. A multi-resolution DPM pedestrian detection algorithm is proposed in this paper. During the stage of model training, a resolution factor is added to a set of hidden variables of a latent SVM model. Then, in the stage of detection, a standard DPM model is used for the high resolution objects and a rigid template is adopted in case of the low resolution objects. In our experiments, we find that in case of low resolution objects the detection accuracy of a standard DPM model is lower than that of a rigid template. In Caltech, the omission ratio of a multi-resolution DPM detector is 52% with 1 false positive per image (1FPPI);and the omission ratio rises to 59% (1FPPI) as far as a standard DPM detector is concerned. In the large-scale sample set of Caltech, the omission ratios given by the multi-resolution and the standard DPM detectors are 18% (1FPPI) and 26% (1FPPI), respectively.展开更多
Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of metho...Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.展开更多
This study proposes a virtual globe-based vector data model named the quaternary quadrangle vector tile model(QQVTM)in order to better manage,visualize,and analyze massive amounts of global multi-scale vector data.The...This study proposes a virtual globe-based vector data model named the quaternary quadrangle vector tile model(QQVTM)in order to better manage,visualize,and analyze massive amounts of global multi-scale vector data.The model integrates the quaternary quadrangle mesh(a discrete global grid system)and global image,terrain,and vector data.A QQVTM-based organization method is presented to organize global multi-scale vector data,including linear and polygonal vector data.In addition,tilebased reconstruction algorithms are designed to search and stitch the vector fragments scattered in tiles to reconstruct and store the entire vector geometries to support vector query and 3D analysis of global datasets.These organized vector data are in turn visualized and queried using a geometry-based approach.Our experimental results demonstrate that the QQVTM can satisfy the requirements for global vector data organization,visualization,and querying.Moreover,the QQVTM performs better than unorganized 2D vectors regarding rendering efficiency and better than the latitude–longitude-based approach regarding data redundancy.展开更多
Two simplification algorithms are proposed for automatic decimation of polygonal models, and for generating their LODs. Each algorithm orders vertices according to their priority values and then removes them iterative...Two simplification algorithms are proposed for automatic decimation of polygonal models, and for generating their LODs. Each algorithm orders vertices according to their priority values and then removes them iteratively. For setting the priority value of each vertex, exploiting normal field of its one-ring neighborhood, we introduce a new measure of geometric fidelity that reflects well the local geometric features of the vertex. After a vertex is selected, using other measures of geometric distortion that are based on normal field deviation and distance measure, it is decided which of the edges incident on the vertex is to be collapsed for removing it. The collapsed edge is substituted with a new vertex whose position is found by minimizing the local quadric error measure. A comparison with the state-of-the-art algorithms reveals that the proposed algorithms are simple to implement, are computationally more efficient, generate LODs with better quality, and preserve salient features even after drastic simplification. The methods are useful for applications such as 3D computer games, virtual reality, where focus is on fast running time, reduced memory overhead, and high quality LODs.展开更多
To manipulate the layout analysis problem for complex or irregular document image, a Unified HMM-based Layout Analysis Framework is presented in this paper. Based on the multi-resolution wavelet analysis results of th...To manipulate the layout analysis problem for complex or irregular document image, a Unified HMM-based Layout Analysis Framework is presented in this paper. Based on the multi-resolution wavelet analysis results of the document image, we use HMM method in both inner-scale image model and trans-scale context model to classify the pixel region properties, such as text, picture or background. In each scale, a HMM direct segmentation method is used to get better inner-scale classification result. Then another HMM method is used to fuse the inner-scale result in each scale and then get better final segmentation result. The optimized algorithm uses a stop rule in the coarse to fine multi-scale segmentation process, so the speed is improved remarkably. Experiments prove the efficiency of proposed algorithm.展开更多
基金This project was supported by the National Natural Foundation of China (60404022) and the Foundation of Department ofEducation of Hebei Province (2002209).
文摘Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.
基金Project partially supported by NSF (No. CCR0306438) and theBoeing Company, USA
文摘We propose a high-performance path planning algorithm for automatic target tracking in the applications of real-time simulation and visualization of large-scale terrain datasets, with a large number of moving objects （such as vehicles） tracking multiple moving targets. By using a modified Dijkstra＇s algorithm, an optimal path between each vehicle-target pair over a weighted grid-presented terrain is computed and updated to eliminate the problem of local minima and losing of tracking. Then, a dynamic path re-planning strategy using multi-resolution representation of a dynamic updating region is proposed to achieve high-performance by trading-off precision for efficiency, while guaranteeing accuracy. Primary experimental results showed that our algorithm successfully achieved l0 to 96 frames per second interactive path-replanning rates during a terrain simulation scenario with 10 to 100 vehicles and multiple moving targets.
基金the National Natural Science Foundation of China(Grant No.11471004)the Key Research and Development Program of Shaanxi Province,China(Grant No.2018SF-251)。
文摘To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov random field(MRMRF)model.The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales.The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm,and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation.The results are then segmented by the improved MRMRF model.In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model,it is proposed to introduce variable weight parameters in the segmentation process of each scale.Furthermore,the final segmentation results are optimized.We name this algorithm the variable-weight multi-resolution Markov random field(VWMRMRF).The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness,and can accurately and stably achieve low signal-to-noise ratio,weak boundary MR image segmentation.
文摘为了规范和统一多分辨率模型的描述方法、建模步骤和活动,提出一种基于BOM(Base Object Model)和FEDEP(Federation Development and Execution Process)的多分辨率建模框架.该框架包括3种基于BOM的多分辨率建模方法和基于FEDEP的多分辨率建模过程.简要介绍这3种方法,重点分析FEDEP中与BOM和多分辨率建模相关的基本活动,将基于BOM的多分辨率建模过程与FEDEP集成在一起.该框架可以实现多分辨率模型描述的形式化和通用性、建模步骤和过程的规范化,促进多分辨率模型的重用、互操作和组合,保证模型的一致性和多分辨率建模的有效性.
文摘In object detection, detecting an object with 100 pixels is substantially different from detecting an object with 10 pixels. Many object detection algorithms assume that the pedestrian scale is fixed during detection, such as the DPM detector. However, detectors often give rise to different detection effects under the circumstance of different scales. If a detector is used to perform pedestrian detection in different scales, the accuracy of pedestrian detection could be improved. A multi-resolution DPM pedestrian detection algorithm is proposed in this paper. During the stage of model training, a resolution factor is added to a set of hidden variables of a latent SVM model. Then, in the stage of detection, a standard DPM model is used for the high resolution objects and a rigid template is adopted in case of the low resolution objects. In our experiments, we find that in case of low resolution objects the detection accuracy of a standard DPM model is lower than that of a rigid template. In Caltech, the omission ratio of a multi-resolution DPM detector is 52% with 1 false positive per image (1FPPI);and the omission ratio rises to 59% (1FPPI) as far as a standard DPM detector is concerned. In the large-scale sample set of Caltech, the omission ratios given by the multi-resolution and the standard DPM detectors are 18% (1FPPI) and 26% (1FPPI), respectively.
基金financially supported by the National Natural Science Foundation of China(No.51978494)the Science and Technology Innovation Program Project of Shanghai City Investment Co.,Ltd.(No.CTKY-ZDXM-2020-012).
文摘Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.
基金the National Natural Science Foundation of China[grant number 41171314],[grant number 41023001]the Fundamental Research Funds for the Central Universities[grant number 2014619020203].Comments from the anonymous reviewers and editor are appreciated.
文摘This study proposes a virtual globe-based vector data model named the quaternary quadrangle vector tile model(QQVTM)in order to better manage,visualize,and analyze massive amounts of global multi-scale vector data.The model integrates the quaternary quadrangle mesh(a discrete global grid system)and global image,terrain,and vector data.A QQVTM-based organization method is presented to organize global multi-scale vector data,including linear and polygonal vector data.In addition,tilebased reconstruction algorithms are designed to search and stitch the vector fragments scattered in tiles to reconstruct and store the entire vector geometries to support vector query and 3D analysis of global datasets.These organized vector data are in turn visualized and queried using a geometry-based approach.Our experimental results demonstrate that the QQVTM can satisfy the requirements for global vector data organization,visualization,and querying.Moreover,the QQVTM performs better than unorganized 2D vectors regarding rendering efficiency and better than the latitude–longitude-based approach regarding data redundancy.
文摘Two simplification algorithms are proposed for automatic decimation of polygonal models, and for generating their LODs. Each algorithm orders vertices according to their priority values and then removes them iteratively. For setting the priority value of each vertex, exploiting normal field of its one-ring neighborhood, we introduce a new measure of geometric fidelity that reflects well the local geometric features of the vertex. After a vertex is selected, using other measures of geometric distortion that are based on normal field deviation and distance measure, it is decided which of the edges incident on the vertex is to be collapsed for removing it. The collapsed edge is substituted with a new vertex whose position is found by minimizing the local quadric error measure. A comparison with the state-of-the-art algorithms reveals that the proposed algorithms are simple to implement, are computationally more efficient, generate LODs with better quality, and preserve salient features even after drastic simplification. The methods are useful for applications such as 3D computer games, virtual reality, where focus is on fast running time, reduced memory overhead, and high quality LODs.
文摘To manipulate the layout analysis problem for complex or irregular document image, a Unified HMM-based Layout Analysis Framework is presented in this paper. Based on the multi-resolution wavelet analysis results of the document image, we use HMM method in both inner-scale image model and trans-scale context model to classify the pixel region properties, such as text, picture or background. In each scale, a HMM direct segmentation method is used to get better inner-scale classification result. Then another HMM method is used to fuse the inner-scale result in each scale and then get better final segmentation result. The optimized algorithm uses a stop rule in the coarse to fine multi-scale segmentation process, so the speed is improved remarkably. Experiments prove the efficiency of proposed algorithm.
