Projects

A Hemispherical Imaging Camera

C. Gao, H. Hua, N. Ahuja

| Demo | Details | Back to Theme |

High-Resolution Double Pyramid Panoramic Cameras

K. Tan, H. Hua and N. Ahuja

Uses mirror pyramids to virtually collocate a number of physical cameras to obtain a visual field having a width of 360 degrees, and a height same as, or twice, that of the individual cameras. One or more panoramic images may be acquired in parallel. Each panoramic image is acquired at video rate, and has uniform resolution and a single apparent viewpoint.

1. Hong Hua, Narendra Ahuja, A High-Resolution Panoramic Camera , Computer Vision and Pattern Recognition ( CVPR'01) - Volume 1, pp. 960 ~ 967 Full Text (890KB)
2. K.-H. Tan, H. Hua and N. Ahuja, Multiview Panoramic Cameras Using Mirror Pyramids, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 6, June 2004. Full Text
3. K.-H. Tan, H. Hua and N. Ahuja, Multiview Mirror Pyramid-based Panoramic Cameras, Proceedings of the IEEE Workshop on Omnidirectional Vision (Omnivis) , June 2002, Copenhagen, Denmark, 87-93.

| Demo | Details | Back to Theme |

A Single Lens Depth Camera

C. Gao, N. Ahuja

A visual depth sensor composed of a single camera and a transparent plate rotating about the optical axis in front of the camera. Depth is estimated from the disparities of scene points observed in multiple images acquired viewing through the rotating the plate

1. Chunyu Gao, Narendra Ahuja, Single camera stereo using planar parallel plate , Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4, pp. 108-111 08, 2004, Cambridge UK Full Text (68 KB)
2. Chunyu Gao and Narendra Ahuja, "A Refractive Camera for Acquiring Stereo and Super-resolution  Images", Computer Vision and Pattern Recognition, IEEE Computer
   Society Conference on, Volume 2,  17-22 June 2006 Page(s):2316 - 2323

| Demo | Details | Back to Theme |

An Omnidirectional Stereo Vision System Using a Single Camera

S. Yi, N. Ahuja

A new omnidirectional stereo imaging system that uses a concave lens and a convex mirror to produce a stereo pair of images on the sensor of a conventional camera.

1. Sooyeong Yi, Narendra Ahuja, "An Omnidirectional Stereo System Using a Single Camera", 18th International Conference on (ICPR'06), 2006, Hong Kong, China Full Text (252 KB)
2. Sooyeong Yi, Narendra Ahuja, "A Novel Omnidirectional Stereo System Using a Single Camera", International Conference on Image Analysis and Recognition (ICIAR), 2006

| Demo | Details | Back to Theme |

Omnifocus Imaging Using Graph Cuts

N. Xu, N. Ahuja

Given a set of images captured with different focus settings but from the same viewpoint, develop a focus measure that is robust near occlusion boundaries and the amount of texture present, and output an omnifocus image with all pixels in focus.

1. Ning Xu and Narendra Ahuja. Generating Omnifocus Images Using Graph Cuts and a New Focus Measure. Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4. pp 697-700, 08, 2004 Cambridge UK. Full Text

| Demo | Details | Back to Theme |

Dense Stereo Mapping Using Kernel Maximum Likelihood Estimation

 A. Jagmohan, M. Singh, H. Arora, N. Ahuja

A robust stereo matching algorithm using kernel representation of the probability density functions (pdf's) of the sources that generate the stereoscopic images. Matching is done using either a Maximum Likelihood framework or using correlation in the pdf domain and an MRF prior to model the disparity function.

1. A. Jagmohan, M. Singh, and N. Ahuja, Dense Two View Stereo Matching Using Kernel Maximum Likelihood Estimation, Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3, pp. 28-31, 08, 2004 Cambridge UK IEEE Reference
2. M. Singh, H. Arora and N. Ahuja, Robust Registration and Tracking Using Kernel Density Correlation, 2004 Conference on Computer Vision and Pattern Recognition Workshop on Image and Video Registration, CVPRW'04 Volume 11, p. 174, 06 27 - 07 02, 2004, Washington, D.C., USA Full Text

| Demo | Details | Back to Theme |

3D Surface from Multiple Views

N. Xu, T. Yu, N. Ahuja

Given multiple calibrated pictures of a real world object captured from different viewpoints, reconstruct a three-dimensional model of the object.

1. Tianli Yu, Ning Xu and Narendra Ahuja, Reconstructing a Dynamic Surface from Video Sequences Using Graph Cuts in 4D Space-Time, Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2, pp. 245-248 08, 2004 Cambridge UK Full Text
2. Ning Xu, Tianli Yu and Narendra Ahuja. Shape from color consistency using node cut. In Proceedings of Asian Conference on Computer Vision, Jeju Island, Korea. January 2004. Abstract and Full Text
3. Ning Xu and Narendra Ahuja. A Three-view Matching Algorithm Considering Foreshortening Effects. In Proceedings of International Conference on Computer Vision, Pattern Recognition and Image Processing, pp. 635-638, Cary, NC. September 2003. Abstract and Full Text

| Demo | Details | Back to Theme |

Non-Lambertian Surface Reconstruction and Reflectance Modeling.

T. Yu, N. Xu, N. Ahuja

Non-lambertian surfaces causes difficulties for many stereo systems. We describe methods to recover both 3D surface shape and reflectance models of an object from multiple views. We use an iterative method, based on multi-view shape from shading, to estimate shape and reflectance models. The estimated models can be used to generate objects in new views and under new lighting conditions using computer graphics techniques.

1. Tianli Yu, Ning Xu and Narendra Ahuja, Recovering Shape and Reflectance Model of Non-Lambertian Objects from Multiple Views, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) Volume 2, pp. 226-233, 06 27 - 07 02, 2004, Washington, D.C., USAFull Text
2. Tianli Yu, Ning Xu and Narendra Ahuja, Shape and View Independent Reflectance Map from Multiple Views, ECCV 2004, LNCS 3024, pp. 602-616, May 11-14, Prague. Full Text

| Demo | Details | Back to Theme |

Object Tracking and Registration

M. Singh, H. Arora, N. Ahuja

The source and target data are modeled using nonparametric density estimators. They are then registered using a deformable, parametric transformation model. The registration algorithm is based on a novel variational optimization algorithm. The algorithm can be used for image alignment, object registration and tracking.

1. M. Singh, H. Arora and N. Ahuja, Robust Registration and Tracking Using Kernel Density Correlation, 2nd IEEE Workshop on Image and Video Registration (held with CVPR), 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 11, p. 174, 2004, Washington, D.C., USA2004. Full Text

| Demo | Details | Back to Theme |

Estimation and Segmentation of Images Using Parametric Image Models

M. Singh, H. Arora, N. Ahuja

A Maximum Likelihood parameter estimation framework using a linear parametric image model with additive noise. Noise density is represented using kernel pdf estimators. The resulting estimator, the KML Estimator, is a redescending M-Estimator. This novel approach provides a link between parametric image models and nonparametric pdf models for additive noise.

1. M. Singh, H. Arora and N. Ahuja, "A Robust Probabilistic Estimation Framework for Parametric Image Models", European Conference on Computer Vision, LNCS 3021, pp. 508-522, 2004. Full Text

| Demo | Details | Back to Theme |

Bandwidth Selection for Kernel Density Estimators

M. Singh, N. Ahuja

A regression-based model which admits a realistic framework for automatically choosing bandwidth parameters which minimizes a global error criterion. This is used for automatic segmentation of images at any input resolution scale (for e.g., the wavelet decomposition scale).

1. M. Singh and N. Ahuja, "Regression based Bandwidth Selection for Segmentation using Parzen Windows", in Ninth IEEE International Conference in Computer Vision, Proceedings, vol. 1, pp. 2-9, Oct. 2003, Nice, France. Full Text
2. M. Singh and N. Ahuja, Mean-Shift Segmentation with Wavelet-based Bandwidth Selection, IEEE Workshop on Applications in Computer Vision, pp. 43-50, Dec. 3-4, 2002, Florida. Full Text

| Demo | Details | Back to Theme |

Shape Regularized Active Contour for Medical Image Segmentation

T. Yu, N. Ahuja

A robust image segmentation methods to allow automatic analysis of X-ray images. Our algorithm learns what shape to look for in the new image from a set of training examples. The resulting algorithm has excellent robustness to noise and distracting structures in medical images, and is able to segment objects with large (nonlinear) shape variations.

1. Tianli Yu, Jiebo Luo and Narendra Ahuja, Shape Regularized Active Contour using Iterative Global Search and Local Optimization, accepted by CVPR 2005, June 20-26 2005, San Diego, CA, USA Full Text (2.0 MB)
2. Tianli Yu, Jiebo Luo, Amit Singhal, and Narendra Ahuja, Shape regularized active contour based on dynamic programming for anatomical structure segmentation, SPIE Medical Imaging 2005, February 12-17 2005, San Diego, CA, USA Full Text (4.3 MB)

| Demo | Details | Back to Theme |

An algorithm for Image Segmentation using a novel ramp discontinuity region model. The regions are modelled as homogeneous contiguous portions in an image, surrounded by a slowly varying ramp discontinuity. Ramp discontinuities usually arises in real images due to blurring of edges and existing algorithm for segmentaiton fail at these edges.
 

1. Himanshu Arora, Narendra Ahuja, Analysis of ramp discontinuity model for multiscale image segmentation. To appear in ICPR(1), 2006.

| Demo | Details | Back to Theme |

1. S. Todorovic and N. Ahuja, 3D texture classification using the belief net of a segmentation tree, in Proc. 18th Int. Conf. Pattern Recognition (ICPR 2006), Hong Kong, China, 2006. Full Text

| Demo | Details | Back to Theme |

Predictive Multiple Description Coding using Wyner-Ziv Codes

A. Jagmohan, A. Sehgal, N. Ahuja

Two-channel predictive multiple description coding is posed as a variant of the Wyner-Ziv coding problem. Practical code constructions are proposed within this framework, and the performance of the proposed codes is compared with conventional approaches, for communication of a first-order Gauss-Markov source over erasure channels with independent failure probabilities.

1. A. Jagmohan, A. Sehgal, N. Ahuja, "WYZE-PMD based Multiple Description Video Codec," Proc. IEEE Int. Conf. Multimedia Expo, 2003, pp. I-569-572 Full Text
2. A. Jagmohan, N. Ahuja, "Wyner-Ziv Encoded Predictive Multiple Descriptions," Proc. Data Compression Conference, p. 213 2003. Full Text
3. A. Jagmohan, A. Sehgal, N. Ahuja, "Predictive Encoding using Coset Codes, " Invited Paper, Proc. IEEE Int. Conf. Image Processing, pp. I-29-32, 2002. Full Text

| Demo | Details | Back to Theme |

Compression of Image-based Rendering Data

A. Jagmohan, A. Sehgal, N. Ahuja

The design of compression techniques for streaming of image-based rendering data to remote viewers. A compression algorithm based on the use of Wyner-Ziv codes is proposed, which satisfies the key constraints for IBR streaming, namely those of random access for interactivity, and precompression.

1. A. Jagmohan, A. Sehgal, N. Ahuja "Compression of Light-field Rendering Data using Coset Codes , " Invited Paper, Proc. Asilomar Conf. on Sig., Syst., and Comp., 2003. Full Text

| Demo | Details | Back to Theme |

Video Encoding using Coset Codes

A. Sehgal, A. Jagmohan, N. Ahuja

This project deals with scalable coding and robust Internet streaming of predictively encoded media. We frame the problem of predictive coding as a variant of the Wyner-Ziv problem in Information theory. Subsequently, LDPC based coset code constructions are used to compress the media in a scalable, error-resilient manner.

1. A. Sehgal, A. Jagmohan, N. Ahuja "Wyner-Ziv Coding of Video: Applications to Error Resilience," IEEE Trans. Multimedia, April 2004, pages 249 - 258. Full Text
2. A. Sehgal, A. Jagmohan, N. Ahuja "A State-free Causal Video Encoding Paradigm, " Invited Paper, Proc. IEEE Int. Conf. Image Processing, 2003, pp. I-605-608 Full Text
3. A. Sehgal, A. Jagmohan, N. Ahuja "Scalable Predictive Coding and the Wyner-Ziv Problem, " Proc. IEEE Int. Conf. Comm. Systems, 2002. Full Text
4. A. Sehgal, N. Ahuja, "Robust predictive coding and the Wyner-Ziv problem," Data Compression Conference, Snowbird, Utah, 2002. pp. 103 Full Text

| Demo | Details | Back to Theme |

Fusion of Frequency and Spatial Domain Information for Motion Analysis

A. Briassouli, N. Ahuja

Analysis of multiple motions in video by fusing frequency and spatial domain information. The number of moving objects and their velocities are estimated. The objects are then tracked, and completely reconstructed from both the Fourier and spatial domain data, thus achieving motion segmentation.

1. Alexia Briassouli, Narendra Ahuja, Fusion of frequency and spatial domain information for motion analysis , Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2, pp. 175-178, 2004 Cambridge UK Full Text (4MB)
2. Alexia Briassouli, Narendra Ahuja, Spatial and Fourier Error Minimization for Motion Estimation and Segmentation, ICPR 2006, Hong Kong Full Text

| Demo | Details | Back to Theme |

Time Frequency Analysis of Multiple Periodicities

A. Briassouli, N. Ahuja

A new approach to extraction and estimation of multiple periodic motions from a video sequence based on spatial and time-frequency analysis. Multiple periodic or near-periodic trajectories are extracted and their periods are estimated.

1. Alexia Briassouli, Narendra Ahuja, Estimation of Multiple Periodic Motions from
   Video, ECCV 2006, Graz, Austria  Full Text

| Demo | Details | Back to Theme |

Facial Expression Decomposition

H. Wang, N. Ahuja

New algorithms for facial image analysis based on multilinear algebra. We learn the expression subspace and person subspace from a corpus of images based on Higher-Order Singular Value Decomposition, and investigate their applications in facial expression synthesis, face recognition and facial expression recognition.

1. Hongcheng Wang, Narendra Ahuja, Facial Expression Decomposition, Ninth IEEE International Conference on Computer Vision Volume 2, p. 958 10 13 - 10, 2003, Nice, FranceFull Text

| Demo | Details | Back to Theme |

Tensor Decomposition Using Image-as-Matrix Representation

H. Wang, N. Ahuja

The goal of this project is to explore new algorithms based on multilinear algebra for representation of multidimensional data in computer vision.

1. Hongcheng Wang and Narendra Ahuja, Rank-R Approximation of Tensors Using Image-as-Matrix Representation, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2005
2. Hongcheng Wang and Narendra Ahuja, Compact Representation of Multidimensional Data Using Tensor Rank-One Decomposition, Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1, pp. 44-47 08 23 - 08, 2004, Cambridge UK Full Text
   

| Demo | Details | Back to Theme |

| Demo | Details | Back to Theme |

A. Himanshu and N. Ahuja

An automatic object detection, localization and segmentation system is proposed for object categories. Object categories are modelled as templates of patches around interest points, encoding both location and appearance information. The automatic segmentation algorithm integrates the localization information with the edge information in the image.

| Demo | Details | Back to Theme |

Out-of-Core Tensor Approximation of Multidimensional Matrices of Visual Data

H. Wang, Q. Wu, L. Shi, Y. Yu, N. Ahuja

An algorithm for memory (core) efficient tensor approximation that obtains a compact representation of multidimensional visual data for efficient image-based rendering. The algorithm manages with a small memory size. We apply it to 6D Bidirectional Texture Functions (BTFs), 7D Dynamic BTFs and 4D temporal volume sequences. . 

1. Hongcheng Wang, Qing Wu, Lin Shi, Yizhou Yu and Narendra Ahuja, Out-of-Core Tensor Approximation of Multi-Dimensional Matrices of Visual Data,  in ACM SIGGRAPH 2005.

| Demo | Details | Back to Theme |

Videoshop: A New Framework for Video Editing in Gradient Domain

H. Wang, N. Xu, R. Raskar, N. Ahuja

A new framework for seamless video editing in gradient domain with the objective of replacing video segments in one video sequence from those in another, composing video sequences by juxtaposing multiple other video sequences, etc.

1. Hongcheng Wang, Ning Xu, Ramesh Raskar and Narendra Ahuja, Videoshop: A New Framework for Video Editing in Spatio-Temporal Gradient Domain, IEEE, Video Proceedings, International Conference on Computer Vision and Pattern Recognition, 2005

2.  Hongcheng Wang, Ramesh Raskar and Narendra Ahuja, Seamless Video Editing, Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, Aug. 2004, pp. III-858-861

| Demo | Details | Back to Theme |

Sparse Lumigraph Relighting by Illumination and Reflectance Estimation from Multi-View Images

T. Yu, H. Wang, N. Ahuja and W-C. Chen

A novel relighting approach that does not assume that the illumination is known or controllable. Instead, we estimate the illumination and texture from multi-view images captured under a single illumination setting, given the object shape.

1. Tianli Yu, Hongcheng Wang, Narendra Ahuja, Wei-Chao Chen, Sparse Lumigraph Relight by Illumination and Reflectance Estimation from Multi-View Images, Eurographics Symposium on Rendering (EGSR), 2006  Full Text
2. Tianli Yu, Hongcheng Wang, Narendra Ahuja, Wei-Chao Chen, Sparse Lumigraph Relight by Illumination and Reflectance Estimation from Multi-View Images, Technical Sketch, SIGGRAPH, 2006  Full Text

| Demo | Details | Back to Theme |