Hwal-Suk Lee

A Novel Template Matching Scheme for Fast Full-Search Boosted by an Integral Image

A new template matching method accelerated by an integral image is proposed. In contrast to the conventional winner-update template matching algorithm, the proposed scheme uses an integral image instead of a block sum pyramid to represent the search area. When an integral image is used, block sums on the lowest level are evaluated very fast. As a result, the speed with which nonbest candidates are rejected is nearly double that of the conventional scheme. Moreover, the proposed scheme needs less memory than the conventional approach to maintain block sums of candidates and can be easily extended to nonsquare (rectangular) template matching.

Fast block matching algorithm using spatial intensity distribution

Block matching algorithm is useful in many applications such as stereo vision, visual tracking and so on. And the heavy computational burden of the full-search algorithm induces many faster algorithms, which can be classified into two. One class reduces the search area where the other reduces the unnecessary computation of each candidate block. In this paper, a new matching algorithm, which reduces the computational burden by using vote strategy, is proposed. With the observation of the property that the best match also has the similar spatial intensity distribution, block matching algorithm is described. The proposed matching algorithm is fast and robust to speckle noise or object occlusion.

2:1 Candidate Position Subsampling Technique for Fast Optimal Motion Estimation

The candidate position subsampling technique (CPST) basically chooses candidates in a search window at a sampling rate. The 2:1 CPST chooses half the candidates, and then selects one or more candidates that are considered as to be close to the optimal motion vector before conducting a fine search. The fine search is conducted by checking four neighbors of the chosen candidate(s) referred to as winner(s). The CPST can be combined with a fast optimal block-matching algorithm, such as the multilevel successive elimination algorithm (MSEA), in order to reduce the number of computations used in rejecting the nonbest candidate. We propose a new 2:1 CPST fitted to the MSEA. The proposed algorithm adopts a new condition for the winner which helps to find the best candidate efficiently. Moreover, a fast motion estimation step is used to reduce the number of computations of the MSEA, and the peak signal-to-noise ratio (PSNR) compensation step is adopted to guarantee that the PSNR performance of the proposed algorithm is very close to that of the full search. Experimental results show that the proposed algorithm reduces the computational loads of the MSEA by 47.26% on average with only -0.027 dB PSNR degradation in the worst case.

An effective successive elimination algorithm for fast optimal block-matching motion estimation

The successive elimination technique is used widely in the successive elimination algorithm (SEA), the multilevel successive elimination algorithm (MSEA), and the fine granularity successive elimination (FGSE) for fast optimal block-matching motion estimation. The computational cost of a series of these algorithms is primarily affected by a set of lower bounds. In this paper, an efficient scheme to build a set of lower bounds is proposed. This scheme efficiently produces the same set of lower bounds as those of MSEA. Moreover, the optimal number and positions of checking the validity of a candidate block using the proposed scheme is studied. Based on our study, a new algorithm is proposed: the effective successive elimination algorithm (ESEA). Experimental results are given to show the superiority of the proposed algorithm over previous approaches.

Development of a demeaning filter for small object detection in infrared images

The demeaning filter detects a small object by removing a background with a mean filter as well as the covariance of an object and backgrounds. The factors considered in the design of the demeaning filter are the method of demeaning, which involves subtracting the local mean value from all pixel values, and the acquisition of templates for both the object and the background. This study compares the sliding window method and the grid method as a demeaning method, and studies the method of acquisition of an object template. Moreover, a method involving the use of previous frames, a mean filter, and an opening operation are studied in an effort to acquire a background template. Based on the results of this study, a practical design of a demeaning filter that is able to detect a small object in an IR image in real time is proposed. Experiment results demonstrate the superiority of the proposed design in detecting a small object following a 2-D Gaussian distribution even under severe zero-mean Gaussian noise.

Robust Method for Detecting an Infrared Small Moving Target based on the Facet-based Model

In this paper, a new condition for the target is proposed to increase the robustness of the facet-based detection method for zero-mean Gaussian noise. In the proposed algorithm, the pixels detected from the maximum extremum condition are checked further to discern if they are false maximum points in the proposed scheme. The experimental results show that the proposed algorithm is much more robust for zero-mean Gaussian noise than the conventional detection method.

Adaptive Target Segmentation Using Runtime-Weighted Features

Target segmentation plays an important role in the entire target tracking process. This process decides whether the current pixel belongs to the target region or not. In the previous works, the target region was extracted according to whether the intensity of each pixel is larger than a certain value. But simple binarization using one feature, i.e. intensity, can easily fail to track as condition changes. In this paper, we employ more features such as intensity, deviation over time duration, matching error, etc. rather than intensity only and each feature is weighted by the weighting logic, which compares the characteristics in the target region with that in the background region. The weighting logic gives a higher weight to the feature which has a large difference between the target region and the background region. So the proposed segmentation method can control the priority of features adaptively and is robust to the condition changes of various circumstances.

An Efficient Diamond Search with Large Kite Search Patterns for Fast Block Motion Estimation

One of the well known block-matching motion estimation (BMME) algorithm is the diamond search (DS). Two improved versions of DS in terms of speed are known to be the cross-diamond search (CDS) and the cross-diamond-hexagonal search (CDHS). Based on these methods, our proposed algorithm employs a new scheme to find small motion vectors with the smallest checking points and proposes two novel search patterns designed to reduce checking points efficiently for large motion vectors. The speed improvement of the proposed algorithm can be up to 61% faster than the diamond search (DS) algorithm, 44% faster than the CDS, and 25% faster than the CDHS while providing similar prediction accuracies