• 한국안전학회지
• /
• 제11권1호
• /
• pp.133-141
• /
• 1996

In spite of a tendency automatizing manaufacturing processes, since power presses are highly repetitive at high speeds, they have still been using to a large extent in many industries. More often than not, press workers have to make decisions whether work materials are located well or not, they should rearrange them or not, and their bodies would be safe or not. If the decision would be wrong, of course, they cause severe damages to human workers so that many workers haven't been willing to work with them. However, with the help of computer technologies, it would be possible to aid the press workers' decisions, and to allow or prohibit them from inserting their hands between slide rams and dies. Thus, this research was aimed to evaluate and analyze possibilities of applying Image Processing Techniques for prevention of press accidents. Through a series of procedures including Capturing work sites and material, Image Enhancement, Contouring, and Edge Finding, work characteristics were obtained and analyzed. The results showed that there were somewhat differences in image characteristics between accident-induced work scenes and accident-free ones. Consequently, if the image analyses are well carried out in real time, they would give a successful help to human press workers.

• Journal of the Korean Physical Society
• /
• 제73권12호
• /
• pp.1821-1826
• /
• 2018

Uniformity is a key feature of state-of-the-art infrared focal planed array (IRFPA) and infrared imaging system. Unlike traditional infrared telescope facility, a ground-based infrared radiant characteristics measurement system with an IRFPA not only provides a series of high signal-to-noise ratio (SNR) infrared image but also ensures the validity of radiant measurement data. Normally, a long integration time tends to produce a high SNR infrared image for infrared radiant characteristics radiometry system. In view of the variability of and uncertainty in the measured target's energy, the operation of switching the integration time and attenuators usually guarantees the guality of the infrared radiation measurement data obtainted during the infrared radiant characteristics radiometry process. Non-uniformity correction (NUC) coefficients in a given integration time are often applied to a specified integration time. If the integration time is switched, the SNR for the infrared imaging will degenerate rapidly. Considering the effect of the SNR for the infrared image and the infrared radiant characteristics radiometry above, we propose a-wide-dynamic-range NUC algorithm. In addition, this essasy derives and establishes the mathematical modal of the algorithm in detail. Then, we conduct verification experiments by using a ground-based MWIR(Mid-wave Infared) radiant characteristics radiometry system with an Ø400 mm aperture. The experimental results obtained using the proposed algorithm and the traditional algorithm for different integration time are compared. The statistical data shows that the average non-uniformity for the proposed algorithm decreased from 0.77% to 0.21% at 2.5 ms and from 1.33% to 0.26% at 5.5 ms. The testing results demonstrate that the usage of suggested algorithm can improve infrared imaging quality and radiation measurement accuracy.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.251-254
• /
• 2001

본 논문에서는 Self Organizing Map을 이용하여 fMRI data를 분석해 보았다. fMRl (functional Magnetic Resonance Imaging)는 인간의 뇌에 대한 비 침투적 연구 방법 중 최근에 각광받고 있는 것이다. Motor task를 수행하고 있는 피험자로부터 image data를 얻어내어 SOM을 적용하여 clustering한 결과 motor cortex 영역이 뚜렷하게 clustering 되었음을 알 수 있었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.861-864
• /
• 1993

This research provides the results of a trial to generate the chaos by using nonlinear function constructed by fuzzy inference rules. The chaos generation function or chaotic behavior can be obtained by using Takagi-Sugeno fuzzy model with some constraint of the relationship of its parameters. Two examples are shown in this research. The first is simple example that construct of logistic image by fuzzy model. The second is more complicated one that provide the chaotic time series by non-linear autoregression based on fuzzy model. Simulated results are shown in these examples.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 지구물리와물리탐사
• /
• 제24권4호
• /
• pp.171-179
• /
• 2021

시간영역 유도분극 탐사 자료로부터 Cole-Cole 변수를 추정하는 2차원 역산법을 개발하였다. 모든 유도분극 과도 전위 자료를 역산하여 전기비저항, 충전성, 완화 시간 및 주파수 승수 등의 2D Cole-Cole 변수를 추정하였다. 개발된 역산법은 2단계로 구성된다. 우선 음의 겉보기 충전성 문제를 피하기 위하여 측정된 유도분극 반응을 전류 주입 중 겉보기 전기비저항으로 변환하였다. 1단계 역산에서는 시간에 따라 항상 증가하는 전기비저항을 추정하는 4차원 역산을 통하여 각 역산 블록에서의 전기비저항 시계열 모델을 구축하였다. 2단계 역산에서는 4차원 역산에서 얻어진 전기비저항 시계열 자료를 역산하여 Cole-Cole 변수를 추정하였다. 이때 격자 탐색법을 통하여 참값에 근접한 초기 모델을 설정하는 방법을 통하여 신속한 역산이 가능하였다. 마지막으로 수치 자료에 대한 역산 실험을 통해 개발된 알고리즘이 Cole-Cole 지하 모델을 효과적으로 영상화할 수 있음을 확인하였다.

• 대한원격탐사학회지
• /
• 제37권6_3호
• /
• pp.1931-1942
• /
• 2021

최근 고해상도 광학 위성영상의 활용성이 강조되면서 이를 이용한 지표 모니터링 연구가 활발히 수행되고 있다. 그러나 고해상도 위성영상은 낮은 시간 해상도에서 획득되기 때문에 그 활용성에 한계가 있다. 이러한 한계를 보완하기 위해 서로 다른 시간 및 공간 해상도를 갖는 다중 위성영상을 융합해 높은 시공간 해상도의 합성 영상을 생성하는 시공간 자료 융합을 적용할 수 있다. 기존 연구에서는 중저해상도의 위성영상을 대상으로 시공간 융합 모델이 개발되어 왔기 때문에 고해상도 위성영상에 대한 기개발된 융합 모델의 적용성을 평가할 필요가 있다. 이를 위해 이 연구에서는 KOMPSAT-3A 영상과 Sentinel-2 영상을 대상으로 기개발된 시공간 융합 모델의 적용성을 평가하였다. 여기에는 예측을 위해 사용하는 정보가 다른 Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM)과 Spatial Time-series Geostatistical Deconvolution/Fusion Model (STGDFM)을 적용하였다. 연구 결과, 시간적으로 연속적인 반사율 값을 결합하는 STGDFM의 예측 성능이 ESTARFM 보다 높은 것으로 나타났다. 특히 KOMPSAT 영상의 낮은 시간 해상도로 같은 시기에서 KOMPSAT 및 Sentinel-2 영상을 동시에 획득하기 어려운 경우, STGDFM의 예측 성능 향상이 더욱 크게 나타났다. 본 실험 결과를 통해 연속적인 시간 정보를 결합해 상대적으로 높은 예측 성능을 가지는 STGDFM을 이용해 낮은 재방문 주기로 인한 고해상도 위성영상의 한계를 보완할 수 있음을 확인하였다.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.690-706
• /
• 2021

Classification is a substantial operation in data mining, and each element is distributed taking into account its feature values in the corresponding class. Metaheuristics have been widely used in attempts to solve satellite image classification problems. This article proposes a hybrid approach, the flower pigeons-inspired optimization algorithm (FPIO), and the local search method of the flower pollination algorithm is integrated into the pigeon-inspired algorithm. The efficiency and power of the proposed FPIO approach are displayed with a series of images, supported by computational results that demonstrate the cogency of the proposed classification method on satellite imagery. For this work, the Davies-Bouldin Index is used as an objective function. FPIO is applied to different types of images (synthetic, Alsat-2B, and Sentinel-2). Moreover, a comparative experiment between FPIO and the genetic algorithm genetic algorithm is conducted. Experimental results showed that GA outperformed FPIO in matters of time computing. However, FPIO provided better quality results with less confusion. The overall experimental results demonstrate that the proposed approach is an efficient method for satellite imagery classification.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.399-408
• /
• 2020

The construction industry is suffering from aging workers, frequent accidents, as well as low productivity. With the rapid development of information technologies in recent years, automatic construction, especially automatic cranes, is regarded as a promising solution for the above problems and attracting more and more attention. However, in practice, limited by the complexity and dynamics of construction environment, manual inspection which is time-consuming and error-prone is still the only way to recognize the search object for the operation of crane. To solve this problem, an image-processing-based automated object recognition approach is proposed in this paper, which is a fusion of Convolutional-Neutral-Network (CNN)-based and traditional object detections. The search object is firstly extracted from the background by the trained Faster R-CNN. And then through a series of image processing including Canny, Hough and Endpoints clustering analysis, the vertices of the search object can be determined to locate it in 3D space uniquely. Finally, the features (e.g., centroid coordinate, size, and color) of the search object are extracted for further recognition. The approach presented in this paper was implemented in OpenCV, and the prototype was written in Microsoft Visual C++. This proposed approach shows great potential for the automatic operation of crane. Further researches and more extensive field experiments will follow in the future.

• Current Optics and Photonics
• /
• 제8권5호
• /
• pp.463-471
• /
• 2024

Multimode fibers (MMFs) possess high information throughput and small core diameter, making them highly promising for applications such as endoscopy and communication. However, modal dispersion hinders the direct use of MMFs for image transmission. By training neural networks on time-series waveforms collected from MMFs it is possible to reconstruct images, transforming blurred speckle patterns into recognizable images. This paper proposes a fully convolutional neural-network model, MSMDFNet, for image restoration in MMFs. The network employs an encoder-decoder architecture, integrating multiscale convolutional modules in the decoding layers to enhance the receptive field for feature extraction. Additionally, attention mechanisms are incorporated from both spatial and channel dimensions, to improve the network's feature-perception capabilities. The algorithm demonstrates excellent performance on MNIST and Fashion-MNIST datasets collected through MMFs, showing significant improvements in various metrics such as SSIM.