• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.2
• /
• pp.97-104
• /
• 1999

Digital elevation models(DEMs) represent an important data base for orthophoto generation The quality of a DEM depends on the geometrical accuracy of the original point or line data. This study analyzes the effects of grid space and scanning resolution in DEM creation with image matching method. The less standard deviation of DEM error was introduced when we adopted small grid space, but no effects in scanning resolution. Based on the bias error analysis of the DEM, we found that the error of a large scale of aerial photograph was bigger than that of a small scale case, and that such error mainly came from the closed area in large scale photographs. In order to reduce the closed area, the experiment has been conducted using multi scale and different overlap of aerial photo images. The result shows that the size of closed area and the shaded area has been dramatically decreased due to the adoption of multi scale aerial images instead of a couple of stereo images.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.475-481
• /
• 2014

The aim of this work was to develop the gamma camera system for small animal gamma imaging and environmental radiation monitoring imaging using a parallel hole collimator and pinhole collimator. The small gamma camera system consists of a CsI(Tl) scintillation crystal with 6 mm in thickness and $50{\times}50mm$ in area coupled with a Hamamatsu H8500C PSPMT, are resistive charge divider, pre-amplifiers, charge amplifiers, nuclear instrument modules (NIMs), an analog to digital converter and a computer for control and display. We have developed a radiation monitoring system composed of a combined pinhole gamma camera and a charge-coupled devices (CCD) camera. The results demonstrated that the parallel hole collimator and pinhole collimator gamma camera designed in this study could be utilized to perform small animal imaging and environmental radiation monitoring system. Consequently in this paper, we proved that our gamma detector system is reliable for a gamma camera which can be used as small animal imaging and environmental radiation monitoring system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.23-31
• /
• 2012

This paper proposes a motion estimation-based super resolution algorithm to restore input low-resolution images of large movement into a super-resolution image. It is difficult to find the sub-pixel motion estimation in images of large movement compared to typical experimental images. Also, it has disadvantage which have high computational complexity to find reference images and candidate images using general motion estimation method. In order to solve these problems for the traditional two-dimensional motion estimation using the proposed registration threshold that satisfy the conditions based on the reference image is determined. Candidate image with minimum weight among the best candidates for super resolution images, the restoration process to proceed with to find a new image registration algorithm is proposed. According to experimental results, the average PSNR of the proposed algorithm is 31.89dB and this is better than PSNR of traditional super-resolution algorithm and it also shows improvement of computational complexity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.12
• /
• pp.2636-2641
• /
• 2010

To support anti-collision between ship to ship and sea-search and sea-rescue work, ship automatic identification system(AIS) that can both send and receive messages between ship and VTS Traffic control have been adopted. And port control system can control traffic vessel service which is co-operated with AIS. For more efficient traffic vessel service, ship recognition and display system is required to cooperated with AIS. In this paper, we propose ship detection system which is co-operated with AIS by using background estimation based on image processing for on the sea or harbor image extracted from camera. We experiment with on the sea or harbor image extracted from real-time input image from camera. By computer simulation and real world test, the proposed system show more effective to ship monitoring.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.375-378
• /
• 2019

최근 딥러닝과 머신러닝 기법이 소프트웨어의 성능 향상에 도움이 되는 것이 입증됨에 따라, 의료 영상 진단 보조 소프트웨어를 개발하기 위한 시도가 활발해 지고 있다. 그 중 캡슐내시경은 소장 소화기관을 관찰할 수 있는 초소형 의료기기로, 기존의 내시경 검사와 다르게 이물감이 느껴지지 않고 의료보험 적용으로 최근 들어 널리 이용되고 있다. 일반적으로 캡슐 내시경은 8 시간 동안 소화기간을 촬영하며, 한 번의 검사 결과로 생성된 동영상 데이터 셋은 수 만장의 이미지를 포함하기 때문에, 방대한 양의 이미지들을 효율적으로 관리하기 위한 체계가 필요하다. 특히, 방대한 양의 캡슐내시경 이미지를 학습하는 경우, 수 만장의 이미지 속에서 유의미한 특징(촬영정보, 의사소견, 환자정보, 병변의 위치 및 크기 등)을 추출해내야 하므로 학습 데이터 레이블링을 위한 정보를 정확히 추출해야 하는 작업이 요구된다. 따라서 본 논문에서는 캡슐내시경 영상을 학습할 때, 학습 데이터 레이블 정보를 체계적으로 구축할 수 있게 하는 레이블 정보 추출 기법을 제안하고자 한다. 제안하는 기법은 병원에서 14년간 수집된 총 340명의 캡슐내시경 데이터(약 1,700 만장의 이미지)를 토대로 영상데이터를 구조적으로 분석하여 유의미한 정보를 추출하고 노이즈 데이터를 제거한 뒤, 빅데이터 저장소에 적재할 수 있음을 보였다.

• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.353-359
• /
• 2006

Image frame analysis is a conventional way of evaluating loop detector's performance. In image frame analysis, the time to evaluate performance is linearly proportional to the number of evaluated subjects, and the results can be subjective, depending on operator's personal evaluation standards and physical condition. Also, this method is often inferior in accuracy to that provided by the evaluated devices. Therefore, it is critical to develop a portable standard system which has better accuracy and more objectivity in evaluating vehicle detectors. This paper discusses function and reliability of tape-switch detector, which can be a replacement for image frame analysis, for effectively measuring traffic volume, speed, and occupancy.

• Progress in Medical Physics
• /
• v.14 no.3
• /
• pp.167-174
• /
• 2003

In the radiation treatment planning (RTP) process, especially for stereotactic radiosurgery (SRS), knowing the exact volume and shape and the precise position of a lesion is very important. Sometimes X-ray projection images, such as angiograms, become the best choice for lesion identification. However, while the exact target position can be acquired by bi-projection images, 3D target reconstruction from bi-projection images is considered to be impossible. The aim of this study was to reconstruct the 3D target volume from multiple projection images. It was assumed that we knew the exact target position in advance, and all processes were performed in Target Coordinates, where the origin was the center of the target. We used six projections: two projections were used to make a Reconstruction Box and four projections were for image acquisition. The Reconstruction Box was made up of voxels of 3D matrices. Projection images were transformed into 3D in this virtual box using a geometric back-projection method. The resolution and the accuracy of the reconstructed target volume were dependent on the target size. An algorithm was applied to an ellipsoid model and a horseshoe-shaped model. Projection images were created geometrically using C program language, and reconstruction was also performed using C program language and Matlab ver. 6(The Mathwork Inc., USA). For the ellipsoid model, the reconstructed volume was slightly overestimated, but the target shape and position proved to be correct. For the horseshoe-shaped model, reconstructed volume was somewhat different from the original target model, but there was a considerable improvement in determining the target volume.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.687-693
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea. showed: (1) average RMSE error of the approach was 0.435 pixel; (2) the average number of matching points was over 25,573; (3) the average processing time was 4.2 min per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.