Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300974
V. Girondel, A. Caplier, L. Bonnaud
We present an algorithm that can track multiple persons and their faces simultaneously in a video sequence, even if they are completely occluded from the camera's point of view. The algorithm is based on the detection and tracking of person masks and their faces. Face localization uses skin detection based on color information with an adaptive thresholding. In order to handle occlusions, a Kalman filter is defined for each person that allows the prediction of the person bounding box, of the face bounding box and of its speed. In case of incomplete measurements (for instance, in case of partial occlusion), a partial Kalman filtering is done. Several results show the efficiency of this method. This algorithm allows real time processing.
{"title":"Real time tracking of multiple persons by Kalman filtering and face pursuit for multimedia applications","authors":"V. Girondel, A. Caplier, L. Bonnaud","doi":"10.1109/IAI.2004.1300974","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300974","url":null,"abstract":"We present an algorithm that can track multiple persons and their faces simultaneously in a video sequence, even if they are completely occluded from the camera's point of view. The algorithm is based on the detection and tracking of person masks and their faces. Face localization uses skin detection based on color information with an adaptive thresholding. In order to handle occlusions, a Kalman filter is defined for each person that allows the prediction of the person bounding box, of the face bounding box and of its speed. In case of incomplete measurements (for instance, in case of partial occlusion), a partial Kalman filtering is done. Several results show the efficiency of this method. This algorithm allows real time processing.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121950241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The article describes a new algorithm for the restoration of solar radio images. The technique is based on the use of adaptive regularization procedures that incorporate the k-means clustering algorithm over local roughness measures. Experimental results involving simulated and real images are described. The results demonstrate the superiority of the adaptive procedure compared to conventional regularization, both from the visual and numerical points of view.
{"title":"Restoration of solar radio images using adaptive regularization techniques based on clustering","authors":"Will Machado, N. Mascarenhas, J. Costa","doi":"10.1109/ICPR.2004.907","DOIUrl":"https://doi.org/10.1109/ICPR.2004.907","url":null,"abstract":"The article describes a new algorithm for the restoration of solar radio images. The technique is based on the use of adaptive regularization procedures that incorporate the k-means clustering algorithm over local roughness measures. Experimental results involving simulated and real images are described. The results demonstrate the superiority of the adaptive procedure compared to conventional regularization, both from the visual and numerical points of view.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121428288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300960
I. Stuke, T. Aach, E. Barth, C. Mota
Estimation of local orientation in images is often posed as the task of finding the minimum variance axis in a local neighborhood. The solution is given as the eigenvector belonging to the smaller eigenvalue of a 2/spl times/2 tensor. Ideally, the tensor is rank-deficient, i.e., the smaller eigenvalue is zero. A large minimal eigenvalue signals the presence of more than one local orientation. We describe a framework for estimating such superimposed orientations. Our analysis of superimposed orientations is based on the eigensystem analysis of a suitably extended tensor. We show how to carry out the eigensystem analysis efficiently using tensor invariants. Unlike in the single orientation case, the eigensystem analysis does not directly yield the orientations, rather, it provides so-called mixed orientation parameters. We therefore show how to decompose the mixed orientation parameters into the individual orientations. These, in turn, allow the superimposed patterns to be separated.
{"title":"Analysing superimposed oriented patterns","authors":"I. Stuke, T. Aach, E. Barth, C. Mota","doi":"10.1109/IAI.2004.1300960","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300960","url":null,"abstract":"Estimation of local orientation in images is often posed as the task of finding the minimum variance axis in a local neighborhood. The solution is given as the eigenvector belonging to the smaller eigenvalue of a 2/spl times/2 tensor. Ideally, the tensor is rank-deficient, i.e., the smaller eigenvalue is zero. A large minimal eigenvalue signals the presence of more than one local orientation. We describe a framework for estimating such superimposed orientations. Our analysis of superimposed orientations is based on the eigensystem analysis of a suitably extended tensor. We show how to carry out the eigensystem analysis efficiently using tensor invariants. Unlike in the single orientation case, the eigensystem analysis does not directly yield the orientations, rather, it provides so-called mixed orientation parameters. We therefore show how to decompose the mixed orientation parameters into the individual orientations. These, in turn, allow the superimposed patterns to be separated.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126337961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300938
Yung-Hsiang Lu, E. Delp
We describe some of the research issues and challenges in image-based location awareness and navigation. We describe two systems being developed at Purdue University as testbeds for our ideas. The main system architecture combines image processing, mobility, wireless communication, and location awareness.
{"title":"Image-based location awareness and navigation: who cares?","authors":"Yung-Hsiang Lu, E. Delp","doi":"10.1109/IAI.2004.1300938","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300938","url":null,"abstract":"We describe some of the research issues and challenges in image-based location awareness and navigation. We describe two systems being developed at Purdue University as testbeds for our ideas. The main system architecture combines image processing, mobility, wireless communication, and location awareness.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129508532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300943
C. Grassl, T. Zinßer, H. Niemann
The main aim of our work is to improve the accuracy of the hyperplane tracker of F. Jurie and M. Dhome (see IEEE Trans. Pattern Anal. and Machine Intelligence, vol.24, no.7, p.996-1000, 2002) for real-time template matching. As the computation time of the initialization of the algorithm depends on the number of points used for estimating the motion of the template, only a subset of points in the tracked template is considered. Traditionally, this subset is determined at random. We present three different methods for selecting points better suited for the hyperplane tracker. We also propose to incorporate color information by working with eigenintensities instead of gray-level intensities, which can greatly improve the estimation accuracy, but only entails a slight increase in computation time. We have carefully evaluated the performance of the proposed methods in experiments with real image sequences.
{"title":"Efficient hyperplane tracking by intelligent region selection","authors":"C. Grassl, T. Zinßer, H. Niemann","doi":"10.1109/IAI.2004.1300943","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300943","url":null,"abstract":"The main aim of our work is to improve the accuracy of the hyperplane tracker of F. Jurie and M. Dhome (see IEEE Trans. Pattern Anal. and Machine Intelligence, vol.24, no.7, p.996-1000, 2002) for real-time template matching. As the computation time of the initialization of the algorithm depends on the number of points used for estimating the motion of the template, only a subset of points in the tracked template is considered. Traditionally, this subset is determined at random. We present three different methods for selecting points better suited for the hyperplane tracker. We also propose to incorporate color information by working with eigenintensities instead of gray-level intensities, which can greatly improve the estimation accuracy, but only entails a slight increase in computation time. We have carefully evaluated the performance of the proposed methods in experiments with real image sequences.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132399928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300947
B. Shah, P. Dhatric, Vijay V. Raghavan
The process of selecting a small number of representative colors from an image of higher color resolution is called color image quantization. A well-known problem in quantizing images is to select the best representative colors that not only reduce the quantization error, but also account for the perception of human vision. The technique we propose effectively handles this problem by using the variation of colors in different regions of an image, in addition to the use of the color histogram, for effective perception and quantization. We introduce the property of inverse image frequency (IIF) for computing the representative colors of an image. IIF is based on the observation that colors within a color subset having non-uniform frequency distribution across the different regions of an image have better discriminating properties than those having uniform distribution. Our approach to incorporate the information derived from IIF can be combined with any standard quantization algorithm. The results show that our approach quantizes an image more effectively than using just the well-known median cut algorithm.
{"title":"Using inverse image frequency for perception-based color image quantization","authors":"B. Shah, P. Dhatric, Vijay V. Raghavan","doi":"10.1109/IAI.2004.1300947","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300947","url":null,"abstract":"The process of selecting a small number of representative colors from an image of higher color resolution is called color image quantization. A well-known problem in quantizing images is to select the best representative colors that not only reduce the quantization error, but also account for the perception of human vision. The technique we propose effectively handles this problem by using the variation of colors in different regions of an image, in addition to the use of the color histogram, for effective perception and quantization. We introduce the property of inverse image frequency (IIF) for computing the representative colors of an image. IIF is based on the observation that colors within a color subset having non-uniform frequency distribution across the different regions of an image have better discriminating properties than those having uniform distribution. Our approach to incorporate the information derived from IIF can be combined with any standard quantization algorithm. The results show that our approach quantizes an image more effectively than using just the well-known median cut algorithm.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133600443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300951
Yi-Ming Wu, C. Fuh, Jui-Pin Hsu
The paper proposes a method to reduce the problems of blurred-edge effects and color alias effects in the color interpolation for a single charge-coupled device (CCD) color camera. We first introduce the background, and review some traditional interpolation methods. Then we explain our proposed methods as well as the results. Conclusions and future works are addressed.
{"title":"Color interpolation for single CCD color camera","authors":"Yi-Ming Wu, C. Fuh, Jui-Pin Hsu","doi":"10.1109/IAI.2004.1300951","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300951","url":null,"abstract":"The paper proposes a method to reduce the problems of blurred-edge effects and color alias effects in the color interpolation for a single charge-coupled device (CCD) color camera. We first introduce the background, and review some traditional interpolation methods. Then we explain our proposed methods as well as the results. Conclusions and future works are addressed.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114056921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300966
D. Zhou, V. DeBrunner, J. Havlicek
Xu, Y. et al. (see IEEE T-IP, vol.3, no.6, 1994) proposed an effective wavelet based spatially selective denoising algorithm. The performance of the algorithm depends on the noise power estimation. Pan, Q. et al. (see IEEE T-SP, vol.47, no.12, 1999) tried to improve the performance via a small modification. However, our simulation shows that both of these methods are sensitive to noise estimation. We analyze the sensitivity of these two methods and introduce a new spatially selective noise filter based on the UDWT (undecimated wavelet transform) that uses spatial correlation thresholding. Theoretic analysis and simulations show our algorithm improves the denoising effect. They also show that our proposed method is robust to errors in the noise power estimate. Because our approach is robust, we can relax the requirements for the estimation of the threshold without sacrificing performance, and so our method is more computationally efficient. We also put some perspective on the impact of employing nonorthogonal representations. Simulation results show the effectiveness of our proposed algorithm.
{"title":"A spatially selective filter based on the undecimated wavelet transform that is robust to noise estimation error","authors":"D. Zhou, V. DeBrunner, J. Havlicek","doi":"10.1109/IAI.2004.1300966","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300966","url":null,"abstract":"Xu, Y. et al. (see IEEE T-IP, vol.3, no.6, 1994) proposed an effective wavelet based spatially selective denoising algorithm. The performance of the algorithm depends on the noise power estimation. Pan, Q. et al. (see IEEE T-SP, vol.47, no.12, 1999) tried to improve the performance via a small modification. However, our simulation shows that both of these methods are sensitive to noise estimation. We analyze the sensitivity of these two methods and introduce a new spatially selective noise filter based on the UDWT (undecimated wavelet transform) that uses spatial correlation thresholding. Theoretic analysis and simulations show our algorithm improves the denoising effect. They also show that our proposed method is robust to errors in the noise power estimate. Because our approach is robust, we can relax the requirements for the estimation of the threshold without sacrificing performance, and so our method is more computationally efficient. We also put some perspective on the impact of employing nonorthogonal representations. Simulation results show the effectiveness of our proposed algorithm.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114146201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300949
B. Romaniuk, V. Guilloux, M. Desvignes, M. Deshayes
We deal with the problem of partially observed objects. These objects are defined by sets of points and their shape variations are represented by a statistical model. We present two models: a linear model based on PCA and a non-linear model based on KPCA (kernel PCA). The present work attempts to localize non visible parts of an object from visible parts and from the model, explicitly. using the variability represented by the model. Both are applied to the cephalometric problem with good results.
{"title":"Partially observed objects localization with PCA and KPCA models","authors":"B. Romaniuk, V. Guilloux, M. Desvignes, M. Deshayes","doi":"10.1109/IAI.2004.1300949","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300949","url":null,"abstract":"We deal with the problem of partially observed objects. These objects are defined by sets of points and their shape variations are represented by a statistical model. We present two models: a linear model based on PCA and a non-linear model based on KPCA (kernel PCA). The present work attempts to localize non visible parts of an object from visible parts and from the model, explicitly. using the variability represented by the model. Both are applied to the cephalometric problem with good results.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114278319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-28DOI: 10.1109/IAI.2004.1300969
M. Benjelloun, R. Terán
Our goal is the development of a visual computer tool to study the motion induced in the abdomen by breathing. Our inputs are X-ray images, which are acquired in normal inspiration and normal expiration positions. Our researches lead to the conception of a software program that allows an accurate, complete and efficient analysis of visceral dynamics.
{"title":"Visceral dynamic computing","authors":"M. Benjelloun, R. Terán","doi":"10.1109/IAI.2004.1300969","DOIUrl":"https://doi.org/10.1109/IAI.2004.1300969","url":null,"abstract":"Our goal is the development of a visual computer tool to study the motion induced in the abdomen by breathing. Our inputs are X-ray images, which are acquired in normal inspiration and normal expiration positions. Our researches lead to the conception of a software program that allows an accurate, complete and efficient analysis of visceral dynamics.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114521786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：