• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.309-314
• /
• 2017

Recently, the fields such as the service robot, the autonomous driving electric car, and the torpedo ladle cars operated autonomously to enhance the efficiency of management of the steel mill are receiving great attention. But development of automatic power supply that doesn't need human intervention be a problem. In this paper, a position tracking technology of power connector receptacle based on the computer vision is studied which can recognize and identify the position of the power connector receptacle, and finally its possibility is verified using OpenCV program.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.443-444
• /
• 2019

본 논문에서는 라즈베리파이(Raspberry Pi)와 실시간 객체 감지 기술인 YOLO를 이용한 전기차충전기앞불법주차 경고 영상인식 시스템을 제안한다. 최근 전기 자동차의 사용과 더불어 충전 인프라는 점점 늘어나는 중이지만, 여전히 전기차 충전기는 많지 않은 것이 현실이다. 전국 1,000여 곳이 넘는 전기차 충전소에 대해 법령으로 인한 규제를 시행 중임에도 불구하고 불법주차를 하는 일반차 오너들은 여전히 많다. 이로 인해 전기차 오너들은 충전에 많은 불편함이 있다. 이 시스템은 전기 자동차의 번호판을 인식하여 실시간 객체 감지 딥러닝 기법인 YOLO를 이용해 전기 자동차의 번호판에 특정 부분을 인식하고 특정 부분이 없는 일반 자동차가 전기차 충전기 앞 불법 주차를 하게 되면 부저와 LED경고를 통해 주차된 일반 차량에게 경고를 하여, 불법 주차자와 더불어 주변을 지나가는 행인들에게도 전기차 앞 불법 주차에 대해 각인을 시켜줄 수 있는 시스템이다.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1057-1068
• /
• 2022

This paper compares the combination performance of feature point-based matching algorithms as a study to confirm the matching possibility between image taken by a user and a virtual texture image with the goal of developing mobile-based real-time image positioning technology. The feature based matching algorithm includes process of extracting features, calculating descriptors, matching features from both images, and finally eliminating mismatched features. At this time, for matching algorithm combination, we combined the process of extracting features and the process of calculating descriptors in the same or different matching algorithm respectively. V-World 3D desktop was used for the virtual indoor texture image. Currently, V-World 3D desktop is reinforced with details such as vertical and horizontal protrusions and dents. In addition, levels with real image textures. Using this, we constructed dataset with virtual indoor texture data as a reference image, and real image shooting at the same location as a target image. After constructing dataset, matching success rate and matching processing time were measured, and based on this, matching algorithm combination was determined for matching real image with virtual image. In this study, based on the characteristics of each matching technique, the matching algorithm was combined and applied to the constructed dataset to confirm the applicability, and performance comparison was also performed when the rotation was additionally considered. As a result of study, it was confirmed that the combination of Scale Invariant Feature Transform (SIFT)'s feature and descriptor detection had the highest matching success rate, but matching processing time was longest. And in the case of Features from Accelerated Segment Test (FAST)'s feature detector and Oriented FAST and Rotated BRIEF (ORB)'s descriptor calculation, the matching success rate was similar to that of SIFT-SIFT combination, while matching processing time was short. Furthermore, in case of FAST-ORB, it was confirmed that the matching performance was superior even when 10° rotation was applied to the dataset. Therefore, it was confirmed that the matching algorithm of FAST-ORB combination could be suitable for matching between virtual texture image and real image.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.16 no.2
• /
• pp.87-92
• /
• 1987

Crease cut pearled baller was studied in relation to product and quality, and processing electricity requirement with various pearling yields. 1. Increasing the pearling rate resulted in increasing broken grain of cut-Polished barley. 2. The range of length/width ratio in cut-polished baller were from 2.09 to 2.13 and those of pearled barley were 1.36, respectively. 3. Cut-polished barley required more electricity than pearled barley at the same polishing rate. As pearling rate increased at first polishing before cutting, total electricity requirement of cut-polished barley reduced significantly.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.103-112
• /
• 2011

Motion estimation (ME) is regarded as an important component in a video encoding process, because it consumes a large computation complexity. H.264/AVC requires additional computation overheads for fractional search and interpolation. This causes a problem that computational complexity is increased. In Motion estimation, SATD(Sum of Transform Difference) has the characteristics of a parabolic based on the minimum point. In this paper, we propose new prediction algorithm to reduce search point in motion estimation by sub-pixel interpolation characteristics. The proposed algorithm reduces the time of encoding process by decreasing computational complexity. Experimental results show that the proposed method reduces 20% of the computation complexity of motion estimation, while the degradation in video quality is negligible.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.1 no.2
• /
• pp.78-85
• /
• 2008

Purpose: The findings of preoperative magnetic resonance imaging (MRI) and ultrasonography (US) examination in the diagnosis of rotator cuff tear were then compared with the findings of arthroscopic examination, and to evaluate the postoperative integrity of rotator cuff using serial US examination. Methods: Between February and May 2008, 29 patients with rotator cuff tear had undergone preoperative US and MRI examination and subsequent arthroscopic examination. And the results of MRI and US were compared with intra-operative results of the arthroscopic examination. We observed the postoperative integrity of rotator cuff using serial (postoperative 2 weeks, 6 weeks, 3 months) US examination. Results: The sensitivity of US and MRI for identifying rotator cuff tear were 100% and 100%. The sensitivity of US and MRI were 95% and 82% in full thickness tear, and 50%, 33% in partial thickness tear, respectively. Overall accuracy of US and MRI were 86%, 69%. Among 22 patients were operated for full thickness tear, intra-operative gap formation was identified in 11 patients (50%, small to medium 2 cases, large to massive 9 cases) which were identified at 2 weeks postoperative US. We could find 5 re-tears (23%, small to medium 1 case, large to massive 4 cases) on 6 weeks postoperative US after passive range of motion (ROM) exercise, and could also find 7 re-tears (32%, small to medium 2 cases, large to massive 5 cases)on 3 months postoperative US after active ROM exercise. Conclusion: Serial US after arthroscopic rotator cuff repair was useful to differentiate intra-operative gap formation from postoperative re-tear. We found 5 retears (23%) at 6 weeks and 7 retears (32%) at 3 months postoperative US, it was useful to make treatment plan during postoperative rehabilitation.

• Investigative Magnetic Resonance Imaging
• /
• v.1 no.1
• /
• pp.154-161
• /
• 1997

Purpose: Traumatic rupture of the diaphragm is not easy to diagnose and often delayed. Delayed diagnosis of diaphragmatic rupture accompanied by higher chances of strangulation of herniated viscera which may result in higher morbility and mortality. The purpose of this study was to evaluate diagnostic accuracy of spiral CT, MRI and US for the diagnosis of diaphragmatic rupture in an animal model. Materials and Methods: Small, medium, and large sized transabdominal diaphragmatic ruptures were surgically made in experimental rabbits and then followed up with spiral CT, MR!, and US at 1 day, 3 day, and 1 week after operation. Results: US was superior to MR! or spiral CT in diagnosis of diaphragmatic rupture(P(0.05). The sensitivity and specificity were 94.4% and 92.9% for US, 54.0% and 85.7% for MRI, and 46.0% and 78.6% for spiral CT, respectively. The size of laceration was not related to diagnostic sensitivity in US. Sensitivity of MRI and spiral CT increased as the size of laceration were larger, but no statistical significance was present(P>0.05). All experimental animals developed pleural effusion or hemothorax one day after operation. In acute phase, US and MRI were more sensitive than spiral CT in detecting diaphragmatic rupture. Spiral CT was more sensitive than US and MRI in delayed phase but without statistical significance(P>0.05). In the experimental rabbits with accompanying visceral hernia through the diaphragmatic defect, diagnostic accuracy was found equally high among three image modalities(P>0.05). Conclusion: This study indicates that US is the most accurate diagnostic method in detecting injury to the diaphragm in a rabbit model. The findings obtained in this experimental study can be applied to the diaphragmatic rupture of human being.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4C
• /
• pp.276-282
• /
• 2005

These studies developed system as well as its algorithm which can measure traffic flow and vehicle speed on the highway as well as road by using industrial television(ITV) system. This algorithm used the real time processing of dynamic images. The processing algorithm of dynamic images is developed and proved its validity by frame grabber. Frame grabber can process the information of a small number of sample points only instead of the whole pixel of the images. In the techniques of this algorithm, we made approximate contour of vehicle by allocating sampling points in cross-direction of image, and recognized top of contour of vehicle. Applying these technique, we measured the number of passing vehicles of one lane as well as multilane. Speed of each vehicle is measured by computing the time difference between a pair of sample points on two sample Points lines.

• Journal of Advanced Navigation Technology
• /
• v.9 no.1
• /
• pp.10-18
• /
• 2005

These studies developed system as well as its algorithm which can measure traffic flow and vehicle speed on the highway as well as road by using industrial television(ITV) system. This algorithm used the real time processing of dynamic images. The processing algorithm of dynamic images is developed and proved its validity by frame grabber. Frame grabber can process the information of a small number of sample points only instead of the whole pixel of the images. In the techniques of this algorithm, we made approximate contour of vehicle by allocating sampling points in cross-direction of image, and recognized top of contour of vehicle. Applying these technique, we measured the number of passing vehicles of one lane as well as multilane. Speed of each vehicle is measured by computing the time difference between a pair of sample points on two sample points lines.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.677-687
• /
• 2017

In this paper, we propose the use of hierarchical classification for winter crop mapping based on satellite imagery. A hierarchical classification is a classifier that maps input data into defined subsumptive output categories. This classification method can reduce mixed pixel effects and improve classification performance. The methodology are illustrated focus on winter cropsin Gimje city, Jeonbuk with Landsat-8 imagery. First, agriculture fields were extracted from Landsat-8 imagery using Smart Farm Map. And then winter crop fields were extracted from agriculture fields using temporal Normalized Difference Vegetation Index (NDVI). Finally, winter crop fields were then classified into wheat, barley, IRG, whole crop barley and mixed crop fields using signature from Unmanned Aerial Vehicle (UAV). The results indicate that hierarchical classifier could effectively identify winter crop fields with an overall classification accuracy of 98.99%. Thus, it is expected that the proposed classification method would be effectively used for crop mapping.