We present a novel human action recognition method based on space-time locally adaptive regressio... more We present a novel human action recognition method based on space-time locally adaptive regression kernels and the matrix cosine similarity measure. The proposed method operates using a single example (e.g., short video clip) of an action of interest to find similar matches. It does not require prior knowledge (learning) about actions being sought; and does not require foreground/background segmentation, or any motion estimation or tracking. Our method is based on the computation of the so-called local steering kernels as space-time descriptors from a query video, which measure the likeness of a voxel to its surroundings. Salient features are extracted from said descriptors and compared against analogous features from the target video. This comparison is done using a matrix generalization of the cosine similarity measure. The algorithm yields a scalar resemblance volume with each voxel here, indicating the likelihood of similarity between the query video and all cubes in the target ...
Frontiers in Optics 2009/Laser Science XXV/Fall 2009 OSA Optics & Photonics Technical Digest, 2009
ABSTRACT I present a nonparametric framework for locally-adaptive signal processing and analysis.... more ABSTRACT I present a nonparametric framework for locally-adaptive signal processing and analysis. Without making strong assumptions about noise/signal models, the framework is applicable to many problems including denoising, upscaling, and object detection in images and video.
ABSTRACT The statistics of natural images play an important role in many image processing tasks. ... more ABSTRACT The statistics of natural images play an important role in many image processing tasks. In particular, statis- tical assumptions about difierences between neighboring pixel values are used extensively in the form of prior information for many diverse applications. The most common assumption is that these pixel difierence values can be described be either a Laplace or Generalized Gaussian distribution. The statistical validity of these two assumptions is investigated formally in this paper by means of Chi-squared goodness of flt tests. The Laplace and Generalized Gaussian distributions are seen to deviate from real images, with the main source of error being the large number of zero and close to zero nearby pixel difierence values. These values correspond to the relatively uniform areas of the image. A mixture distribution is proposed to retain the edge modeling ability of the Laplace or Generalized Gaussian distribution, and to improve the modeling of the efiects introduced by smooth image regions. The Chi-squared tests of flt indicate that the mixture distribution ofiers a signiflcant improvement in flt.
ABSTRACT In this article, the author presents a practical and accessible framework to understand ... more ABSTRACT In this article, the author presents a practical and accessible framework to understand some of the basic underpinnings of these methods, with the intention of leading the reader to a broad understanding of how they interrelate. The author also illustrates connections between these techniques and more classical (empirical) Bayesian approaches. The proposed framework is used to arrive at new insights and methods, both practical and theoretical. In particular, several novel optimality properties of algorithms in wide use such as block-matching and three-dimensional (3-D) filtering (BM3D), and methods for their iterative improvement (or nonexistence thereof) are discussed. A general approach is laid out to enable the performance analysis and subsequent improvement of many existing filtering algorithms. While much of the material discussed is applicable to the wider class of linear degradation models beyond noise (e.g., blur,) to keep matters focused, we consider the problem of denoising here.
... specific areas: 1. We exploit recent advances in the physical design of fast optical systems ... more ... specific areas: 1. We exploit recent advances in the physical design of fast optical systems which enable active imaging and ranging with ballistic light. In this modality, fast bursts of optical energy are transmitted into a ...
A high-resolution ground penetrating radar system was designed to help define the optimal radar p... more A high-resolution ground penetrating radar system was designed to help define the optimal radar parameters needed for the efficient standoff detection of buried and surface- laid antitank mines. The design requirements call for a forward-looking GPR capable of detecting antitank miens in a 5 to 8 meter wide swath, 7 to 60 meters in front of a mobile platform. The
Theoretical and practical limitations usually constrain the achievable resolution of any imaging ... more Theoretical and practical limitations usually constrain the achievable resolution of any imaging device. Super-Resolution (SR) methods are developed through the years to go beyond this limit by acquiring and fusing several low-resolution (LR) images of the same scene, producing a high-resolution (HR) image. The early works on SR, although occasionally mathematically optimal for particular models of data and noise, produced poor results when applied to real images. In this paper, we discuss two of the main issues related to designing a practical SR system, namely reconstruction accuracy and computational efficiency. Reconstruction accuracy refers to the problem of designing a robust SR method applicable to images from different imaging systems. We study a general framework for optimal reconstruction of images from grayscale, color, or color filtered (CFA) cameras. The performance of our proposed method is boosted by using powerful priors and is robust to both measurement (e.g. CCD re...
Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101), 2000
Page 1. AN EFFICIENT WAVELET-BASED ALGORITHM FOR IMAGE SUPERRESOLUTIONNhat Nguyen Scientific Comp... more Page 1. AN EFFICIENT WAVELET-BASED ALGORITHM FOR IMAGE SUPERRESOLUTIONNhat Nguyen Scientific Computing and Computational Mathematics Program Gates Bldg. 2B Stanford, CA 94305 nguyen@sccm.stanford.edu ...
This paper discusses the problem of recovering a planar polygon from its measured complex moments... more This paper discusses the problem of recovering a planar polygon from its measured complex moments. These moments correspond to an indicator function defined over the polygon's support. Previous work on this problem gave necessary and sufficient conditions for such successful recovery process and focused mainly on the case of exact measurements being given. In this paper, we extend these results
Abstract, Super-resolution reconstruction produces one or a set of high-resolution images from a ... more Abstract, Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their short-comings. We
2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010
... 5. Top: plots of PSNR,SSIM, and Q metric versus it-eration number in ISKR denoising, Middle: ... more ... 5. Top: plots of PSNR,SSIM, and Q metric versus it-eration number in ISKR denoising, Middle: a noisy image (std=20), boundary map, selected anisotropic patches (red area), Bottom ... [12] HJSeo and P ... [13] LA Chan, SZ Der, and NM Nasarbadi, Automatic target detection, Ency ...
We present a novel human action recognition method based on space-time locally adaptive regressio... more We present a novel human action recognition method based on space-time locally adaptive regression kernels and the matrix cosine similarity measure. The proposed method operates using a single example (e.g., short video clip) of an action of interest to find similar matches. It does not require prior knowledge (learning) about actions being sought; and does not require foreground/background segmentation, or any motion estimation or tracking. Our method is based on the computation of the so-called local steering kernels as space-time descriptors from a query video, which measure the likeness of a voxel to its surroundings. Salient features are extracted from said descriptors and compared against analogous features from the target video. This comparison is done using a matrix generalization of the cosine similarity measure. The algorithm yields a scalar resemblance volume with each voxel here, indicating the likelihood of similarity between the query video and all cubes in the target ...
Frontiers in Optics 2009/Laser Science XXV/Fall 2009 OSA Optics & Photonics Technical Digest, 2009
ABSTRACT I present a nonparametric framework for locally-adaptive signal processing and analysis.... more ABSTRACT I present a nonparametric framework for locally-adaptive signal processing and analysis. Without making strong assumptions about noise/signal models, the framework is applicable to many problems including denoising, upscaling, and object detection in images and video.
ABSTRACT The statistics of natural images play an important role in many image processing tasks. ... more ABSTRACT The statistics of natural images play an important role in many image processing tasks. In particular, statis- tical assumptions about difierences between neighboring pixel values are used extensively in the form of prior information for many diverse applications. The most common assumption is that these pixel difierence values can be described be either a Laplace or Generalized Gaussian distribution. The statistical validity of these two assumptions is investigated formally in this paper by means of Chi-squared goodness of flt tests. The Laplace and Generalized Gaussian distributions are seen to deviate from real images, with the main source of error being the large number of zero and close to zero nearby pixel difierence values. These values correspond to the relatively uniform areas of the image. A mixture distribution is proposed to retain the edge modeling ability of the Laplace or Generalized Gaussian distribution, and to improve the modeling of the efiects introduced by smooth image regions. The Chi-squared tests of flt indicate that the mixture distribution ofiers a signiflcant improvement in flt.
ABSTRACT In this article, the author presents a practical and accessible framework to understand ... more ABSTRACT In this article, the author presents a practical and accessible framework to understand some of the basic underpinnings of these methods, with the intention of leading the reader to a broad understanding of how they interrelate. The author also illustrates connections between these techniques and more classical (empirical) Bayesian approaches. The proposed framework is used to arrive at new insights and methods, both practical and theoretical. In particular, several novel optimality properties of algorithms in wide use such as block-matching and three-dimensional (3-D) filtering (BM3D), and methods for their iterative improvement (or nonexistence thereof) are discussed. A general approach is laid out to enable the performance analysis and subsequent improvement of many existing filtering algorithms. While much of the material discussed is applicable to the wider class of linear degradation models beyond noise (e.g., blur,) to keep matters focused, we consider the problem of denoising here.
... specific areas: 1. We exploit recent advances in the physical design of fast optical systems ... more ... specific areas: 1. We exploit recent advances in the physical design of fast optical systems which enable active imaging and ranging with ballistic light. In this modality, fast bursts of optical energy are transmitted into a ...
A high-resolution ground penetrating radar system was designed to help define the optimal radar p... more A high-resolution ground penetrating radar system was designed to help define the optimal radar parameters needed for the efficient standoff detection of buried and surface- laid antitank mines. The design requirements call for a forward-looking GPR capable of detecting antitank miens in a 5 to 8 meter wide swath, 7 to 60 meters in front of a mobile platform. The
Theoretical and practical limitations usually constrain the achievable resolution of any imaging ... more Theoretical and practical limitations usually constrain the achievable resolution of any imaging device. Super-Resolution (SR) methods are developed through the years to go beyond this limit by acquiring and fusing several low-resolution (LR) images of the same scene, producing a high-resolution (HR) image. The early works on SR, although occasionally mathematically optimal for particular models of data and noise, produced poor results when applied to real images. In this paper, we discuss two of the main issues related to designing a practical SR system, namely reconstruction accuracy and computational efficiency. Reconstruction accuracy refers to the problem of designing a robust SR method applicable to images from different imaging systems. We study a general framework for optimal reconstruction of images from grayscale, color, or color filtered (CFA) cameras. The performance of our proposed method is boosted by using powerful priors and is robust to both measurement (e.g. CCD re...
Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101), 2000
Page 1. AN EFFICIENT WAVELET-BASED ALGORITHM FOR IMAGE SUPERRESOLUTIONNhat Nguyen Scientific Comp... more Page 1. AN EFFICIENT WAVELET-BASED ALGORITHM FOR IMAGE SUPERRESOLUTIONNhat Nguyen Scientific Computing and Computational Mathematics Program Gates Bldg. 2B Stanford, CA 94305 nguyen@sccm.stanford.edu ...
This paper discusses the problem of recovering a planar polygon from its measured complex moments... more This paper discusses the problem of recovering a planar polygon from its measured complex moments. These moments correspond to an indicator function defined over the polygon's support. Previous work on this problem gave necessary and sufficient conditions for such successful recovery process and focused mainly on the case of exact measurements being given. In this paper, we extend these results
Abstract, Super-resolution reconstruction produces one or a set of high-resolution images from a ... more Abstract, Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their short-comings. We
2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010
... 5. Top: plots of PSNR,SSIM, and Q metric versus it-eration number in ISKR denoising, Middle: ... more ... 5. Top: plots of PSNR,SSIM, and Q metric versus it-eration number in ISKR denoising, Middle: a noisy image (std=20), boundary map, selected anisotropic patches (red area), Bottom ... [12] HJSeo and P ... [13] LA Chan, SZ Der, and NM Nasarbadi, Automatic target detection, Ency ...
Uploads
Papers