• ETRI Journal
• /
• v.37 no.6
• /
• pp.1143-1153
• /
• 2015

In this paper, we propose an efficient architecture for a real-time image stitching engine for vision SoCs found in motor vehicles. To enlarge the obstacle-detection distance and area for safety, we adopt panoramic images from multiple telegraphic cameras. We propose a stitching method based on a fixed homography that is educed from the initial frame of a video sequence and is used to warp all input images without regeneration. Because the fixed homography is generated only once at the initial state, we can calculate it using SW to reduce HW costs. The proposed warping HW engine is based on a linear transform of the pixel positions of warped images and can reduce the computational complexity by 90% or more as compared to a conventional method. A dual-core SW/HW image stitching engine is applied to stitching input frames in parallel to improve the performance by 70% or more as compared to a single-core engine operation. In addition, a dual-core structure is used to detect a failure in state machines using rock-step logic to satisfy the ISO26262 standard. The dual-core SW/HW image stitching engine is fabricated in SoC with 254,968 gate counts using Global Foundry's 65 nm CMOS process. The single-core engine can make panoramic images from three YCbCr 4:2:0 formatted VGA images at 44 frames per second and frequency of 200 MHz without an LCD display.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.97-107
• /
• 2006

In this paper, we present a method for the detection and recognition of rectangular markers from a camera image. It converts the camera image to a binary image and extracts contours of objects in the binary image. After that. it approximates the contours to a list of line segments. It finds rectangular markers by using geometrical features which are extracted from the approximated line segments. It normalizes the shape of extracted markers into exact squares by using the warping technique. It extracts feature vectors from marker image by using principal component analysis. It then calculates the distance between feature vector of input marker image and those of standard markers. Finally, it recognizes the marker by using minimum distance method. Experimental results show that the Proposed method achieves 98% recognition rate at maximum for 50 markers and execution speed of 11.1 frames/sec for images which contains eleven markers.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.9
• /
• pp.119-126
• /
• 2013

In this paper, we propose a chromatic aberration removal algorithm in image capture devices, which considers local properties of the image. Chromatic aberration is generated by the fact that the refractive index of the lens is different for different wavelengths, which produces color artifacts on strong edge due to misalignment of RGB channels. Under the characteristics of the artifacts, the proposed algorithm first estimates the regions with the apparent color artifacts as the neighborhoods of the strong edge. In the regions, the proposed algorithm removes the color artifacts by matching the edges of RGB channels. The widely used conventional methods based on global image warping could not remove the color artifacts of longitudinal chromatic aberration and purple fringing identified by the image sensor, whereas the matching process of the proposed method could reduce them. Experimental results show that the proposed algorithm outperforms the conventional methods on objective and subjective criteria.

• Journal of radiological science and technology
• /
• v.23 no.1
• /
• pp.39-47
• /
• 2000

In this study, we showed a comparison and analysis making use of DWI(diffusion weighted image) using early diagnosis of cerebral Infarction and with the classified T2 weighted image, FLAIR images signal intensity for brain infarction period. period of cerebral infarction after the condition of a disease by ischemic stroke. To compare 3 types of image, we performed polynomial warping and affined transform for image matching. Using proposed algorithm, calculated signal intensity difference between T2WI, DWI, FLAIR and DWI. The quantification values between hand made and calculated data are almost the same. We quantified the each period and performed pseudo color mapping by comparing signal intensity each other according to previously obtained hand made data, and compared the result of this paper according to obtained quantified data to that of doctors decision. The examined mean and standard deviation for each brain infarction stage are as follows ; the means and standard deviations of signal intensity difference between DWI and T2WI for each period are $197.7{\pm}6.9$ in hyperacute, $110.2{\pm}5.4$ in acute, and $67.8{\pm}7.2$ in subacute. And the means and standard deviations of signal intensity difference between DWI and FLAIR for each period are $199.8{\pm}7.5$ in hyperacute, $115.3{\pm}8.0$ in acute, and $70.9{\pm}5.8$ in subacute. We can quantificate and decide cerebral infarction period objectively. According to this study, DWI is very exact for early diagnosis. We classified the period of infarction occurrence to analyze the region of disease and normal region in DW, T2WI, FLAIR images.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.89-97
• /
• 2008

In this paper, we present a method for the enhancement of marker detection correctness and marker recognition speed by using artificial neural network. Contours of objects are extracted from the input image. They are approximated to a list of line segments. Quadrangles are found with the geometrical features of the approximated line segments. They are normalized into exact squares by using the warping technique and scale transformation. Feature vectors are extracted from the square image by using principal component analysis. Artincial neural network is used to checks if the square image is a marker image or a non-marker image. After that, the type of marker is recognized by using an artificial neural network. Experimental results show that the proposed method enhances the correctness of the marker detection and recognition.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• Journal of Broadcast Engineering
• /
• v.1 no.2
• /
• pp.85-95
• /
• 1996

The purpose of this paper Is to propose a dubbed signal time-synchroniztion technique based on the SOLA(Synchronized Over-Lap and Add) method which has been widely used to modify the time scale of speech signal. In broadcasting audio recording environments, the high degree of background noise requires dubbing process. Since the time difference between the original and the dubbed signal ranges about 200mili seconds, process is required to make the dubbed signal synchronize to the corresponding image. The proposed method finds he starting point of the dubbing signal using the short-time energy of the two signals. Thereafter, LPC cepstrum analysis and DTW(Dynamic Time Warping) process are applied to synchronize phoneme positions of the two signals. After determining the matched point by the minimum mean square error between orignal and dubbed LPC cepstrums, the SOLA method is applied to the dubbed signal, to maintain the consistency of the corresponding phase. Effectiveness of proposed method is verified by comparing the waveforms and the spectrograms of the original and the time synchronized dubbing signal.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.7
• /
• pp.1456-1461
• /
• 2003

Recently, the quantity of using information go on increasing geometric-progression. At the same time, the management of information is effected on the most organization's effective operation so that many user call for the powerful equipment which expound. access more information. As information searching technology is concentrated about the object of information based on a letter mainly, an effective searching technology for the object of multimedia such as a still image, a video and a sound must be studied. As a monitor of computer is 2-D, it difficult for one to grasp the whole aspect at a look glance like a library. Accordingly, some condition is necessary. First, it acquired the virtual video, turning a camera around by 30 degrees with a camera of 15mm lens, giving a warping and distortion. Second, it improved the books for user to search easily, adding to the video in existing books information system. The original text suggests some way which can embody the video searching technology under the base of personal computer.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2865-2874
• /
• 2013

Recently, most of movies top-ranked in the box office are screening in Stereoscopic 3D, and the world's leading electronics companies such as Samsung and LG are getting the hots for 3DTV sales. However, each person has different binocular disparity and different viewing distance, and thus he or she feels the severe visual fatigue and headaches if he or she is watching 3D content with the same binocular disparity, which is very different from things he or she feels in the real world. To solve this problem, this paper proposes and implement a 3D rendering system that correct the disparity of 3D content by reflecting binocular distance and viewing distance. Then, the computational complexity is analyzed. Optical-flow and Warping algorithms turn out to consume 732 seconds and 5.7 seconds per frame, respectively. Therefore, a dedicated chip-set for both blocks is strongly required for real-time HD 3D display.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.19-26
• /
• 2022

This paper presents a pre-processing method to facilitate the container's BIC-code recognition. We propose a network that can find ROI(Region Of Interests) containing a BIC-code region and estimate a homography matrix for warping. Taking the structure of STN(Spatial Transformer Networks), the proposed network consists of next 3 steps, ROI detection, homography matrix estimation, and warping using the homography estimated in the previous step. It contributes to improving the accuracy of BIC-code recognition by estimating ROI and matrix using the proposed network and correcting perspective distortion of ROI using the estimated matrix. For performance evaluation, five evaluators evaluated the output image as a perfect score of 5 and received an average of 4.25 points, and when visually checked, 224 out of 312 photos are accurately and perfectly corrected, containing ROI.