• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1074-1081
• /
• 2007

This paper presents a method for real-time face detection and tracking which combined Adaboost and Camshift algorithm. Adaboost algorithm is a method which selects an important feature called weak classifier among many possible image features by tuning weight of each feature from learning candidates. Even though excellent performance extracting the object, computing time of the algorithm is very high with window size of multi-scale to search image region. So direct application of the method is not easy for real-time tasks such as multi-task OS, robot, and mobile environment. But CAMshift method is an improvement of Mean-shift algorithm for the video streaming environment and track the interesting object at high speed based on hue value of the target region. The detection efficiency of the method is not good for environment of dynamic illumination. We propose a combined method of Adaboost and CAMshift to improve the computing speed with good face detection performance. The method was proved for real image sequences including single and more faces.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.191-201
• /
• 2019

A fast and accurate integrated traffic object detection framework was proposed and developed, harnessing a computer-vision based deep-learning approach performing automatic object detections, a multi object tracking technology, and video pre-processing tools. The proposed method is capable of detecting traffic object such as autos, buses, trucks and vans from video recordings taken under a various kinds of external conditions such as stability of video, weather conditions, video angles, and counting the objects by tracking them on a real-time basis. By creating plausible experimental scenarios dealing with various conditions that likely affect video quality, it is discovered that the proposed method achieves outstanding performances except for the cases of rain and snow, thereby resulting in 98% ~ 100% of accuracy.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.114-125
• /
• 2002

In this paper, we are proposing a hierarchical segmentation method that first segments the video data into units of shots by detecting cut and dissolve, and then decides types of camera operations or object movements in each shot. In our previous work[1], each picture group is divided into one of the three detailed categories, Shot(in case of scene change), Move(in case of camera operation or object movement) and Static(in case of almost no change between images), by analysing DC(Direct Current) component of I(Intra) frame. In this process, we have designed two-stage hierarchical neural network with inputs of various multiple features combined. Then, the system detects the accurate shot position, types of camera operations or object movements by searching P(Predicted), B(Bi-directional) frames of the current picture group selectively and hierarchically. Also, the statistical distributions of macro block types in P or B frames are used for the accurate detection of cut position, and another neural network with inputs of macro block types and motion vectors method can reduce the processing time by using only DC coefficients of I frames without decoding and by searching P, B frames selectively and hierarchically. The proposed method classified the picture groups in the accuracy of 93.9-100.0% and the cuts in the accuracy of 96.1-100.0% with three different together is used to detect dissolve, types of camera operations and object movements. The proposed types of video data. Also, it classified the types of camera movements or object movements in the accuracy of 90.13% and 89.28% with two different types of video data.

• International Journal of CAD/CAM
• /
• v.4 no.1
• /
• pp.33-45
• /
• 2004

In this work, a rational procedure has been formulated for the selection of points approximating slice contours cut in LOM (Laminated Object manufacturing) with first order approximation. It is suggested that the number of points representing a slice contour can be 'minimised' or 'optmised' by equating the horizontal chordal deviation (HCD) to the user-defined surface form tolerance. It has been shown that such optimization leads to substantial reduction in slice height calculations and NC codes file size for cutting out the slices. Due to optimization, the number of contour points varies from layer to layer, so that points on successive layer contours have to be matched by four sided ruled surface patches and triangular patches. The technological problems associated with the cutting out of triangular patches have been addressed. A robust algorithm has been developed for the determination of slice height for optimum and arbitrary numbers of contour points with different strategies for error calculations. It has been shown that optimisation may even lead to detection and appropriate representation of elusive surface features. An index of optimisation has been defined and calculations of the same have been tabulated.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.78-85
• /
• 2012

This paper proposes an efficient algorithm to develop a 3D terrain tools which is essential in the development of 3D computer games. In particular, this paper proposes a cross detection technique to improve picking speed. In other words, this paper proposes a more efficient cross detection technique consisting of a ray and a parallelogram than a cross detection technique consisting of a ray and a triangle. So, we can confirm the faster picking speed. This paper uses a picking example among DirectX SDK samples to test it. In addition, this paper compares the number of function calls for cross detection using the existing techniques and the proposed technique. As a result, in this paper the proposed technique has fallen off to about a 50 percent than the existing techniques. And if it is calculated by times, in this paper the proposed technique was reduced to 1 to 2 seconds than the existing techniques. Additionally, in this paper 3D terrain tools are provide more improved algorithms for features such as texture splatting, height map control, object arrangement and realistic water effect. So, 3D terrain tools is available efficient in the development of real 3d computer games.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.7 no.4
• /
• pp.125-132
• /
• 1987

The bundle adjustment used in photogrammetric data reduction is based on the collinearity condition. Photogrammetry has been used in many non-topographic applications. Due to the necessities of having fiducial marks and knowing initial approximations for interior and exterior orientation elements in bundle adjustment, it cannot be applied when non-metric cameras are used. Marzan and Karara develop the DLT(Direct Linear Transformation) program which directly transforms comparator coordinates into object space coordinates without approximate values. In this paper, several modifications of original DLT program have been made for accuracy improvement in close-range photogrammetry using non-metric cameras. In modified program, gross error detection method and computation of exterior orientation elements are incorporated, and more iterations are introdued.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.265-278
• /
• 2019

Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) data help to enable rapid emergency responses through detection of the artificial and natural disasters occurring at night. The DNB data without correction of lunar irradiance effect distributed by Korea Ocean Science Center (KOSC) has advantage for rapid change detection because of direct receiving. In this study, radiance differences according to the phase of the moon was analyzed for urban and mountain areas in Korean Peninsula using the DNB data directly receiving to KOSC. Lunar irradiance correction algorithm was proposed for the change detection. Relative correction was performed by regression analysis between the selected pixels considering the land cover classification in the reference DNB image during the new moon and the input DNB image. As a result of daily difference image analysis, the brightness value change in urban area and mountain area was ${\pm}30$ radiance and below ${\pm}1$ radiance respectively. The object based change detection was performed after the extraction of the main object of interest based on the average image of time series data in order to reduce the matching and geometric error between DNB images. The changes in brightness occurring in mountainous areas were effectively detected after the calibration of lunar irradiance effect, and it showed that the developed technology could be used for real time change detection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.610-616
• /
• 2012

In this paper, we present a method to detect an object such as ship, rock and buoy from sea IR image for the safety navigation. To this end, we do the image smoothing first and the apply watershed algorithm to segment image into subregions. Since watershed algorithm almost always produces over-segmented regions, it requires posterior merging process to get meaningful segmented regions. We propose an efficient merger algorithm that requires only two times of direct access to the pixels regardless of the number of regions. Also by analyzing IR image obtained from sea environments, we could find out that most horizontal edge come out from object regions. For the given input IR image we extract horizontal edge and eliminate isolated edges produced from background and noises by adopting morphological operator. Among the segmented regions, the regions that have horizontal edges are extracted as final results. Experimental results show the adequacy of the proposed method.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.1
• /
• pp.27-37
• /
• 1997

Internal combustion engine is the main source of environmental pollutants and therefore better technology is required to reduce harmful elements from the exhaust gases all over the world. Especially, harmful elements from the exhaust gases are caused by incomplete combustion of mixture inside the engine cylinder and this abnormal combustion like misfire or partial burning is the direct cause of the air pollution and engine performance degradation. the object of this research is to detect abnormal combustion like misfire and to keep the engine performance in the optimal operating state. Development of a new system therefore could be applied to a real car. To realize this, the spark-plug in a conventional ignition system is used as a misfire detection sensor and breakdown voltage is analyzed. In this research, bias voltage(about 3kV) was applied to the electrodes of spark-plug and breakdown voltage signal is obtained. This breakdown voltage signal is analyzed and found that a combustion phenomena in engine cylinder has close relationship with harmonic coefficient K which was introduced in this research. Newly developed combustion diagnostic method( breakdown voltage signal analysis) from this research can be used for the combustion diagnostic and combustion control system in an real car.