1-3hit |
Dae-Hyun KIM Jung-Hoon KIM Yong-In YOON In-Hwan OH Jong-Soo CHOI
In this paper, we propose an algorithm that automatically generates the intermediate scenes using the bidirectional disparity morphing (BDM) from the parallel stereo images. The two-step search strategy is used for speeding up the computation of the bidirectional disparity map and three occluding patterns are used for smoothing the computed disparities more elaborately. Using the bidirectional disparity map, we interpolate the left and the right image to their intermediate scenes. Then we dissolve two interpolated images into the desired intermediate scene which the holes are removed and the effect of the disparity estimation errors is minimized. We implemented the proposed algorithm on TM1300 supported by TriMedia using pSOSytem which enables to do multiprocessing. As a result, we can interpolate the high-quality intermediate scenes with real-time process.
Hee-Won CHANG Eung-Kwan KANG Jong-Soo CHOI
In this paper, we propose a new content-based image retrieval method by using color and color spatial information of an image. To index images, we use the average coordinates of color distribution to obtain the spatial information of each segmented fuzzy region that is less sensitive to image rotation and object translations in an image. Furthermore, we also propose the alternative to solve the ripple phenomenon, which is occurred in the conventional fuzzy region segmentation algorithm and distorts the information of other regions.
Surng-Gabb JAHNG Hyun-Ki HONG Jong-Soo CHOI
The rosette-scanning infrared seeker (RSIS) is a tracker that a single infrared detector scans the total field of view (TFOV) in a rosette pattern, and then produces 2D image about a target. Since the detected image has various shapes in accordance with the target position in the TFOV, it is difficult to determine a precise target position from the obtained image. In order to track this type of target, therefore, we propose an efficient tracking method using the K-means algorithm (KMA). The KMA, which classifies image clusters and calculates their centers, is used to cope with an countermeasure (CM) such as an IR flare. To evaluate the performance of the RSIS using the KMA dynamically, we simulate the RSIS in the various conditions, and discuss the tracking results.