The Experts below are selected from a list of 5256 Experts worldwide ranked by ideXlab platform
Jiang Hu - One of the best experts on this subject based on the ideXlab platform.
-
ICSPCS - A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
-
A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
Yimei Kang - One of the best experts on this subject based on the ideXlab platform.
-
ICSPCS - A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
-
A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
Guan Wang - One of the best experts on this subject based on the ideXlab platform.
-
ICSPCS - A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
-
A Bilinear Interpolation mean shift small target tracking algorithm
2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS), 2011Co-Authors: Yimei Kang, Guan Wang, Jiang HuAbstract:It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. The algorithm included six steps: (1) enlarge the target and the surrounding region by Bilinear Interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. The time complexity of the proposed algorithm is O(n). The experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. The deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. The time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.
A Anderberg - One of the best experts on this subject based on the ideXlab platform.
-
current voltage curve translation by Bilinear Interpolation
Progress in Photovoltaics, 2004Co-Authors: Bill Marion, S Rummel, A AnderbergAbstract:By means of Bilinear Interpolation and four reference current-voltage (I-V) curves, an I-V curve of a photovoltaic (PV) module is translated to desired conditions of irradiance and PV module temperature. The four reference I-V curves are measured at two irradiance and two PV module temperature levels and contain all the essential PV module characteristic information for performing the Bilinear Interpolation. The Interpolation is performed first with respect to open-circuit voltage to account for PV module temperature, and second with respect to short-circuit current to account for irradiance. The translation results over a wide range of irradiances and PV module temperatures agree closely with measured values for a group of PV modules representing seven different technologies. Root-mean-square errors were 1.5% or less for the I-V curve parameters of maximum power, voltage at maximum power, current at maximum power, short-circuit current, and open-circuit voltage. The translation is applicable for determining the performance of a PV module for a specified test condition, or for PV system performance modeling.
-
Current–voltage curve translation by Bilinear Interpolation
Progress in Photovoltaics, 2004Co-Authors: Bill Marion, S Rummel, A AnderbergAbstract:By means of Bilinear Interpolation and four reference current-voltage (I-V) curves, an I-V curve of a photovoltaic (PV) module is translated to desired conditions of irradiance and PV module temperature. The four reference I-V curves are measured at two irradiance and two PV module temperature levels and contain all the essential PV module characteristic information for performing the Bilinear Interpolation. The Interpolation is performed first with respect to open-circuit voltage to account for PV module temperature, and second with respect to short-circuit current to account for irradiance. The translation results over a wide range of irradiances and PV module temperatures agree closely with measured values for a group of PV modules representing seven different technologies. Root-mean-square errors were 1.5% or less for the I-V curve parameters of maximum power, voltage at maximum power, current at maximum power, short-circuit current, and open-circuit voltage. The translation is applicable for determining the performance of a PV module for a specified test condition, or for PV system performance modeling.
Yihuan Dong - One of the best experts on this subject based on the ideXlab platform.
-
A non-rigid registration method for cerebral DSA images based on forward and inverse stretching – avoiding Bilinear Interpolation
Bio-medical Materials and Engineering, 2020Co-Authors: Bingbing Zhang, Yihuan DongAbstract:: In order to reduce the motion artifact caused by the patient in cerebral DSA images, a non-rigid registration method based on stretching transformation is presented in this paper. Unlike other traditional methods, it does not need Bilinear Interpolation which is rather time-consuming and even produce 'originally non-existent gray value'. By this method, the mask image is rasterized to generate appropriate control points. The Energy of Histogram of Differences criterion is adopted as similarity measurement, and the Powell algorithm is utilized for acceleration. A forward stretching transformation is used to complete motion estimation and an inverse stretching transformation to generate target image by pixel mapping strategy. This method is effective to maintain the topological relationships of the gray value before and after the image deformation. The mask image remains clear and accurate contours, and the quality of the subtraction image after the registration is favorable. This method can provide support for clinical treatment and diagnosis of cerebral disease.
-
a non rigid registration method for cerebral dsa images based on forward and inverse stretching avoiding Bilinear Interpolation
Bio-medical Materials and Engineering, 2014Co-Authors: Bingbing Zhang, Yihuan DongAbstract:: In order to reduce the motion artifact caused by the patient in cerebral DSA images, a non-rigid registration method based on stretching transformation is presented in this paper. Unlike other traditional methods, it does not need Bilinear Interpolation which is rather time-consuming and even produce 'originally non-existent gray value'. By this method, the mask image is rasterized to generate appropriate control points. The Energy of Histogram of Differences criterion is adopted as similarity measurement, and the Powell algorithm is utilized for acceleration. A forward stretching transformation is used to complete motion estimation and an inverse stretching transformation to generate target image by pixel mapping strategy. This method is effective to maintain the topological relationships of the gray value before and after the image deformation. The mask image remains clear and accurate contours, and the quality of the subtraction image after the registration is favorable. This method can provide support for clinical treatment and diagnosis of cerebral disease.
