• 제목/요약/키워드: camera monitoring

검색결과 745건 처리시간 0.03초

Improvement of Statistics in Proton Beam Range Measurement by Merging Prompt Gamma Distributions: A Preliminary Study

  • Kim, Sung Hun;Park, Jong Hoon;Ku, Youngmo;Lee, Hyun Su;Kim, Young-su;Kim, Chan Hyeong;Jeong, Jong Hwi
    • Journal of Radiation Protection and Research
    • /
    • 제44권1호
    • /
    • pp.1-7
    • /
    • 2019
  • Background: To monitor proton beam in proton therapy, prompt gamma imaging systems are being developed by several research groups, and these systems are expected to improve the quality of the treatment and the patient safety. To apply the prompt gamma imaging systems into spot scanning proton therapy, the systems should be able to monitor the proton beam range of a spot with a small number of protons ( <$10^8$ protons), which is quite often not the case due to insufficient prompt gamma statistics. Materials and Methods: In the present study, we propose to improve prompt gamma statistics by merging the prompt gamma distributions of several individual spots into a new distribution. This proposal was tested by Geant4 Monte Carlo simulations for a multi-slit prompt gamma camera which has been developed to measure the proton beam range in the patient. Results and Discussion: The results show that the proposed method clearly enhance the statistical precision of beam range measurement. The accuracy of beam range verification is improved, within ~1.4 mm error, which is not achievable before applying the developed method. Conclusion: In this study, we tried to improve the statistics of the prompt gamma statistics by merging the prompt gamma distributions of multiple spots, and it was found that the merged distribution provided sufficient prompt gamma statistics and the proton beam range was determined accurately.

3D Point Cloud 기반 4D map 생성을 통한 노후화 시설물 유지 관리 방안 (The Maintenance and Management Method of Deteriorated Facilities Using 4D map Based on UAV and 3D Point Cloud)

  • 김용구;권종욱
    • 한국건축시공학회지
    • /
    • 제19권3호
    • /
    • pp.239-246
    • /
    • 2019
  • 국내 시설물의 노후화가 급속히 진행되고 있음에 따라 정부는 노후화 시설물의 안정성 검측과 유지관리에 대한 관심을 높이고 있다. 이에 본 연구는 대구광역시 서구 비산 4동/내당 2, 3동의 노후화 지역일대를 조사하고, 비행촬영을 통해 노후화 시설물에 대한 데이터를 획득하여 3D 지도를 구현하였다. 또한 3D 지도에 객관적/주관적 데이터를 추가적으로 기입함으로써 주민들이 쉽게 이해할 수 있으며, 관리자가 노후화 시설물에 대한 유지 보수 관리를 보다 수월하게 진행할 수 있는 4D 지도 생성 방안을 제시하였다.

적응화 평활화법을 이용한 다기능 마찰력 측정기의 성능 분석 (Analysis of Performance of Multi-functioned frictional force measuring instrument using adaptive smoothing)

  • 김태수;김광수
    • 한국정보전자통신기술학회논문지
    • /
    • 제12권2호
    • /
    • pp.113-119
    • /
    • 2019
  • 우리는 선행연구로 다기능 마찰력 측정기를 개발해 왔고 본 논문에서는 적응화 평활화 방법을 적용하여 마찰력 측정기의 성능을 개선하고자 하였으며, 스크래치 테스트를 통해 시편에 대한 마찰력과 마찰면의 모니터링 기능을 심도 있게 분석하였다. 일반적으로 강판을 가공하여 사용하고자 할 때 마찰을 줄이기 위해서 윤활유를 사용하지만, 윤활유는 환경오염의 큰 원인이기 때문에 본 연구에서는 윤활강판을 사용하였다. 특히, 윤활강판의 마찰계수는 유기, 무기 등의 시편의 종류 및 코팅층의 상태에 따라 변화하기 때문에 합금화 용융아연도금강판과 같은 다양한 시편에 대한 정밀한 실험을 통해 분석하였다. 이를 토대로 적응화 평활화법을 이용하여 잡음이 제거된 정확한 마찰계수를 측정할 수 있는 측정기의 성능을 향상시킬 수 있음을 검증하였다. 그 결과로서 마찰계수 0.16에 대하여 적응화 평활화법을 이용한 경우 저감률이 0.0417%임을 보였다.

딥러닝 기술을 이용한 넙치의 질병 예측 연구 (A Study on Disease Prediction of Paralichthys Olivaceus using Deep Learning Technique)

  • 손현승;임한규;최한석
    • 스마트미디어저널
    • /
    • 제11권4호
    • /
    • pp.62-68
    • /
    • 2022
  • 수산 양식장 질병 감염의 확산을 사전에 차단을 위해서는 양식장의 수질 환경 및 생육 어류의 상태를 실시간 모니터링하면서 어류의 질병을 예측하는 시스템이 필요하다. 어류 질병 예측의 기존 연구는 이미지 처리 기법이 대부분이었으나 최근에는 딥러닝 기법을 통한 질병 예측방법의 연구가 활발히 진행되고 있다. 본 논문에서는 수산 양식장에서 발생할 수 있는 넙치의 질병을 딥러닝 기술로 예측하는 방법에 대한 연구결과를 소개하고자 한다. 이 방법은 양식장에서 수집된 카메라 영상에 데이터 증강과 전처리 포함하여 질병 인식률의 성능을 높인다. 이것을 통해 질병 어류를 조기 발견으로 양식 어업에서 어류 집단 폐사 등 어업 재해를 예방하고 지역 수산 양식장으로 어류의 질병 확산 피해를 줄여 매출액 감소 차단될 것으로 기대한다.

사이클링 스마트웨어 제작을 위한 빕 팬츠 디자인 및 패턴 개발 (Development of Bib Pants Design and Pattern for Cycling Smart Wear)

  • 김윤영;유병하;이우재;이기광;김리라
    • 패션비즈니스
    • /
    • 제26권5호
    • /
    • pp.91-104
    • /
    • 2022
  • In this study, a cycling smart wear for measuring cycling posture and motion was developed using a three-dimensional motion analysis camera and an IMU inertial sensor. Results were compared according to parts to derive the optimal smart device attachment location, enabling correct posture measurement and cycle motion analysis to design a pattern. Conclusions were as follows: 1) 'S-T8' > 'S-T10' > 'S-L4' was the most significant area for each lumbar spine using a 3D motion analysis system with representative posture change (90°, 60°, 30°) to derive incisions and size specifications; 2) the part with the smallest relative angle change among significant section reference points during pattern design was applied as a reference point for attaching a cycling smart device to secure detachable safety of the device. Optimal locations for attaching the cycling device were the "S-L4" hip bone (Sacrum) and lumbar spine No. 4 (Lumbar 4th); 3) the most suitable sensor attachment location for monitoring knee induction-abduction was the anatomical location of the rectus femoris; 4) a cycling smart wear pattern was developed without incision in the part where the sensor and electrode passed. The wearing was confirmed with 3D CLO. This study aims to provide basic research on exercise analysis smart wear, to expand the smart cycling area that could only be realized with smart devices and smart watches attached to current cycles, and to provide an opportunity to commercialize it as cycling smart wear.

Synthetic data augmentation for pixel-wise steel fatigue crack identification using fully convolutional networks

  • Zhai, Guanghao;Narazaki, Yasutaka;Wang, Shuo;Shajihan, Shaik Althaf V.;Spencer, Billie F. Jr.
    • Smart Structures and Systems
    • /
    • 제29권1호
    • /
    • pp.237-250
    • /
    • 2022
  • Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

드론을 활용한 교면포장 품질관리 방안에 관한 연구 (A Study on the Quality Control Plan for Bridge Pavement using drones)

  • 송미화;길흥배
    • 한국융합학회논문지
    • /
    • 제13권5호
    • /
    • pp.1-8
    • /
    • 2022
  • 국내에서는 4차 산업혁명의 핵심기술인 드론 등을 이용하여 사회기반시설(SOC)를 디지털화하는 한국판뉴딜 정책을 추진 중에 있고, 국외에서도 열화상카메라 등 융복합센서를 드론에 탑재하여 다양한 산업 분야에서 활용하는 사례가 증가하고 있다. 본 연구에서는 고속도로 교면포장 공사에서 포장 품질을 개선하기 위하여 드론에 열화상 카메라를 탑재하여 포장 작업 구간에 대한 온도 측정 및 검증을 수행하였다. 기존의 방식인 레이저 온도계를 활용한다면 포장 온도를 부분적으로만 측정이 가능하지만, 제안된 방식을 활용하면 포장 작업 구간 전체에 대한 실시간 온도 모니터링 뿐 아니라 온도 분포 확인을 통한 균일성 검증이 가능한 것을 확인하였다. 제안된 방식을 현장에 적용한다면 도로 개방 시기(포장 표면온도≦40℃)에 대한 오판의 가능성을 낮춰줌에 따라 고속도로 포장 품질관리 제고 및 신속한 교통 개방 시기 결정이 가능할 것으로 기대된다.

쿼드콥터를 이용한 야생동물로부터 농작물보호 및 감시 시스템 개발 (Developed using Quadcopter Crop Protection and Monitoring System from Wild Animals)

  • 임현우;지민석;최원혁
    • 한국엔터테인먼트산업학회논문지
    • /
    • 제10권4호
    • /
    • pp.303-310
    • /
    • 2016
  • 인구증가와 산업의 발달로 고속도로, 국도, 철도 등의 개발에 의한 생태계 절단이 증가하여 이로 인한 야생돌물의 서식지 단편화 현상이 증가하였다. 그로 인하여 유해야생동물로 인한 피해가 속출하면서 국내서 금전적 보상을 통해 일부 피해 농가를 구제하는 등의 노력을 펼치고 있다. 하지만 피해사례 주민들은 이러한 야간순찰로 인해 밤잠을 자지 못하거나 기본적인 생활에 많은 어려움을 겪고 있다. 본 연구는 야생동물들의 생태와 습성에 대한 연구를 바탕으로 초음파 및 초저주파를 발생, 재생시켜 일정 범위 내 야생동물의 접근을 방지시키고 접근을 효과적으로 막을 수 있는 비연속적인 시스템에 대한 쿼드콥터를 연구 개발 하였다.

EPAR V2.0: AUTOMATED MONITORING AND VISUALIZATION OF POTENTIAL AREAS FOR BUILDING RETROFIT USING THERMAL CAMERAS AND COMPUTATIONAL FLUID DYNAMICS (CFD) MODELS

  • Youngjib Ham;Mani Golparvar-Fard
    • 국제학술발표논문집
    • /
    • The 5th International Conference on Construction Engineering and Project Management
    • /
    • pp.279-286
    • /
    • 2013
  • This paper introduces a new method for identification of building energy performance problems. The presented method is based on automated analysis and visualization of deviations between actual and expected energy performance of the building using EPAR (Energy Performance Augmented Reality) models. For generating EPAR models, during building inspections, energy auditors collect a large number of digital and thermal imagery using a consumer-level single thermal camera that has a built-in digital lens. Based on a pipeline of image-based 3D reconstruction algorithms built on GPU and multi-core CPU architecture, 3D geometrical and thermal point cloud models of the building under inspection are automatically generated and integrated. Then, the resulting actual 3D spatio-thermal model and the expected energy performance model simulated using computational fluid dynamics (CFD) analysis are superimposed within an augmented reality environment. Based on the resulting EPAR models which jointly visualize the actual and expected energy performance of the building under inspection, two new algorithms are introduced for quick and reliable identification of potential performance problems: 1) 3D thermal mesh modeling using k-d trees and nearest neighbor searching to automate calculation of temperature deviations; and 2) automated visualization of performance deviations using a metaphor based on traffic light colors. The proposed EPAR v2.0 modeling method is validated on several interior locations of a residential building and an instructional facility. Our empirical observations show that the automated energy performance analysis using EPAR models enables performance deviations to be rapidly and accurately identified. The visualization of performance deviations in 3D enables auditors to easily identify potential building performance problems. Rather than manually analyzing thermal imagery, auditors can focus on other important tasks such as evaluating possible remedial alternatives.

  • PDF

Estimation of Heading Date of Paddy Rice from Slanted View Images Using Deep Learning Classification Model

  • Hyeokjin Bak;Hoyoung Ban;SeongryulChang;Dongwon Gwon;Jae-Kyeong Baek;Jeong-Il Cho;Wan-Gyu Sang
    • 한국작물학회:학술대회논문집
    • /
    • 한국작물학회 2022년도 추계학술대회
    • /
    • pp.80-80
    • /
    • 2022
  • Estimation of heading date of paddy rice is laborious and time consuming. Therefore, automatic estimation of heading date of paddy rice is highly essential. In this experiment, deep learning classification models were used to classify two difference categories of rice (vegetative and reproductive stage) based on the panicle initiation of paddy field. Specifically, the dataset includes 444 slanted view images belonging to two categories and was then expanded to include 1,497 images via IMGAUG data augmentation technique. We adopt two transfer learning strategies: (First, used transferring model weights already trained on ImageNet to six classification network models: VGGNet, ResNet, DenseNet, InceptionV3, Xception and MobileNet, Second, fine-tuned some layers of the network according to our dataset). After training the CNN model, we used several evaluation metrics commonly used for classification tasks, including Accuracy, Precision, Recall, and F1-score. In addition, GradCAM was used to generate visual explanations for each image patch. Experimental results showed that the InceptionV3 is the best performing model in terms of the accuracy, average recall, precision, and F1-score. The fine-tuned InceptionV3 model achieved an overall classification accuracy of 0.95 with a high F1-score of 0.95. Our CNN model also represented the change of rice heading date under different date of transplanting. This study demonstrated that image based deep learning model can reliably be used as an automatic monitoring system to detect the heading date of rice crops using CCTV camera.

  • PDF