• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.56-65
• /
• 2009

Stereoscopic images consist of the left image and the right image. Thus, stereoscopic images have much amounts of data than single image. Then an efficient image compression technique is needed, the DPCM-based predicted coding compression technique is used in most video coding standards. Motion and disparity estimation are needed to realize the predicted coding compression technique. Their performing algorithm is block matching algorithm used in most video coding standards. Full search algorithm is a base algorithm of block matching algorithm which finds an optimal block to compare the base block with every other block in the search area. This algorithm presents the best efficiency for finding optimal blocks, but it has very large computational loads. In this paper, we have proposed fast disparity estimation algorithm using motion and disparity vector information of the prior frame in stereo image coding. We can realize fast disparity vector estimation in order to reduce search area by taking advantage of global disparity vector and to decrease computational loads by limiting search points using motion vectors and disparity vectors of prior frame. Experimental results show that the proposed algorithm has better performance in the simple image sequence than complex image sequence. We conclude that the fast disparity vector estimation is possible in simple image sequences by reducing computational complexities.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.6
• /
• pp.587-595
• /
• 2011

In this paper, we focus on the issue of automatic selection for multi-level threshold, and we greatly improve the efficiency of Otsu's method for image segmentation based on genetic algorithm. We have investigated and evaluated the performance of the Otsu and Valley-emphasis threshold methods. Based on this observation we propose a method for automatic threshold method that segments an image into more than two regions with high performance and processing in real-time. Our paper introduced new peak detection, combines with evolution algorithm using MAGA (Modified Adaptive Genetic Algorithm) and HCA (Hill Climbing Algorithm), to find the best threshold automatically, accurately, and quickly. The experimental results show that the proposed evolutionary algorithm achieves a satisfactory segmentation effect and that the processing time can be greatly reduced when the number of thresholds increases.

• Journal of Korean Society of Transportation
• /
• v.19 no.6
• /
• pp.7-17
• /
• 2001

The purpose of this paper is to develop automatic incident detection algorithm using image based detector in freeway management system. This algorithm was developed by using neutral network for high speed roadway and by using speed and occupancy variable for low speed roadway. The image detector system with the developed automatic incident detection algorithm can detect multi-lane as well as several detect areas for each lane. To evaluate this system, field tests to measure the detecting rate of incidents were performed with other systems which have APID and DES algorithm at high speed roadway(freeway) and low speed roadway(national arterial). As the results of field test, it found that the detect rate of this system was highest rate comparing to other two systems.

• Nuclear Engineering and Technology
• /
• v.39 no.4
• /
• pp.313-326
• /
• 2007

In this paper, an algorithm to reconstruct two orthogonal images into a three-dimensional image is developed in order to measure the bubble size and volume in a two-phase boiling flow. The central-active contour model originally proposed by P. $Szczypi\'{n}ski$ and P. Strumillo is modified to reduce the dependence on the initial reference point and to increase the contour stability. The modified model is then applied to the algorithm to extract the object boundary. This improved central contour model could be applied to obscure objects using a variable threshold value. The extracted boundaries from each image are merged into a three-dimensional image through the developed algorithm. It is shown that the object reconstructed using the developed algorithm is very similar or identical to the real object. Various values such as volume and surface area are calculated for the reconstructed images and the developed algorithm is qualitatively verified using real images from rubber clay experiments and quantitatively verified by simulation using imaginary images. Finally, the developed algorithm is applied to measure the size and volume of vapor bubbles condensing in a subcooled boiling flow.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.896-913
• /
• 2018

Seam finding algorithm is one of the most important techniques to construct the high quality 360 VR image. We found that some degradations, such as ghost effect, are generated when the conventional seam finding algorithms (for examples, Voronoi algorithm, Dynamic Programming algorithm, Graph Cut algorithm) are applied, because those make the inefficient masks which cross the body of main objects. In this paper, we proposed an advanced seam finding algorithm providing the efficient masks which go through background region, instead of the body of objects. Simulation results show that the proposed algorithm outperforms the conventional techniques in the viewpoint of the quality of the stitched image.

• Korean Journal of Remote Sensing
• /
• v.29 no.2
• /
• pp.183-195
• /
• 2013

Real-time high-precision image georeferencing is important for the realization of image based precise navigation or sophisticated augmented reality. In general, high-precision image georeferencing can be achieved using the conventional simultaneous bundle adjustment algorithm, which can be performed only as post-processing due to its processing time. The recently proposed sequential bundle adjustment algorithm can rapidly produce the results of the similar accuracy and thus opens a possibility of real-time processing. However, since the processing time still increases linearly according to the number of images, if the number of images are too large, its real-time processing is not guaranteed. Based on this algorithm, we propose a modified fast algorithm, the processing time of which is maintained within a limit regardless of the number of images. Since the proposed algorithm considers only the existing images of high correlation with the newly acquired image, it can not only maintain the processing time but also produce accurate results. We applied the proposed algorithm to the images acquired with 1Hz. It is found that the processing time is about 0.02 seconds at the acquisition time of each image in average and the accuracy is about ${\pm}5$ cm on the ground point coordinates in comparison with the results of the conventional simultaneous bundle adjustment algorithm. If this algorithm is converged with a fast image matching algorithm of high reliability, it enables high precision real-time georeferencing of the moving images acquired from a smartphone or UAV by complementing the performance of position and attitude sensors mounted together.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.211-214
• /
• 2001

This paper presents an efficient fast motion estimation algorithm and image segmentation method for low bit-rate coding. First, with region split information, the algorithm splits the image having homogeneous and semantic regions like face and semantic regions in image. Then, in these regions, We find the motion vector using adaptive search window adjustment. Additionally, with this new segment based fast motion estimation, we reduce blocking artifacts by intensively coding our interesting region(face or arm) in input image. The simulation results show the improvement in coding performance and image quality.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1129-1132
• /
• 2005

In this paper, we proposed real-time stereoscopic image conversion algorithm using object segmentation and motion parallax. The proposed algorithm separates objects using luminance of image, extracts moving object among objects of the image using motion parallax and generates depth map. Parallax process is done based on the depth map. The proposed method has been evaluated using visual test and APD(Absolute Parallx Difference) for comparing the stereoscopic image of the proposed method with that of MTD. The proposed method offers realistic stereoscopic conversion effect regardless of the direction and velocity of the 2-D image.

• Proceedings of the KOSOMBE Conference
• /
• v.1994 no.05
• /
• pp.23-26
• /
• 1994

A new algorithm using a measure for edge detection from ultrasonic image is proposed. Ultrasonic image is blurred by pre-processing for removing speckle noises and precise edge placement is not clear. Because extracted edge from blurred image is thick, a measure utilizing the absolute difference of mean between two windows is used to thin the thickness of extracted edge in blurred image. The algorithm is effective to process blurred image due to the noise filtering that remove speckle noises. Results of the proposed algorithm using a measure show good edge detection performance comparing with other gradient edge operators.

• Journal of Intelligence and Information Systems
• /
• v.6 no.1
• /
• pp.65-72
• /
• 2000

In this paper we propose the new binary image matching algorithm called the Fuzzy logic induced Hausdorff Distance(FHD) for finding the maximally matched image with the query image. The membership histogram is obtained by normalizing the cardinality of the subset with the corresponding radius after obtaining the distribution of the minimum distance computed by the Hausdroff distance between two binary images. in the proposed algorithm, The fuzzy influence method Center of Gravity(COG) is applied to calculate the best matching candidate in the membership function described above. The proposed algorithm shows the excellent results for the face image recognition when the noise is added to the query image as well as for the character recognition.