• 한국멀티미디어학회논문지
• /
• 제15권2호
• /
• pp.195-203
• /
• 2012

본 논문은 다중센서 영상을 이용한 결정 융합 기반의 지상 표적 분류 알고리즘 및 특징 추출 기법을 제안한다. 표적의 인식률 향상을 위하여 가중 투표 방법을 적용함으로써 개별 분류기로부터 획득된 결과를 융합하였다. 또한 개별 센서 영상 내에 속한 표적을 분류하기 위해 CCD 영상으로부터 획득한 CM 영상의 밝기 차이와 FLIR 영상 내 표적의 윤곽선 정보 및 차량과 포탑의 너비 비율을 이용하여 스케일과 회전변화에 강인한 특징들을 추출하였다. 마지막으로 실험을 통하여 본 논문에서 제안한 지상 표적 분류 알고리즘과 특징 추출 기법에 대한 성능을 검증한다.

• 한국정밀공학회지
• /
• 제32권9호
• /
• pp.787-792
• /
• 2015

Recently, 3D printing technology is a hot issue in various industrial fields. According to the user's application, it allows for the free form fabrication method to be utilized in a wide range. The powder based fusion technique is one of the 3D printing methods. When using this method it is possible to apply the various binder jetting techniques such as piezo, thermal bubble jet, dispenser and so on. In this paper, a multi thermal bubble ink jet was integrated for jetting of powder binding material and developing a power fused 3D printing system. For high quality 3D printing parts, it needs an analysis and evaluation of the behavior of the thermal bubble ink jet head. In the experiment, a correlation between jetting binder quantity and layer thickness of powder was investigated, and a 3D part model was fabricated, which was used by measuring the scale factor.

• 한국초전도ㆍ저온공학회논문지
• /
• 제23권4호
• /
• pp.10-13
• /
• 2021

Recently, cable conductors composed of numerous coated conductors have been developed to transport huge current for large-scale applications, for example accelerators and fusion reactors. Various cable conductors such as CORC (Conductor on round core), Roebel Cable, and TSTC (Twisted stacked tape cable) have been designed and tested to apply for large-scale applications. But, these cable conductors cannot improve the engineering critical current density (J_e) because they are made by simple stacking of coated conductors. In this study, multi-HTS (High temperature superconductor) layers on one substrate (MHOS) wire was fabricated to increase the engineering critical current density by using the exfoliation of superconducting layer from substrate and silver diffusion bonding method. By the repetition of these processes, the 10 m long 6-layer MHOS conductor was successfully fabricated without any intermediate layers like buffer or solder. 6-layer MHOS conductor exhibited a high critical current of 2,460A/12mm-w. and high engineering critical current density of 1,367A/mm² at liquid nitrogen temperature.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.79-82
• /
• 2005

Recently the necessity of road data is still being increased in industrial society, so there are many repairing and new constructions of roads at many areas. According to the development of government, city and region, the update and acquisition of road data for GIS (Geographical Information System) is very necessary. In this study, the fusion method with range data(3D Ground Coordinate System Data) and Intensity data in stand alone LiDAR data is used for road extraction and then digital image processing method is applicable. Up to date Intensity data of LiDAR is being studied. This study shows the possibility method for road extraction using Intensity data. Intensity and Range data are acquired at the same time. Therefore LiDAR does not have problems of multi-sensor data fusion method. Also the advantage of intensity data is already geocoded, same scale of real world and can make ortho-photo. Lastly, analysis of quantitative and quality is showed with extracted road image which compare with I: 1,000 digital map.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.653-669
• /
• 2024

Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.

• Nuclear Engineering and Technology
• /
• 제44권6호
• /
• pp.673-682
• /
• 2012

Three dimensional atom probe tomography (3D APT) is applied to characterize the dissimilar metal joint which was welded between the Ni-based alloy, Alloy 690 and the low alloy steel, A533 Gr. B, with Alloy 152 filler metal. While there is some difficulty in preparing the specimen for the analysis, the 3D APT has a truly quantitative analytical capability to characterize nanometer scale particles in metallic materials, thus its application to the microstructural analysis in multi-component metallic materials provides critical information on the mechanism of nanoscale microstructural evolution. In this study, the procedure for 3D APT specimen preparation was established, and those for dissimilar metal weld interface were prepared near the fusion boundary by a focused ion beam. The result of the analysis in this study showed the precipitation of chromium carbides near the fusion boundary between A533 Gr. B and Alloy 152.

• Journal of Korean Neurosurgical Society
• /
• 제42권4호
• /
• pp.251-257
• /
• 2007

Objective : This multi-center clinical study was designed to determine the long-term results of patients who received a one-level posterior lumbar interbody fusion with expandable cage ($Tyche^{(R)}$ cage) for degenerative spinal diseases during the same period in each hospital. Methods : Fifty-seven patients with low back pain who had a one-level posterior lumbar interbody fusion using a newly designed expandable cage were enrolled in this study at five centers from June 2003 to December 2004 and followed up for 24 months. Pain improvement was checked with a Visual Analogue Scale (VAS) and their disability was evaluated with the Oswestry Disability Index. Radiographs were obtained before and after surgery. At the final follow-up, dynamic stability, quality of bone fusion, interveretebral disc height, and lumbar lordosis were assessed. In some cases, a lumbar computed tomography scan was also obtained. Results : The mean VAS score of back pain was improved from 6.44 points preoperatively to 0.44 at the final visit and the score of sciatica was reduced from 4.84 to 0.26. Also, the Oswestry Disability Index was improved from 32.62 points preoperatively to 18.25 at the final visit. The fusion rate was 92.5%. Intervertebral disc height, recorded as $9.94{\pm}2.69\;mm$ before surgery was increased to $12.23{\pm}3.31\;mm$ at postoperative 1 month and was stabilized at $11.43{\pm}2.23\;mm$ on final visit. The segmental angle of lordosis was changed significantly from $3.54{\pm}3.70^{\circ}$ before surgery to $6.37{\pm}3.97^{\circ}$ by 24 months postoperative, and total lumbar lordosis was $20.37{\pm}11.30^{\circ}$ preoperatively and $24.71{\pm}11.70^{\circ}$ at 24 months postoperative. Conclusion : There have been no special complications regarding the expandable cage during the follow-up period and the results of this study demonstrates a high fusion rate and clinical success.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5112-5129
• /
• 2019

Image enhancement is a challenging problem in the field of image processing, especially low-light color images enhancement. This paper proposed a robust and comprehensive enhancement method based several points. First, the idea of bright channel is introduced to estimate the illumination map which is used to attain the enhancing result with Retinex model, and the color constancy is keep as well. Second, in order eliminate the illumination offsets wrongly estimated, morphological closing operation is used to modify the initial estimating illumination. Furthermore, in order to avoid fabricating edges, enlarged noises and over-smoothed visual features appearing in enhancing result, a multi-scale closing operation is used. At last, in order to avoiding the haloes and artifacts presented in enhancing result caused by gradient information lost in previous step, guided filtering is introduced to deal with previous result with guided image is initial bright channel. The proposed method can get good illumination map, and attain very effective enhancing results, including dark area is enhanced with more visual features, color natural and constancy, avoiding artifacts and over-enhanced, and eliminating Incorrect light offsets.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.739-748
• /
• 2014

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.