• Journal of Information Technology Applications and Management
• /
• 제25권2호
• /
• pp.41-52
• /
• 2018

This paper presents a method for accurate camera self-calibration based on SIFT Feature Detection and image quality assessment. We performed image quality assessment to select high quality images for the camera self-calibration process. We defined high quality images as those that contain little or no blur, and have maximum contrast among images captured within a short period. The image quality assessment includes blur detection and contrast assessment. Blur detection is based on the statistical analysis of energy and standard deviation of high frequency components of the images using Discrete Cosine Transform. Contrast assessment is based on contrast measurement and selection of the high contrast images among some images captured in a short period. Experimental results show little or no distortion in the perspective view of the images. Thus, the suggested method achieves camera self-calibration accuracy of approximately 93%.

• 한국멀티미디어학회논문지
• /
• 제12권6호
• /
• pp.815-823
• /
• 2009

Most of existing watermarking schemes insert and extract a watermark, focusing on the visual conservation of an original image. However, existing watermarking schemes could be difficult for a watermark detection in case of various distortion caused by display-capture devices. Therefore, we propose a new display-capture based mobile watermarking scheme. The proposed watermarking scheme is a new concept for embedding a watermark, which uses the generated image instead of a given original image. For effective watermark decoding, we also present a method for detecting the background image whose error bit can not be corrected because of various heavy distortion and for avoiding it from the decoding process. For this scheme, we adopt distortion coefficients of camera calibration when we separate a background image from a captured image. For finding available correction bits of ECC through the decoding process, we capture 30,000 images and then calculate the separation ratio of a background image and the average error bits per an image. As experimental result, the separation ratio of a background image is about 96.5% in 30,000 captured image. And the false alarm ratio shows about $5.18{\times}10^{-4}$ in the separated background image. And also we can confirm the availability of real-time processing because the mean execution time is about 82ms per an image for capturing and decoding.

• 한국멀티미디어학회논문지
• /
• 제10권6호
• /
• pp.726-736
• /
• 2007

In this paper, real-time image scanning system using linescan cameras is designed. The system is specially designed to diagnose and analyse the conditions of tunnels such as crack widths through the captured images. The system consists of two major parts, the image acquisition system and the image merging system. To save scanned image data into storage media in real-time, the image acquisition system has been designed with two different control and management modules. The control modules are in charge of controlling the hardware device and the management modules handle system resources so that the scanned images are safely saved to the magnetic storage devices. The system can be mounted to various kinds of vehicles. After taking images, the image merging system generates extended images by combining saved images. Several tests are conducted in laboratory as well as in the field. In the laboratory simulation, both systems are tested several times and upgraded. In the field-testing, the image acquisition system is mounted to a specially designed vehicle and images of the interior surface of the tunnel are captured. The system is successfully tested in a real tunnel with a vehicle at the speed of 20 km/h. The captured images of the tunnel condition including cracks are vivid enough for an expert to diagnose the state of the tunnel using images instead of seeing through his/her eyes.

• 한국멀티미디어학회논문지
• /
• 제19권4호
• /
• pp.725-735
• /
• 2016

High-resolution satellite images are used in the fields of mapping, natural disaster forecasting, agriculture, ocean-based industries, infrastructure, and environment, and there is a progressive increase in the development and demand for the applications of high-resolution satellite images. Users of the satellite images desire accurate quality of the provided satellite images. Moreover, the distinguishability of each image captured by an actual satellite varies according to the atmospheric environment and solar angle at the captured region, the satellite velocity and capture angle, and the system noise. Hence , NIIRS must be measured for all captured images. There is a significant deficiency in professional human resources and time resources available to measure the NIIRS of few hundred images that are transmitted daily. Currently, NIIRS is measured every few months or even few years to assess the aging of the satellite as well as to verify and calibrate it [3]. Therefore, we develop an algorithm that can measure the national image interpretability rating scales (NIIRS) of a typical satellite image rather than an artificial target satellite image, in order to automatically assess its quality. In this study, the criteria for automatic edge region extraction are derived based on the previous works on manual edge region extraction [4][5], and consequently, we propose an algorithm that can extract the edge region. Moreover, RER and H are calculated from the extracted edge region for automatic edge region extraction. The average NIIRS value was measured to be 3.6342±0.15321 (2 standard deviations) from the automatic measurement experiment on a typical satellite image, which is similar to the result extracted from the artificial target.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• 한국산업융합학회 논문집
• /
• 제23권2_2호
• /
• pp.255-261
• /
• 2020

We consider the problem of autonomously flying a quadcopter in indoor environments. Navigation in indoor settings poses two major issues. First, real time recognition of the marker captured by the camera. Second, The combination of the distributed images is used to determine the position and orientation of the quadcopter in an indoor environment. We autonomously fly a miniature RC quadcopter in small known environments using an on-board camera as the only sensor. We use an algorithm that combines data-driven image classification with image-combine techniques on the images captured by the camera to achieve real 3D localization and navigation.

• Journal of Multimedia Information System
• /
• 제4권1호
• /
• pp.43-50
• /
• 2017

In this paper, we propose a method which detects the nose and face of certain human by using the depth image. The proposed method has advantages of the low computational complexity and the high accuracy even in dark environment. Also, the detection accuracy of nose and face does not change in various postures. The proposed method first locates the locally protruding part from the depth image of the human body captured through the depth camera, and then confirms the nose through the depth characteristic of the nose and surrounding pixels. After finding the correct pixel of the nose, we determine the region of interest centered on the nose. In this case, the size of the region of interest is variable depending on the depth value of the nose. Then, face region can be found by performing binarization using the depth histogram in the region of interest. The proposed method can detect the nose and the face accurately regardless of the pose or the illumination of the captured area.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.255-257
• /
• 2005

This paper describes a method for obstacle avoidance and map building for mobile robots using one CCD camera. The captured image from one camera has the feature that some parts where focused look fine but the other parts look blear (this is the out-focusing effect). Using this feature a mobile robot can find obstacles in his way from the captured image. After Processing the image, a robot can not only determine whether an obstacle is in front of him or not, but also calculate the distance from obstacles based on image data and the focal distance of its camera lens. Finally, robots can avoid the obstacle and build the map using this calculated data.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.829-830
• /
• 2008

In modern days, many of the images are captured by using various devices, such as PDA, digital camera, or cell phone camera. Because all these devise have a limited dynamic range, images captured in real world scenes with high dynamic ranges usually exhibit poor visibility and low contrast, which may make important image features lost or hard to tell by human viewers. In this paper, the efficient color image enhancement method is presented. Experimental result show that the proposed method yields better performance of color enhancement over the previous work for test color images.

• 마이크로전자및패키징학회지
• /
• 제24권2호
• /
• pp.55-59
• /
• 2017

본 논문은 마이크로 BGA(Ball Grid Array)의 3차원 형상 검사를 위한 광학적 방법에 관한 것으로, 특히, LED를 공간적으로 배치한 광원과 경면반사특성을 이용하였다. 이를 위해 비전시스템을 구성하여 BGA의 반사영상을 취득한 후, 영상처리를 통하여 반사된 LED 점광원의 위치를 추출하여 형상검사에 이용하였다. 또한, 영상에 포함된 복수개의 BGA에 대한 상대적 위치의 통계치를 이용하여 BGA 3차원 형상의 결함을 판단하는 방법을 제안하였고, 실험을 통하여 제안된 방법의 효용성을 보였다.