A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relat...A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relating motion models and line parameters. The motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences were also presented.展开更多
Landscape changes were traced over the 20 years from 1974 to 1995 in the upper Minjiang River basin, one of the most important forest regions in China, based on satellite image interpretation to provide basic data for...Landscape changes were traced over the 20 years from 1974 to 1995 in the upper Minjiang River basin, one of the most important forest regions in China, based on satellite image interpretation to provide basic data for local decision-making as well as sustainable landscape use and management. Results revealed that landscape from 1974 to 1995 changed at the regional scale as the area of forestland decreased, while cropland, shrubland, economic forest, grassland, and built-up land increased. Landscape changes mainly occurred in forestland, shrubland, grassland, economic forest, and built-up land. Moreover, the changes among forestland, shrubland, and grassland were the largest, influencing the whole characteristics of the changes in the basin. Analysis of the changes between 1974 and 1995 in the study area indicated that landscape heterogeneity and fragmentation increased, whereas landscape connectivity decreased. There were multiple reasons for landscape changes. A principal component analysis (PCA) was used to quantitatively study driving forces of landscape changes. The PCA results showed that economic and population factors were the principal driving forces of landscape changes from 1974 to 1995 in the upper Minjiang River basin, and that PCA was a suitable method for investigating driving forces of landscape changes.展开更多
The purpose of characterizing the image of space photographic instrument is to gain the space included angles from three coordinate axes in the three-dimensional coordinate of the image and the directionality of the t...The purpose of characterizing the image of space photographic instrument is to gain the space included angles from three coordinate axes in the three-dimensional coordinate of the image and the directionality of the three axes of coordinate in the frame of axes of the instrument. The two reference frames will keep in the same direction finally by adjusting according to space angles. This problem was solved by a new high-precision measurement system composed of a double-theodolite and a set of communication system. In the survey system, two TDA5005 total stations from Leica Company will be selected as the double-theodolite and the interdependence of both coordinate systems can be achieved by moving the stations only at one time. Therefore, this measurement system provides a highly efficient and high-precision surveying method to the image calibration of the space photographic instrument. According to the experiment, its measuring accuracy can reach arc-second level.展开更多
Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications.There is no doubt about the importance of translation estimation in active visual tracking.In this pa...Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications.There is no doubt about the importance of translation estimation in active visual tracking.In this paper an approach is presented,and its performances are evaluated.The approach uses a gradient descent for minimizing a dissimilarity measure.The experimental results reveal that this method is efficient for approaching active image translations.展开更多
A new algorithm for unsupervised hyperspectral data unmixing is investigated, which includes a modified minimum noise fraction （MNF） transformation and independent component analysis （ICA）. The modified MNF transf...A new algorithm for unsupervised hyperspectral data unmixing is investigated, which includes a modified minimum noise fraction （MNF） transformation and independent component analysis （ICA）. The modified MNF transformation is used to reduce noise and remove correlation between neighboring bands. Then the ICA is applied to unmix hyperspectral images, and independent endmembers are obtained from unmixed images by using post-processing which includes image segmentation based on statistical histograms and morphological operations. The experimental results demonstrate that this algorithm can identify endmembers resident in mixed pixels. Meanwhile, the results show the high computational efficiency of the modified MNF transformation. The time consumed by the modified method is almost one fifth of the traditional MNF transformation.展开更多
In this paper, the authors propose a refined Branch-and-Bound algorithm for affine-transformation based image registration. Given two feature point-sets in two images respectively, the authors first extract a sequence...In this paper, the authors propose a refined Branch-and-Bound algorithm for affine-transformation based image registration. Given two feature point-sets in two images respectively, the authors first extract a sequence of high-probability matched point-pairs by considering well-defined features. Each resultant point-pair can be regarded as a constraint in the search space of Branch-and-Bound algorithm guiding the search process. The authors carry out Branch-and-Bound search with the constraint of a pair-point selected by using Monte Carlo sampling according to the match measures of point-pairs. If such one cannot lead to correct result, additional candidate is chosen to start another search. High-probability matched point-pairs usually results in fewer loops and the search process is accelerated greatly. Experimental results verify the high efficiency and robustness of the author’s approach.展开更多
Color histogram is now widely used in image retrieval. Color histogram-based image retrieval methods are simple and efficient but without considering the spatial distribution information of the color. To overcome the ...Color histogram is now widely used in image retrieval. Color histogram-based image retrieval methods are simple and efficient but without considering the spatial distribution information of the color. To overcome the shortcoming of conventional color histogram-based image retrieval methods, an image retrieval method based on Radon Transform (RT) is proposed. In order to reduce the computational complexity, wavelet decomposition is used to compress image data. Firstly, images are decomposed by Mallat algorithm. The low-frequency components are then projected by RT to generate the spatial color feature. Finally the moment feature matrices which are saved along with original images are obtained. Experimental results show that the RT based retrieval is more accurate and efficient than traditional color histogram-based method in case that there are obvious objects in images. Further more, RT based retrieval runs significantly faster than the traditional color histogram methods.展开更多
In dimensional affect recognition, the machine learning methods, which are used to model and predict affect, are mostly classification and regression. However, the annotation in the dimensional affect space usually ta...In dimensional affect recognition, the machine learning methods, which are used to model and predict affect, are mostly classification and regression. However, the annotation in the dimensional affect space usually takes the form of a continuous real value which has an ordinal property. The aforementioned methods do not focus on taking advantage of this important information. Therefore, we propose an affective rating ranking framework for affect recognition based on face images in the valence and arousal dimensional space. Our approach can appropriately use the ordinal information among affective ratings which are generated by discretizing continuous annotations.Specifically, we first train a series of basic cost-sensitive binary classifiers, each of which uses all samples relabeled according to the comparison results between corresponding ratings and a given rank of a binary classifier. We obtain the final affective ratings by aggregating the outputs of binary classifiers. By comparing the experimental results with the baseline and deep learning based classification and regression methods on the benchmarking database of the AVEC 2015 Challenge and the selected subset of SEMAINE database, we find that our ordinal ranking method is effective in both arousal and valence dimensions.展开更多
A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV col...A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV color space to get the V channel. Next, the illuminations are respectively estimated by the guided filtering and the variational framework on the V channel and combined into a new illumination by average gradient. The new reflectance is calculated using V channel and the new illumination. Then a new V channel obtained by multiplying the new illumination and reflectance is processed with contrast limited adaptive histogram equalization(CLAHE). Finally, the new image in HSV space is converted back to RGB space to obtain the enhanced image. Experimental results show that the proposed method has better subjective quality and objective quality than existing methods.展开更多
A spatial pyramidal cross-correlation based on interrogation area sub-division is introduced to improve the measurement resolution in particle image velocimetry(PIV). The high-resolution velocity can be achieved with ...A spatial pyramidal cross-correlation based on interrogation area sub-division is introduced to improve the measurement resolution in particle image velocimetry(PIV). The high-resolution velocity can be achieved with a velocity prediction model via coarse cross-correlation. The prediction formula is deduced from the frequency response of the moving average(MA). The performance of this method was assessed using synthetically generated images of sinusoidal shear flow, two-dimensional vortical cellular flow, and homogeneous turbulence. A real PIV experiment of turbulent boundary layer was used to evaluate the new method. The results indicate that the spatial pyramid cross-correlation can robustly increase the spatial resolution.展开更多
基金The National Natural Science Foundation of China (No. 60675017) The National Basic Research Program (973) of China (No. 2006CB303103)
文摘A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relating motion models and line parameters. The motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences were also presented.
基金Project supported by the Major State Basic Research Development Program of China (973 Program)(No. 2002CB111506).
文摘Landscape changes were traced over the 20 years from 1974 to 1995 in the upper Minjiang River basin, one of the most important forest regions in China, based on satellite image interpretation to provide basic data for local decision-making as well as sustainable landscape use and management. Results revealed that landscape from 1974 to 1995 changed at the regional scale as the area of forestland decreased, while cropland, shrubland, economic forest, grassland, and built-up land increased. Landscape changes mainly occurred in forestland, shrubland, grassland, economic forest, and built-up land. Moreover, the changes among forestland, shrubland, and grassland were the largest, influencing the whole characteristics of the changes in the basin. Analysis of the changes between 1974 and 1995 in the study area indicated that landscape heterogeneity and fragmentation increased, whereas landscape connectivity decreased. There were multiple reasons for landscape changes. A principal component analysis (PCA) was used to quantitatively study driving forces of landscape changes. The PCA results showed that economic and population factors were the principal driving forces of landscape changes from 1974 to 1995 in the upper Minjiang River basin, and that PCA was a suitable method for investigating driving forces of landscape changes.
基金This workis supported byinnovationfund of Chinese Academy ofSciences .(Q03P03Z)
文摘The purpose of characterizing the image of space photographic instrument is to gain the space included angles from three coordinate axes in the three-dimensional coordinate of the image and the directionality of the three axes of coordinate in the frame of axes of the instrument. The two reference frames will keep in the same direction finally by adjusting according to space angles. This problem was solved by a new high-precision measurement system composed of a double-theodolite and a set of communication system. In the survey system, two TDA5005 total stations from Leica Company will be selected as the double-theodolite and the interdependence of both coordinate systems can be achieved by moving the stations only at one time. Therefore, this measurement system provides a highly efficient and high-precision surveying method to the image calibration of the space photographic instrument. According to the experiment, its measuring accuracy can reach arc-second level.
文摘Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications.There is no doubt about the importance of translation estimation in active visual tracking.In this paper an approach is presented,and its performances are evaluated.The approach uses a gradient descent for minimizing a dissimilarity measure.The experimental results reveal that this method is efficient for approaching active image translations.
基金Sponsored by the National Natural Science Foundation of China(Grant No. 60272073).
文摘A new algorithm for unsupervised hyperspectral data unmixing is investigated, which includes a modified minimum noise fraction （MNF） transformation and independent component analysis （ICA）. The modified MNF transformation is used to reduce noise and remove correlation between neighboring bands. Then the ICA is applied to unmix hyperspectral images, and independent endmembers are obtained from unmixed images by using post-processing which includes image segmentation based on statistical histograms and morphological operations. The experimental results demonstrate that this algorithm can identify endmembers resident in mixed pixels. Meanwhile, the results show the high computational efficiency of the modified MNF transformation. The time consumed by the modified method is almost one fifth of the traditional MNF transformation.
基金Project supported by the National Basic Research Program (973) of China (No. 2002CB312101), the National Natural Science Founda-tion of China (Nos. 60475013 and 60273053) and Defense Science and Technology Key Lab. Foundation of China (No. 51476070101JW0409)
文摘In this paper, the authors propose a refined Branch-and-Bound algorithm for affine-transformation based image registration. Given two feature point-sets in two images respectively, the authors first extract a sequence of high-probability matched point-pairs by considering well-defined features. Each resultant point-pair can be regarded as a constraint in the search space of Branch-and-Bound algorithm guiding the search process. The authors carry out Branch-and-Bound search with the constraint of a pair-point selected by using Monte Carlo sampling according to the match measures of point-pairs. If such one cannot lead to correct result, additional candidate is chosen to start another search. High-probability matched point-pairs usually results in fewer loops and the search process is accelerated greatly. Experimental results verify the high efficiency and robustness of the author’s approach.
基金Supported by the National Natural Science Foundation of China (No.60372059) Natural Foundation of Anhui Province (No.03042206).
文摘Color histogram is now widely used in image retrieval. Color histogram-based image retrieval methods are simple and efficient but without considering the spatial distribution information of the color. To overcome the shortcoming of conventional color histogram-based image retrieval methods, an image retrieval method based on Radon Transform (RT) is proposed. In order to reduce the computational complexity, wavelet decomposition is used to compress image data. Firstly, images are decomposed by Mallat algorithm. The low-frequency components are then projected by RT to generate the spatial color feature. Finally the moment feature matrices which are saved along with original images are obtained. Experimental results show that the RT based retrieval is more accurate and efficient than traditional color histogram-based method in case that there are obvious objects in images. Further more, RT based retrieval runs significantly faster than the traditional color histogram methods.
基金supported by the National Natural Science Foundation of China(Nos.61272211 and 61672267)the Open Project Program of the National Laboratory of Pattern Recognition(No.201700022)+1 种基金the China Postdoctoral Science Foundation(No.2015M570413)and the Innovation Project of Undergraduate Students in Jiangsu University(No.16A235)
文摘In dimensional affect recognition, the machine learning methods, which are used to model and predict affect, are mostly classification and regression. However, the annotation in the dimensional affect space usually takes the form of a continuous real value which has an ordinal property. The aforementioned methods do not focus on taking advantage of this important information. Therefore, we propose an affective rating ranking framework for affect recognition based on face images in the valence and arousal dimensional space. Our approach can appropriately use the ordinal information among affective ratings which are generated by discretizing continuous annotations.Specifically, we first train a series of basic cost-sensitive binary classifiers, each of which uses all samples relabeled according to the comparison results between corresponding ratings and a given rank of a binary classifier. We obtain the final affective ratings by aggregating the outputs of binary classifiers. By comparing the experimental results with the baseline and deep learning based classification and regression methods on the benchmarking database of the AVEC 2015 Challenge and the selected subset of SEMAINE database, we find that our ordinal ranking method is effective in both arousal and valence dimensions.
基金supported by the China Scholarship CouncilPostgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX17_0776)the Natural Science Foundation of NUPT(No.NY214039)
文摘A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV color space to get the V channel. Next, the illuminations are respectively estimated by the guided filtering and the variational framework on the V channel and combined into a new illumination by average gradient. The new reflectance is calculated using V channel and the new illumination. Then a new V channel obtained by multiplying the new illumination and reflectance is processed with contrast limited adaptive histogram equalization(CLAHE). Finally, the new image in HSV space is converted back to RGB space to obtain the enhanced image. Experimental results show that the proposed method has better subjective quality and objective quality than existing methods.
基金supported by the National Natural Science Foundation of China(Grant Nos.11702302,51406127&11572331)the Fundamental Research Funds for Central Universities(YWF-16-JCTD-A-05)the Natural Science Foundation of Jiangsu Province(Grant No.BK20140344)
文摘A spatial pyramidal cross-correlation based on interrogation area sub-division is introduced to improve the measurement resolution in particle image velocimetry(PIV). The high-resolution velocity can be achieved with a velocity prediction model via coarse cross-correlation. The prediction formula is deduced from the frequency response of the moving average(MA). The performance of this method was assessed using synthetically generated images of sinusoidal shear flow, two-dimensional vortical cellular flow, and homogeneous turbulence. A real PIV experiment of turbulent boundary layer was used to evaluate the new method. The results indicate that the spatial pyramid cross-correlation can robustly increase the spatial resolution.
