Masahiko Yachida

Video Synthesis with High Spatio-Temporal Resolution Using Motion Compensation and Spectral Fusion

We propose a novel strategy to obtain a high spatio-temporal resolution video. To this end, we introduce a dual sensor camera that can capture two video sequences with the same field of view simultaneously. These sequences record high resolution with low frame rate and low resolution with high frame rate. This paper presents an algorithm to synthesize a high spatio-temporal resolution video from these two video sequences by using motion compensation and spectral fusion. We confirm that the proposed method improves the resolution and frame rate of the synthesized video.

A fast algorithm of video super-resolution using dimensionality reduction by DCT and example selection

In this paper, we propose a novel learning-based video super resolution algorithm with less memory requirements and computational cost. To this end, we adopt discrete cosine transform (DCT) coefficients for feature vector components. Moreover, we design an example selection procedure to construct a compact database. We conducted evaluative experiments using MPEG test sequences to synthesize a high resolution video. Experimental results show that our method can improve effectiveness of super-resolution algorithm, while preserving the quality of synthesized image.

An adaptive-scale robust estimator for motion estimation

Although RANSAC is the most widely used robust estimator in computer vision, it has certain limitations making it ineffective in some situations, such as the motion estimation problem, in which uncertainty on the image features changes according to the capturing conditions. The greatest problem is that the threshold used by RANSAC to detect inliers cannot be changed adaptively; instead it is fixed by the user. An adaptive scale algorithm must therefore be applied in such cases. In this paper, we propose a new adaptive scale robust estimator that adaptively finds the best solution with the best scale to fit the inliers, without the need for predefined information. Our new adaptive scale estimator matches the residual probability density from an estimate and the standard Gaussian probability density function to find the best inlier scale. Our algorithm is evaluated in several motion estimation experiments under varying conditions and the results are compared with several of the latest adaptive-scale robust estimators.

Adaptive-Scale robust estimator using distribution model fitting

We propose a new robust estimator for parameter estimation in highly noisy data with multiple structures and without prior information on the noise scale of inliers This is a diagnostic method that uses random sampling like RANSAC, but adaptively estimates the inlier scale using a novel adaptive scale estimator The residual distribution model of inliers is assumed known, such as a Gaussian distribution Given a putative solution, our inlier scale estimator attempts to extract a distribution for the inliers from the distribution of all residuals This is done by globally searching a partition of the total distribution that best fits the Gaussian distribution Then, the density of the residuals of estimated inliers is used as the score in the objective function to evaluate the putative solution The output of the estimator is the best solution that gives the highest score Experiments with various simulations and real data for line fitting and fundamental matrix estimation are carried out to validate our algorithm, which performs better than several of the latest robust estimators.

Construction Method of Efficient Database for Learning-Based Video Super-Resolution

There are two major problems with learning-based super-resolution algorithms. One is that they require a large amount of memory to store examples; while the other is the high computational cost of finding the nearest neighbors in the database. In order to alleviate these problems, it is helpful to reduce the dimensionality of examples and to store only a small number of examples that contribute to the synthesis of a high quality video. Based on these ideas, we have developed an efficient algorithm for learning-based video super-resolution. We introduce several strategies to construct an efficient database. Through the evaluation experiments we show the efficiency of our approach in improving super-resolution algorithms.

Highly Robust Estimator Using a Case-dependent Residual Distribution Model

The latest robust estimators usually take advantage of density estimation, such as kernel density estimation, to improve the robustness of inlier detection. However, the challenging problem for these systems is choosing the suitable smoothing parameter, which can result in the population of inliers being overor under-estimated, and this, in turn, reduces the robustness of the estimation. To solve this problem, we propose a robust estimator that estimates an accurate inlier scale. The proposed method first carries out an analysis to figure out the residual distribution model using the obvious case-dependent constraint, the residual function. Then the proposed inlier scale estimator performs a global search for the scale producing the residual distribution that best fits the residual distribution model. Knowledge about the residual distribution model provides a major advantage that allows us to estimate the inlier scale correctly, thereby improving the estimation robustness. Experiments with various simulations and real data are carried out to validate our algorithm, which shows certain benefits compared with several of the latest robust estimators.