• 제목/요약/키워드: Three-dimensional Convolutional Neural Network

검색결과 33건 처리시간 0.019초

Human Gait Recognition Based on Spatio-Temporal Deep Convolutional Neural Network for Identification

  • Zhang, Ning;Park, Jin-ho;Lee, Eung-Joo
    • 한국멀티미디어학회논문지
    • /
    • 제23권8호
    • /
    • pp.927-939
    • /
    • 2020
  • Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

Assessment of ASPECTS from CT Scans using Deep Learning

  • Khanh, Trinh Le Ba;Baek, Byung Hyun;Kim, Seul Kee;Do, Luu-Ngoc;Yoon, Woong;Park, Ilwoo;Yang, Hyung-Jeong
    • 한국멀티미디어학회논문지
    • /
    • 제22권5호
    • /
    • pp.573-579
    • /
    • 2019
  • Alberta Stroke Program Early Computed Tomographic Scoring (ASPECTS) is a 10-point CT-scan score designed to quantify early ischemic changes in patients with acute ischemic stroke. However, an assessment of ASPECTS remains a challenge for neuroradiologists in stroke centers. The purpose of this study is to develop an automated ASPECTS scoring system that provides decision-making support by utilizing binary classification with three-dimensional convolutional neural network to analyze CT images. The proposed method consists of three main steps: slice filtering, contrast enhancement and image classification. The experiments show that the obtained results are very promising.

MLCNN-COV: A multilabel convolutional neural network-based framework to identify negative COVID medicine responses from the chemical three-dimensional conformer

  • Pranab Das;Dilwar Hussain Mazumder
    • ETRI Journal
    • /
    • 제46권2호
    • /
    • pp.290-306
    • /
    • 2024
  • To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transferlearning methodology and a multilabel convolutional neural network for COVID (MLCNN-COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer-learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN-COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three-dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN-COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer-learning model's performance. It shows that three-dimensional conformers adequately identify negative COVID medicine responses.

Human Activity Recognition Based on 3D Residual Dense Network

  • Park, Jin-Ho;Lee, Eung-Joo
    • 한국멀티미디어학회논문지
    • /
    • 제23권12호
    • /
    • pp.1540-1551
    • /
    • 2020
  • Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

R-CNN 기법을 이용한 건물 벽 폐색영역 추출 적용 연구 (Application Research on Obstruction Area Detection of Building Wall using R-CNN Technique)

  • 김혜진;이정민;배경호;어양담
    • 지적과 국토정보
    • /
    • 제48권2호
    • /
    • pp.213-225
    • /
    • 2018
  • 3차원 공간정보 구축을 위해 건물 텍스처를 촬영하는 과정에서 폐색영역 문제가 발생한다. 이를 해결하기 위해선 폐색영역을 자동 인식하여 이를 검출하고 텍스처를 자동 보완하는 자동화 기법 연구가 필요하다. 현실적으로 매우 다양한 구조물 형상과 폐색을 발생시키는 경우가 있으므로 이를 극복하는 대안들이 고려되고 있다. 본 연구는 최근 대두되고 있는 딥러닝 기반의 알고리즘을 이용하여 폐색지역 패턴화하고, 학습기반 폐색영역 자동 검출하는 접근을 시도한다. 영상 내 객체 추출에서 우수한 성과를 발표하는 Convolutional Neural Network (CNN) 기법의 향상된 알고리즘인 Faster Region-based Convolutional Network (R-CNN)과 Mask R-CNN 2가지를 이용하여, 건물 벽면 촬영 시 폐색을 유발하는 사람, 현수막, 차량, 신호등에 대한 자동 탐지하는 성능을 알아보기 위해 실험하고, Mask R-CNN의 미리 학습된 모델에 현수막을 학습시켜 자동탐지하는 실험을 통해 적용이 높은 결과를 확인할 수 있었다.

합성곱 신경망과 복셀화를 활용한 선박 저항 성능 예측 (Prediction of Ship Resistance Performance Based on the Convolutional Neural Network With Voxelization)

  • 박종서;최민주;송지수
    • 대한조선학회논문집
    • /
    • 제60권2호
    • /
    • pp.110-119
    • /
    • 2023
  • The prediction of ship resistance performance is typically obtained by Computational Fluid Dynamics (CFD) simulations or model tests in towing tank. However, these methods are both costly and time-consuming, so hull-form designers use statistical methods for a quick feed-back during the early design stage. It is well known that results from statistical methods are often less accurate compared to those from CFD simulations or model tests. To overcome this problem, this study suggests a new approach using a Convolution Neural Network (CNN) with voxelized hull-form data. By converting the original Computer Aided Design (CAD) data into three dimensional voxels, the CNN is able to abstract the hull-form data, focusing only on important features. For the verification, suggested method in this study was compared to a parametric method that uses hull parameters such as length overall and block coefficient as inputs. The results showed that the use of voxelized data significantly improves resistance performance prediction accuracy, compared to the parametric approach.

계층적 컨볼루션 신경망을 이용한 공작기계의 공구 상태 진단 (Machine Tool State Monitoring Using Hierarchical Convolution Neural Network)

  • 이경민
    • 융합신호처리학회논문지
    • /
    • 제23권2호
    • /
    • pp.84-90
    • /
    • 2022
  • 공작기계 상태 진단은 기계의 상태를 자동으로 감지하는 프로세스이다. 실제로 가공의 효율과 제조공정에서 제품의 품질은 공구 상태에 영향을 받으며 마모 및 파손된 공구는 공정 성능에 보다 심각한 문제를 일으키고 제품의 품질 저하를 일으킬 수 있다. 따라서 적절한 시기에 공구가 교체될 수 있도록 공구 마모 진행 및 공정 중 파손 방지 시스템 개발이 필요하다. 본 논문에서는 공구의 적절한 교체 시기 등을 진단하기 위해 딥러닝 기반의 계층적 컨볼루션 신경망을 이용하여 5가지 공구 상태를 진단하는 방법을 제안한다. 기계가 공작물을 절삭할 때 발생하는 1차원 음향 신호를 주파수 기반의 전력스펙트럼밀도 2차원 영상으로 변환하여 컨볼루션 신경망의 입력으로 사용한다. 학습 모델은 계층적 3단계를 거쳐 5가지 공구 상태를 진단한다. 제안한 방법은 기존의 방법과 비교하여 높은 정확도를 보였고, 실시간 연동을 통해 다양한 공작기계를 모니터링할 수 있는 스마트팩토리 고장 진단 시스템에 활용할 수 있을 것이다.

딥러닝 기반 균열 추출 기법을 통한 수압 파쇄 균열 형상 분석 (Morphological Analysis of Hydraulically Stimulated Fractures by Deep-Learning Segmentation Method)

  • 박지민;김광염;윤태섭
    • 한국지반공학회논문집
    • /
    • 제39권8호
    • /
    • pp.17-28
    • /
    • 2023
  • 본 연구에서는 화강암 시편을 대상으로 파쇄 유체의 점성과 주입 속도를 변화시키며 실내 수압 파쇄 실험을 수행하였고, 3D X-ray CT 촬영을 통해 파쇄 후 시편 내부를 관찰하였다. 이미지 처리에 탁월한 성능을 보이는 합성곱 신경망(Convolutional Neural Network, CNN) 기반 Nested U-Net 모델 구조를 활용하여 CT 이미지 내 수압 파쇄 균열 추출을 수행하였고, 복잡한 형상의 미세균열을 정교하게 추출할 수 있었다. CNN 기반 모델로 추출된 균열을 3차원으로 재구성하여 균열의 부피, 두께, 굴곡도, 균열면 거칠기를 분석하였다. 그 결과 파쇄 유체의 점성이 클수록 균열 부피와 두께가 증가하였고, 굴곡도와 균열면의 거칠기가 감소하는 경향을 보였다. 또한 균열면의 굴곡도와 거칠기 이방성이 존재함을 확인할 수 있었다. 본 연구는, CNN 기반의 균열 추출 모델을 활용해 전통적인 이미지 처리 방법보다 정교한 균열 추출을 수행하고, 이를 기반으로 수압 파쇄 균열의 정량 분석을 성공적으로 수행하였다.

이중흐름 3차원 합성곱 신경망 구조를 이용한 효율적인 손 제스처 인식 방법 (An Efficient Hand Gesture Recognition Method using Two-Stream 3D Convolutional Neural Network Structure)

  • 최현종;노대철;김태영
    • 한국차세대컴퓨팅학회논문지
    • /
    • 제14권6호
    • /
    • pp.66-74
    • /
    • 2018
  • 최근 가상환경에서 몰입감을 늘리고 자유로운 상호작용을 제공하기 위한 손 제스처 인식에 대한 연구가 활발히 진행되고 있다. 그러나 기존의 연구는 특화된 센서나 장비를 요구하거나, 낮은 인식률을 보이고 있다. 본 논문은 정적 손 제스처와 동적 손 제스처 인식을 위해 카메라 이외의 별도의 센서나 장비 없이 딥러닝 기술을 사용한 손 제스처 인식 방법을 제안한다. 일련의 손 제스처 영상을 고주파 영상으로 변환한 후 손 제스처 RGB 영상들과 이에 대한 고주파 영상들 각각에 대해 덴스넷 3차원 합성곱 신경망을 통해 학습한다. 6개의 정적 손 제스처와 9개의 동적 손 제스처 인터페이스에 대해 실험한 결과 기존 덴스넷에 비해 4.6%의 성능이 향상된 평균 92.6%의 인식률을 보였다. 본 연구결과를 검증하기 위하여 3D 디펜스 게임을 구현한 결과 평균 34ms로 제스처 인식이 가능하여 가상현실 응용의 실시간 사용자 인터페이스로 사용가능함을 알 수 있었다.

Evaluation of maxillary sinusitis from panoramic radiographs and cone-beam computed tomographic images using a convolutional neural network

  • Serindere, Gozde;Bilgili, Ersen;Yesil, Cagri;Ozveren, Neslihan
    • Imaging Science in Dentistry
    • /
    • 제52권2호
    • /
    • pp.187-195
    • /
    • 2022
  • Purpose: This study developed a convolutional neural network (CNN) model to diagnose maxillary sinusitis on panoramic radiographs(PRs) and cone-beam computed tomographic (CBCT) images and evaluated its performance. Materials and Methods: A CNN model, which is an artificial intelligence method, was utilized. The model was trained and tested by applying 5-fold cross-validation to a dataset of 148 healthy and 148 inflamed sinus images. The CNN model was implemented using the PyTorch library of the Python programming language. A receiver operating characteristic curve was plotted, and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive values for both imaging techniques were calculated to evaluate the model. Results: The average accuracy, sensitivity, and specificity of the model in diagnosing sinusitis from PRs were 75.7%, 75.7%, and 75.7%, respectively. The accuracy, sensitivity, and specificity of the deep-learning system in diagnosing sinusitis from CBCT images were 99.7%, 100%, and 99.3%, respectively. Conclusion: The diagnostic performance of the CNN for maxillary sinusitis from PRs was moderately high, whereas it was clearly higher with CBCT images. Three-dimensional images are accepted as the "gold standard" for diagnosis; therefore, this was not an unexpected result. Based on these results, deep-learning systems could be used as an effective guide in assisting with diagnoses, especially for less experienced practitioners.