Yun-Ho Ko

Intelligent video tracking based on fuzzy-reasoning segmentation

In our previous work [J. Cho, D. Kim, D. Park, Robust centroid target tracker based on new distance features in cluttered image sequences. IEICE Transactions on Information and Systems, Vol. E83-D, No. 12, December, 2000.], we presented a novel centroid target tracker based on new distance features in cluttered image sequences. A real-time adaptive segmentation method based on new distance features was proposed for the binary centroid tracker. The target classifier by the Bayes decision rule for minimizing the probability of error should properly estimate the state-conditional densities. In this correspondence, the proposed target classifier adopts the fuzzy-reasoning segmentation instead of the estimation of the state-conditional probability densities. Comparative experiments show that the performance of the proposed fuzzy-reasoning segmentation is superior to that of the conventional thresholding methods. The usefulness of the fuzzy-reasoning segmentation for practical applications is demonstrated by considering two sequences of real target images. The tracking results are good and stable without difficulty of the probability densities estimation.

Video rate control using an adaptive quantization based on a combined activity measure

A new rate control algorithm for videos is presented. The method comes from the MPEG-2 Test Model 5(TM5) rate control, while a buffer constraint and a new measure for the macroblock (MB) activity based on spatio-temporal sensitivity are introduced. Experimental results show that the proposed method outperforms the TM5 rate control in picture quality.

Frame rate up-conversion method based on texture adaptive bilateral motion estimation

In this paper, a new frame rate up-conversion scheme is proposed in order to overcome motion blur problems of liquid crystal displays caused by slow responses. Conventional bilateral motion estimation methods used in the frame rate upconversion scheme present a major drawback of missing true motion vectors if there are blocks with simple textures in search range. To solve this problem, a texture adaptive bilateral motion estimation method increasing the cost value of a block with simple texture is proposed. Also a motion estimation scheme that utilizes neighboring motion vector effectively is proposed to reduce computation time required to estimate motion. Since the proposed scheme does not apply all available motion vectors within search range, the execution time of frame rate up conversion can be reduced dramatically. Experimental results show that the interpolated frame image quality is improved as well as the processing time of the proposed method is greatly reduced compared with those of conventional methods.

Dual block truncation coding for overdriving of full HD LCD driver

This paper presents an image coding method for overdriving of a 10bit Full HD LCD display considering the chip size of TCON (Timing Controller) and real-time operation. The proposed method is an adaptive scheme of AM-BTC (Absolute Moment Block Truncation Coding). It splits a sample block into two sub-blocks considering the color level distribution of the sample block and applies AMBTC to each sub-block. Experimental results show that the proposed method is superior to the conventional method in both objective and subjective visual quality.

Fast motion estimation algorithm combining search point sampling technique with adaptive search range algorithm

This paper presents an enhanced fast motion estimation method where a search point sampling technique is combined with the adaptive search range algorithm (ASRA) based on the distribution of motion vector differences, which is our previous work. Since the ASRA is based on downsizing of search ranges for less computational complexity rather than sub-sampling of search points that is adopted by most of the fast algorithms, it results in smaller search areas where all points are considered as search points. Therefore, the conventional fast algorithms based on search point sampling techniques such as three-step search algorithm can be easily employed to the ASRA. As a result, we propose an algorithm where a part of the points within the search areas determined by the ASRA are sampled as the search points. Experimental results show that the proposed method reduces complexity of our ASRA by about 60% without quality degradation.

Precision tracking based-on fuzzy reasoning segmentation in cluttered image sequences

In our previous work [7], we presented a robust centroid target tracker based on new distance features in cluttered image sequences. A real-time adaptive segmentation method based on new distance features was proposed for the binary centroid tracker. The target classifier by the Bayes decision rule for minimizing the probability error should properly estimate the state-conditional densities. In this correspondence, the proposed target classifier adopts the fuzzy-reasoning segmentation using the fuzzy membership functions instead of the estimation of the state-conditional probability densities. Comparative experiments also show that the performance of the proposed fuzzy- reasoning segmentation is superior to that of the conventional thresholding methods. The usefulness of the method for practical applications is demonstrated by considering two sequences of real target images. The tracking results are good and stable without difficulty of the estimation.

Context adaptive block scan for video coding

A new coefficient scanning method using context adaptive block scan (CABS) is presented. A number of additional scan patterns for entropy coding are employed in addition to the conventional zigzag scan. The scan pattern is adaptively selected per 4×4 block basis. In order to avoid any increment of overhead bits, the scan pattern for each block is determined in the context adaptive manner.

3D profiling of thin film using contour analysis of interference fringe image and interpolation method

In this paper we propose a new framework to obtain 3D shape information of thin film rapidly. The conventional equipments based on reflectometry are not suitable for obtaining 3D overall shape information of thin film rapidly since they require more than 30 minutes to measure the absolute thickness for 170 points. The proposed framework is based on an image analysis method that extracts contour lines from interference fringes images using Canny edge detector. The absolute thicknesses for contour lines are measured and then a height map from the contour lines is obtained by interpolation using modified Borgefors distance transformation. The extracted height map is visualized using the DirectX 3D terrain rendering method. The proposed framework can provide 3D overall shape information of thin film in about 5 minutes since relatively small number of real measurement for contour lines is required.

Robust shadow removal algorithm for accurate object detection based on background subtraction method

This paper presents a new shadow removal algorithm for accurate object detection based on the background subtraction method. The algorithm requires no threshold to determine shadow regions, whereas the conventional algorithms suffer from specifying the thresholds for various illumination conditions. It finds shadow regions by means of measuring relative similarities between shadow candidate regions and a background image given by the BSM. We empirically verify that it is very effective to remove the shadow regions.