• E2M - 전기 전자와 첨단 소재
• /
• 제8권5호
• /
• pp.551-557
• /
• 1995

For the observation of treeing, a visual measurement with an optical microscope has been used to explain breakdown mechanism in high-voltage systems. The conventional directed visual method of tree aging observation is difficult to measure in short time processing, and it is impossible to analyze on tree degradation area, progressed direction, tree pattern, etc. By using an image processing technique, the tree features which appear immediately after the tree initiation as well as changes in the configuration of the tree can be easily measured and observed than using the conventional visual methods. In this paper, we have developed a tree observating system by using image processing for tree growth, degradation area and other treeing progress. As an experimental result, it can be concluded that the image processing method is a more effective alternative than directed visual observation method. As a matter of fact, it is possible to record the image of tree propagation immediately after its first appearance and explain the characteristics of tree growth froth the computer processing image.

• 방송공학회논문지
• /
• 제17권2호
• /
• pp.223-236
• /
• 2012

본 논문에서는 인간 인지 기반 비디오 코딩을 위한 비디오 처리 방법을 개발한다. 제안하는 방법은 율-왜곡(rate-distortion) 최적화의 영향뿐만 아니라 제한적인 시, 공간 해상도, 지역적인 움직임 이력(history), visual saliency에 의한 인간 시각 인지를 고려한다. 이러한 인간의 인지적인 효과들을 고려하기 위하여 본 논문에서는 움직임 패턴을 모델링하고 Hedge 알고리듬을 사용하여 움직임 패턴을 결정하는 기법을 개발한다. 그 다음, 제안한 움직임 패턴과 기존의 visual saliency와의 결합을 통하여 인간 시각 인지 모델을 수립한다. 제안된 인간 시각 인지 모델을 구현하기 위하여 기존의 foveation filtering 방법을 확장한다. 시각적 자극이 덜한 지역만을 부드럽게(smoothing)하는 기존의 foveation filtering 기법과 비교하여 제안하는 foveation filtering 기법은 인간 시각 인지 모델에 따라 지역적으로 부드럽게 또는 지역적 특성을 향상시킴으로써, 시각적 자극이 덜한 지역에서 줄여진 대역폭을 효과적으로 시각적 자극이 큰 지역에서 사용하도록 이동 시킬 수 있는 장점이 있다. 제안된 방법의 성능은 전반적인 비디오 화질을 만족할 뿐만 아니라 인간이 인지하는 화질의 품질을 12%~44% 향상시킨다.

• 한국통신학회논문지
• /
• 제22권4호
• /
• pp.706-713
• /
• 1997

In this paper, we propose a band stop filter(BSF) for reducing drag-like effect of the low pass filter(LPF), a block by block adaptive filtering method, and a motion adaptive filtering method, which show better results in terms of PSNR or human visual perception compared to the conventional method using LPF. The BSF improves the draglike effects of the low pass filter by passing temporal high frequency components of video sequences which correspond to objects with large motion. The proposed adaptive methods also improve the conventional adaptive filtering by modifying the conventional algorithm and applying the algorithms for small blocks. The simulation results show that the proposed filtering methods show better results in terms of PSNR and subjective tests in most cases. Also in case of block by block adaptive filtering, it is verified that the application of the algorithm for smaller block gives better results.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.65-71
• /
• 2024

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.

• 로봇학회논문지
• /
• 제2권2호
• /
• pp.129-136
• /
• 2007

This paper introduces a position-based robust visual servoing method which is developed for operation of a human-like robot with two arms. The proposed visual servoing method utilizes SIFT algorithm for object detection and CAMSHIFT algorithm for object tracking. While the conventional CAMSHIFT has been used mainly for object tracking in a 2D image plane, we extend its usage for object tracking in 3D space, by combining the results of CAMSHIFT for two image plane of a stereo camera. This approach shows a robust and dependable result. Once the robot's task is defined based on the extracted 3D information, the robot is commanded to carry out the task. We conduct several position-based visual servoing tasks and compare performances under different conditions. The results show that the proposed visual tracking algorithm is simple but very effective for position-based visual servoing.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1671-1679
• /
• 2004

This study has proposed visual-feature extraction methods for each band in wavelet domain with both spatial frequency features and multi resolution features. In addition, it has brought forward similarity measurement method using fuzzy theory and new color feature expression method taking advantage of the frequency of the same color after color quantization for reducing quantization error, a disadvantage of the existing color histogram intersection method. Experiments are performed on a database containing 1,000 color images. The proposed method gives better performance than the conventional method in both objective and subjective performance evaluation.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• 반도체디스플레이기술학회지
• /
• 제16권2호
• /
• pp.1-8
• /
• 2017

The visual inspection of electronic parts consists of two steps: automatic visual inspection and verification inspection. In the stage of a verification inspection, the human inspector sequentially inspects all the areas which detected in the automatic inspection. In this study, we propose an algorithm to determine the order of verification inspection by Bayes inference well known in the field of machine learning. This is a method of prioritizing a region estimated to have a high probability of defect using experience data of past inspection. This algorithm was applied to the visual inspection of ultraviolet filters to verify its effectiveness. As a result of the comparison experiment, it was confirmed that the verification inspection can be completed 30% of the conventional method by adapting proposed algorithm.

• The Korean Journal of Pain
• /
• 제6권1호
• /
• pp.55-59
• /
• 1993

Using a visual analogue scale, we compare the effect of patient-controlled analgesia and conventional intramuscular opioid regimen in 68 patients undergoing lower abdominal or gynecological surgery. We also recorded the incidence of side effects. We checked visual analogue scale 4 hours interval for 30 cases managed by patient-controlled analgesia and 38 cases of conventional intramuscular opioid group managed by obstetrician. We maintained fentanyl $0.33{\mu}g/kg/hr$ and set self administrable bolus dose $5.0{\mu}g$(lockout interval: 15 min) in patient-controlled analgesia group. Conventional intramuscular bolus injection group were administered meperidine 50 mg for 4 hour interval. Mean visual analogue scale scores obtained by patient-controlled analgesia group and intramuscular bolus injection group were $2.49{\pm}0.67$ and $4.53{\pm}1.28$(p<0.05). Side effects such as; no significant incidence of respiratory depression, urinary retention, postural hypotension, nausea, vomiting and pruritus were developed by either group. These results suggest that patient-controlled analgesia was more effective method compared with conventional intraumuscular opioid injection regimen for post-operative pain management.

• 전자공학회논문지B
• /
• 제30B권12호
• /
• pp.67-72
• /
• 1993

An adaptive block truncation coding(BTC) using human visual system(HVS) is proposed. To reduce visible blocking effect at sensitive area in HVS. a new category classification coefficient is proposed. The categroy classification coefficient was derived by combining the modified HVS and standard deviation. By computer simulations, we showed that the proposed method reduced blocking effect at low bit rate coding more than the conventional Hui's method.