To become robust, a tracking algorithm must be able to support uncertainty and ambiguity often inherently present in the data in form of occlusion and clutter. This comes usually at the price of more demanding computations. Sampling methods, such as the popular particle filter, accommodate this capability and provide a means of controlling the computational trade-off by adapting their resolution. This paper presents a method for adapting resolution on-the-fly to current demands. The key idea is to select the number of samples necessary to populate the high probability regions with a predefined density. The scheme then allocates more particles when uncertainty is high while saving resources otherwise. The resulting tracker propagates compact while consistent representations and enables for reliable real time operation otherwise compromised.
{"title":"An information theoretic rule for sample size adaptation in particle filtering","authors":"O. Lanz","doi":"10.1109/ICIAP.2007.23","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.23","url":null,"abstract":"To become robust, a tracking algorithm must be able to support uncertainty and ambiguity often inherently present in the data in form of occlusion and clutter. This comes usually at the price of more demanding computations. Sampling methods, such as the popular particle filter, accommodate this capability and provide a means of controlling the computational trade-off by adapting their resolution. This paper presents a method for adapting resolution on-the-fly to current demands. The key idea is to select the number of samples necessary to populate the high probability regions with a predefined density. The scheme then allocates more particles when uncertainty is high while saving resources otherwise. The resulting tracker propagates compact while consistent representations and enables for reliable real time operation otherwise compromised.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129119062","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}
This paper presents a subspace algorithm called block independent component analysis (B-ICA) for face recognition. Unlike the traditional ICA, in which the whole face image is stretched into a vector before calculating the independent components (ICs), B-ICA partitions the facial images into blocks and takes the block as the training vector. Since the dimensionality of the training vector in B-ICA is much smaller than that in traditional ICA, it can reduce the face recognition error caused by the dilemma in ICA, i.e. the number of available training samples is greatly less than that of the dimension of training vector. Experiments on the well-known Yale and AR databases validate that the B-ICA can achieve higher recognition accuracy than ICA and enhanced ICA (EICA).
{"title":"Block Independent Component Analysis for Face Recognition","authors":"Lei Zhang, Quanxue Gao, David Zhang","doi":"10.1109/ICIAP.2007.38","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.38","url":null,"abstract":"This paper presents a subspace algorithm called block independent component analysis (B-ICA) for face recognition. Unlike the traditional ICA, in which the whole face image is stretched into a vector before calculating the independent components (ICs), B-ICA partitions the facial images into blocks and takes the block as the training vector. Since the dimensionality of the training vector in B-ICA is much smaller than that in traditional ICA, it can reduce the face recognition error caused by the dilemma in ICA, i.e. the number of available training samples is greatly less than that of the dimension of training vector. Experiments on the well-known Yale and AR databases validate that the B-ICA can achieve higher recognition accuracy than ICA and enhanced ICA (EICA).","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130702755","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}
M. Mesmoudi, E. Danovaro, L. Floriani, Umberto Port
Curvature is one of the most relevant notions that links the metric properties of a surface to its geometry and to its topology (Gauss-Bonnet theorem). In the literature, a variety of approaches exist to compute curvatures in the discrete case. Several techniques are computationally intensive or suffer from convergence problems. In this paper, we discuss the notion of concentrated curvature, introduced by Troyanov [24]. We discuss properties of this curvature and compare with a widely-used technique that estimates the Gaussian curvatures on a triangulated surface. We apply our STD method [13] for terrain segmentation to segment a surface by using different curvature approaches and we illustrate our comparisons through examples.
{"title":"Surface Segmentation through Concentrated Curvature","authors":"M. Mesmoudi, E. Danovaro, L. Floriani, Umberto Port","doi":"10.1109/ICIAP.2007.123","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.123","url":null,"abstract":"Curvature is one of the most relevant notions that links the metric properties of a surface to its geometry and to its topology (Gauss-Bonnet theorem). In the literature, a variety of approaches exist to compute curvatures in the discrete case. Several techniques are computationally intensive or suffer from convergence problems. In this paper, we discuss the notion of concentrated curvature, introduced by Troyanov [24]. We discuss properties of this curvature and compare with a widely-used technique that estimates the Gaussian curvatures on a triangulated surface. We apply our STD method [13] for terrain segmentation to segment a surface by using different curvature approaches and we illustrate our comparisons through examples.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130297592","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}
In this paper we present the results of a two-years research project on automatic people counting in public crowded environments. The aim of the proposed system is to estimate the number of people passing through a gate in a public area such as a metro or a railway station. The problem is particularly challenging due to both the presence of crowd which makes it difficult the use of previous systems based on detection of isolated passengers and to the high level of statistic accuracy requested by traffic monitoring applications (error rate less then 5%).
{"title":"A Statistical Method for People Counting in Crowded Environments","authors":"M. Bozzoli, L. Cinque, E. Sangineto","doi":"10.1109/ICIAP.2007.17","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.17","url":null,"abstract":"In this paper we present the results of a two-years research project on automatic people counting in public crowded environments. The aim of the proposed system is to estimate the number of people passing through a gate in a public area such as a metro or a railway station. The problem is particularly challenging due to both the presence of crowd which makes it difficult the use of previous systems based on detection of isolated passengers and to the high level of statistic accuracy requested by traffic monitoring applications (error rate less then 5%).","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130870599","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}
Marco Aiello, F. Andreozzi, E. Catanzariti, F. Isgrò, M. Santoro
Over the last years computer vision researchers have shown great interest for the so called spectral clustering, where the data are clustered analysing the first few eigenvectors (i.e., the ones relative to the first eigenvalues) of a the Laplacian matrix, derived directly from the data-set. Note that for the purpose of data clustering the eigenvectors need not to be determined accurately. When clustering (segmenting) images the dimension of this matrix is large (e.g., an image as small as 100 times 100 results in a 10000 times 10000 matrix), and standard diagonalisation algorithms such Lanczos, necessary for determining the eigenvectors, do require a certain number of iterations: typically in the order of radicn step for n times n matrices, and may take some iterations for getting close to the solutions. Here we report the first attempt using a recent diagonalisation algorithm (named APL) borrowed from the nuclear physics literature, that, among other properties, has the main advantage of obtaining in a small number of iteration steps eigenvectors, that even if not accurate, are good enough for performing a reasonable segmentation. In this sense we talk of fast convergence of spectral clustering. The experimental results obtained support this claim, and open the way to further work exploiting further detail of the algorithm not included in this study.
{"title":"Fast convergence for spectral clustering","authors":"Marco Aiello, F. Andreozzi, E. Catanzariti, F. Isgrò, M. Santoro","doi":"10.1109/ICIAP.2007.66","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.66","url":null,"abstract":"Over the last years computer vision researchers have shown great interest for the so called spectral clustering, where the data are clustered analysing the first few eigenvectors (i.e., the ones relative to the first eigenvalues) of a the Laplacian matrix, derived directly from the data-set. Note that for the purpose of data clustering the eigenvectors need not to be determined accurately. When clustering (segmenting) images the dimension of this matrix is large (e.g., an image as small as 100 times 100 results in a 10000 times 10000 matrix), and standard diagonalisation algorithms such Lanczos, necessary for determining the eigenvectors, do require a certain number of iterations: typically in the order of radicn step for n times n matrices, and may take some iterations for getting close to the solutions. Here we report the first attempt using a recent diagonalisation algorithm (named APL) borrowed from the nuclear physics literature, that, among other properties, has the main advantage of obtaining in a small number of iteration steps eigenvectors, that even if not accurate, are good enough for performing a reasonable segmentation. In this sense we talk of fast convergence of spectral clustering. The experimental results obtained support this claim, and open the way to further work exploiting further detail of the algorithm not included in this study.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130912635","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}
This paper studies the performance of various scale- invariant detectors in the context of feature matching. In particular, we propose an implementation of the Hessian-Laplace operator that we called scale-interpolated Hessian-Laplace. This research also proposes to use Haar descriptors which are derived from the Haar wavelet transform. It offers the advantage of being computationally inexpensive and smaller in size when compared to other descriptors.
{"title":"Performance Evaluation of Scale-Interpolated Hessian-Laplace and Haar Descriptors for Feature Matching","authors":"Akshay Bhatia, R. Laganière, G. Roth","doi":"10.1109/ICIAP.2007.102","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.102","url":null,"abstract":"This paper studies the performance of various scale- invariant detectors in the context of feature matching. In particular, we propose an implementation of the Hessian-Laplace operator that we called scale-interpolated Hessian-Laplace. This research also proposes to use Haar descriptors which are derived from the Haar wavelet transform. It offers the advantage of being computationally inexpensive and smaller in size when compared to other descriptors.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125971656","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}
In this paper, we propose novel blur and similarity transform (i.e. rotation, scaling and translation) invariant features for the recognition of objects in images. The features are based on blur invariant forms of the log-polar sampled phase-only bispectrum and are invariant to centrally symmetric blur, including linear motion and out of focus blur. An additional advantage of using the phase-only bispectrum is the invariance to uniform illumination changes. According to our knowledge, the invariants of this paper are the first blur and similarity transform invariants in the Fourier domain. We have compared our features to the blur invariants based on complex image moments using simulated and real data. The moment invariants have not been evaluated earlier in the case of similarity transform. The results show that our invariants can recognize objects better in the presence of noise.
{"title":"A Method for Blur and Similarity Transform Invariant Object Recognition","authors":"Ville Ojansivu, J. Heikkilä","doi":"10.1109/ICIAP.2007.10","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.10","url":null,"abstract":"In this paper, we propose novel blur and similarity transform (i.e. rotation, scaling and translation) invariant features for the recognition of objects in images. The features are based on blur invariant forms of the log-polar sampled phase-only bispectrum and are invariant to centrally symmetric blur, including linear motion and out of focus blur. An additional advantage of using the phase-only bispectrum is the invariance to uniform illumination changes. According to our knowledge, the invariants of this paper are the first blur and similarity transform invariants in the Fourier domain. We have compared our features to the blur invariants based on complex image moments using simulated and real data. The moment invariants have not been evaluated earlier in the case of similarity transform. The results show that our invariants can recognize objects better in the presence of noise.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127724319","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}
This paper introduces a vision based algorithm that detects and localizes ahead vehicles elaborating images taken by a stereo camera installed on an intelligent vehicle. The algorithm is based on the analysis of stereo images, estimating the ground plane by least square fitting of disparity data, and segmenting the obstacles by a rule based split/merge strategy. Quantitative experiments on complex real world sequences validate the approach. The method is demonstrated to operate in real-time.
{"title":"Localization of ahead vehicles with on-board stereo cameras","authors":"M. Zanin","doi":"10.1109/ICIAP.2007.86","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.86","url":null,"abstract":"This paper introduces a vision based algorithm that detects and localizes ahead vehicles elaborating images taken by a stereo camera installed on an intelligent vehicle. The algorithm is based on the analysis of stereo images, estimating the ground plane by least square fitting of disparity data, and segmenting the obstacles by a rule based split/merge strategy. Quantitative experiments on complex real world sequences validate the approach. The method is demonstrated to operate in real-time.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122363660","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}
Giuseppe Boccignone, A. Marcelli, Paolo Napoletano, M. Ferraro
We present a probabilistic model for motion estimation in which motion characteristics are inferred on the basis of a finite mixture of motion models. The model is graphically represented in the form of a pairwise Markov random field network upon which a Loopy belief propagation algorithm is exploited to perform inference. Experiments on different video clips are presented and discussed.
{"title":"Motion Estimation via Belief Propagation","authors":"Giuseppe Boccignone, A. Marcelli, Paolo Napoletano, M. Ferraro","doi":"10.1109/ICIAP.2007.88","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.88","url":null,"abstract":"We present a probabilistic model for motion estimation in which motion characteristics are inferred on the basis of a finite mixture of motion models. The model is graphically represented in the form of a pairwise Markov random field network upon which a Loopy belief propagation algorithm is exploited to perform inference. Experiments on different video clips are presented and discussed.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121036814","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}
A novel objective full-reference image quality assessment metric based on symmetric geometric moments (SGM) is proposed. SGM is used to represent the structural information in the reference and test images. The reference and test images are divided into (8 times 8) blocks and the SGM up to fourth order for each block is computed. SGM of the corresponding blocks of the reference and test images are used to form the correlation index or quality metric of each block. The correlation index of the test image is then obtained by taking the average of all blocks. The performance of the proposed metric is validated through subjective evaluation by comparing with objective methods (PSNR and MSSIM) on a database of 174 Gaussian blurred images. The proposed metric performs better than PSNR and MSSIM by providing larger correlation coefficients and smaller errors after nonlinear regression fitting.
{"title":"Quality Assessment of Gaussian Blurred Images Using Symmetric Geometric Moments","authors":"Chong-Yaw Wee, R. Paramesran, R. Mukundan","doi":"10.1109/ICIAP.2007.104","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.104","url":null,"abstract":"A novel objective full-reference image quality assessment metric based on symmetric geometric moments (SGM) is proposed. SGM is used to represent the structural information in the reference and test images. The reference and test images are divided into (8 times 8) blocks and the SGM up to fourth order for each block is computed. SGM of the corresponding blocks of the reference and test images are used to form the correlation index or quality metric of each block. The correlation index of the test image is then obtained by taking the average of all blocks. The performance of the proposed metric is validated through subjective evaluation by comparing with objective methods (PSNR and MSSIM) on a database of 174 Gaussian blurred images. The proposed metric performs better than PSNR and MSSIM by providing larger correlation coefficients and smaller errors after nonlinear regression fitting.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"6 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128820664","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：