ABSTRACT: Hyperspectral imaging is a promising tool for applications in geosensing, cultural heritage and beyond. However, compared to current RGB cameras, existing hyperspectral cameras are severely limited in spatial resolution. In this paper, we introduce a simple new technique for reconstructing a very high-resolution hyperspectral image from two readily obtained measurements: A lower-resolution hyper-spectral image and a high-resolution RGB image. Our approach is divided into two stages: We first apply an unmixing algorithm to the hyperspectral input, to estimate a basis representing reflectance spectra. We then use this representation in conjunction with the RGB input to produce the desired result. Our approach to unmixing is motivated by the spatial sparsity of the hyperspectral input, and casts the unmixing problem as the search for a factorization of the input into a basis and a set of maximally sparse coefficients. Experiments show that this simple approach performs reasonably well on both simulations and real data examples.
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on; 07/2011
ABSTRACT: We propose a method for estimating demosaicing algorithms from image noise variance. We show that the noise variance in interpolated pixels becomes smaller than that of directly observed pixels without interpolation. Our method capitalizes on the spatial variation of image noise variance in demosaiced images to estimate the color filter array patterns and demosaicing algorithms. We verify the effectiveness of the proposed method using various images demosaiced with different demosaicing algorithms extensively.
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on; 07/2010
ABSTRACT: This paper presents a simple yet practical 3-D modeling method for recovering surface shape and reflectance from a set of images. We attach a point light source to a hand-held camera to add a photometric constraint to the multi-view stereo problem. Using the photometric constraint, we simultaneously solve for shape, surface normal, and reflectance. Unlike prior approaches, we formulate the problem using realistic assumptions of a near light source, non-Lambertian surfaces, perspective camera model, and the presence of ambient lighting. The effectiveness of the proposed method is verified using simulated and real-world scenes.
Computer Vision, 2009 IEEE 12th International Conference on; 11/2009
ABSTRACT: We propose a method for estimating camera response functions using a probabilistic intensity similarity measure. The similarity measure represents the likelihood of two intensity observations corresponding to the same scene radiance in the presence of noise. We show that the response function and the intensity similarity measure are strongly related. Our method requires several input images of a static scene taken from the same viewing position with fixed camera parameters. Noise causes pixel values at the same pixel coordinate to vary in these images, even though they measure the same scene radiance. We use these fluctuations to estimate the response function by maximizing the intensity similarity function for all pixels. Unlike prior noise-based estimation methods, our method requires only a small number of images, so it works with digital cameras as well as video cameras. Moreover, our method does not rely on any special image processing or statistical prior models. Real-world experiments using different cameras demonstrate the effectiveness of the technique.
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on; 07/2008
ABSTRACT: Variation in illumination conditions, caused by weather, season, time of day, etc., makes the task difficult when building surveillance systems of real world scenes. Especially, cast shadows produce troublesome appearance variations to accomplish monitoring with computer vision techniques, typically moving object tracking from a stationary viewpoint. To eliminate lighting effects robustly from image sequences as a preprocessing stage for robust video surveillance, we propose a framework based on the idea of intrinsic images. Unlike previous methods to derive intrinsic images, we derive time-varying reflectance images. As a result, we obtain illumination images that capture only lighting effects on the scene. Using these reflectance images and illumination images, we construct an illumination eigenspace to estimate directly the illumination images under the arbitrary lighting conditions of the same scene. By canceling out the lighting effects using this illumination image, robust video surveillance can be accomplished. We explain the theory of the framework with simulation results, and apply the framework to a real world monitoring data set to prove its effectiveness.
Motion and Video Computing, 2002. Proceedings. Workshop on; 01/2003
ABSTRACT: Densely-sampled image representations such as the light field or lumigraph have been effective in enabling photorealistic image synthesis. Unfortunately, lighting interpolation with such representations has not been shown to be possible without the use of accurate 3D geometry and surface reflectance properties. In this paper we propose an approach to image-based lighting interpolation that is based on estimates of geometry and shading from relatively few images. We decompose captured light fields at different lighting conditions into intrinsic images (reflectance and illumination images), and estimate view-dependent scene geometries using multi-view stereo. We call the resulting representation an intrinsic lumigraph. In the same way that the lumigraph uses geometry to permit more accurate view interpolation, the intrinsic lumigraph uses both geometry and intrinsic images to allow high-quality interpolation at different views and lighting conditions. Joint use of geometry and intrinsic images is effective in the computation of shadow masks for shadow prediction at new lighting conditions. We illustrate our approach with images of real scenes.
Computer Graphics and Applications, 2002. Proceedings. 10th Pacific Conference on; 02/2002
ABSTRACT: We have developed an algorithm, referred to as spatio-temporal
Markov random field, for traffic images at intersections. This algorithm
models a tracking problem by determining the state of each pixel in an
image and its transit, and how such states transit along both the x-y
image axes as well as the time axes. Our algorithm is sufficiently
robust to segment and track occluded vehicles at a high success rate of
93%-96%. This success has led to the development of an extendable robust
event recognition system based on the hidden Markov model (HMM). The
system learns various event behavior patterns of each vehicle in the HMM
chains and then, using the output from the tracking system, identifies
current event chains. The current system can recognize bumping, passing,
and jamming. However, by including other event patterns in the training
set, the system can be extended to recognize those other events, e.g.,
illegal U-turns or reckless driving. We have implemented this system,
evaluated it using the tracking results, and demonstrated its
IEEE Transactions on Intelligent Transportation Systems 07/2000; · 3.45 Impact Factor
ABSTRACT: It is very important to achieve reliable vehicle tracking for the
sake of individual behavior analysis of vehicles. But the most difficult
problem associated with vehicle tracking is the occlusion effect among
vehicles. Such occlusion effects usually occur at intersections and the
effects prevent us from individual behavior analysis of vehicles. In
order to resolve this problem we applied the dedicated algorithm which
we defined as spatio-temporal Markov random field model (MRF) to traffic
images at an intersection. Spatio-temporal MRF considers texture
correlations between consecutive images as well as the correlation among
neighbors within a image. This algorithm is generally applicable to
traffic image, because it requires only gray scaled images and does not
assume any shape models of vehicles. We applied this method to 3214
vehicles in 25 minute traffic images at an intersection. As a result,
the method was able to track separated vehicles that do not cause
occlusions at over 99% success rate, and the method was able to segment
and track occluded vehicles at about 95% success rate. Because vehicles
appear in various kinds of shapes and they move in random manners at the
intersection, occlusions occur in such complicated manners. The method
was proved to be robust against such random occlusions
Intelligent Transportation Systems, 2000. Proceedings. 2000 IEEE; 02/2000
ABSTRACT: It is very important to achieve reliable vehicle tracking in ITS
application such as accident detection. The most difficult problem
associated with vehicle tracking is the occlusion effect among vehicles.
In order to resolve this problem, we applied the dedicated algorithm
which we defined as spatio-temporal Markov random field model to traffic
images at an intersection. The spatio-temporal MRF considers texture
correlations between consecutive images as well as the correlation among
neighbors within a image. As a result, we were able to track vehicles at
the intersection robustly against occlusions. Vehicles appear in various
kinds of shapes and they move in random manners at the intersection.
Although occlusions occur in such complicated manners, the algorithm
given was able to segment and track such occluded vehicles at a high
success rate of 93-96%. The algorithm requires only gray scale images
and does not assume any physical models of vehicles
Pattern Recognition, 2000. Proceedings. 15th International Conference on; 02/2000