• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.532-533
• /
• 2020

원격 및 가상환경에서 사용자의 동작에 따른 3D 모델을 제공하기 위해 light detection and range (LiDAR)로 측정된 3D point cloud로 사용자의 3D 모델이 생성되어 원격 및 가상환경에 사용자의 모습이 제공된다. 하지만 3D 모델을 생성하기 위해서는 사용자의 신체 전부가 측정된 3D point cloud가 필요하다. 사용자의 신체 전체를 측정하기 위해서는 적어도 두 개 이상의 LiDAR가 필요하다. 두 개 이상의 LiDAR을 사용할 경우에는 LiDAR을 사용할 공간과 LiDAR를 구비하기 위한 비용이 발생한다. 단일 LiDAR로 3D 모델을 생성하는 방법이 요구된다. 본 논문에서는 단일 LiDAR에서 측정된 3D point cloud를 이용하여 3D 모델을 생성하는 방법이 제안된다. End-to-End 기반 Convolutional Neural Network (CNN) 모델로 측정된 3D point cloud를 분석하여 사용자의 체형과 자세를 예측하도록 학습한다. 기본자세를 취하는 동안 수집된 3D point cloud로 기본이 되는 사용자의 3D 모델을 생성한다. 학습된 CNN 모델을 통하여 측정된 3D point cloud로 사용자의 자세를 예측하여 기본이 되는 3D 모델을 수정하여 3D 모델을 제공한다.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.71-76
• /
• 2022

In autonomous driving cars, 3D pose estimation can be one of the effective methods to enhance safety control for OOP (Out of Position) passengers. There have been many studies on human pose estimation using a camera. Previous methods, however, have limitations in automotive applications. Due to unexplainable failures, CNN methods are unreliable, and other methods perform poorly. This paper proposes robust real-time multi-human 3D pose estimation architecture in vehicle using monocular RGB camera. Using particle filter, our approach integrates CNN 2D/3D pose measurements with available information in vehicle. Computer simulations were performed to confirm the accuracy and robustness of the proposed algorithm.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.90-101
• /
• 2022

Buses are a popular means of transportation. As such, thorough preparation is needed for passenger safety management. However, the safety system is insufficient because there are accidents such as a death accident occurred when the bus departed without recognizing the elderly approaching to get on in 2018. There is a safety system that prevents pinching accidents through sensors on the back door stairs, but such a system does not prevent accidents that occur in the process of getting on and off like the above accident. If it is possible to predict the intention of bus passengers to get on and off, it will help to develop a safety system to prevent such accidents. However, studies predicting the intention of passengers to get on and off are insufficient. Therefore, in this paper, we propose a 1×1 CNN3D-based getting on and off intention prediction model using skeleton keypoints of passengers extracted from the camera image attached to the bus through UDP-Pose. The proposed model shows approximately 1~2% higher accuracy than the RNN and LSTM models in predicting passenger's getting on and off intentions.

• Nuclear Engineering and Technology
• /
• v.43 no.3
• /
• pp.243-256
• /
• 2011

This paper considers the concept of analog computing based on a cellular neural network (CNN) paradigm to simulate nuclear reactor dynamics using a time-dependent second order form of the neutron transport equation. Instead of solving nuclear reactor dynamic equations numerically, which is time-consuming and suffers from such weaknesses as vulnerability to transient phenomena, accumulation of round-off errors and floating-point overflows, use is made of a new method based on a cellular neural network. The state-of-the-art shows the CNN as being an alternative solution to the conventional numerical computation method. Indeed CNN is an analog computing paradigm that performs ultra-fast calculations and provides accurate results. In this study use is made of the CNN model to simulate the space-time response of scalar flux distribution in steady state and transient conditions. The CNN model also is used to simulate step perturbation in the core. The accuracy and capability of the CNN model are examined in 2D Cartesian geometry for two fixed source problems, a mini-BWR assembly, and a TWIGL Seed/Blanket problem. We also use the CNN model concurrently for a typical small PWR assembly to simulate the effect of temperature feedback, poisons, and control rods on the scalar flux distribution.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.459-462
• /
• 2007

본 연구에서는 동적 수신호 인식문제를 위하여 CNN 모델을 사용한 특징추출 기법과, FMM 신경망을 사용한 특징 분석 기법을 상호 결합한 형태의 패턴 인식 모델을 제안한다. 수신호 인식을 위하여 영상패턴에서 대상물의 움직임 정보에 기초한 3 차원 형식의 데이터 표현 기법과, 이로부터 인식을 위한 특징추출 기법을 제시한다. 특징추출 모듈에서는 3 차원으로 확장된 구조의 수용영역을 고려한 CNN 모델을 제안하며, 이로부터 학습패턴에서 특징점의 공간적 변이에 대한 영향을 최소화할 수 있음을 고찰한다. 또한 인식효율의 개선을 위하여 방대한 양의 특징집합으로부터 효과적인 특징을 선별하기 위한 방법론으로서 WFMM 모델 기반의 특징분석 기법을 정의하고 이로부터 선별된 특징을 사용하는 인식 기법을 소개한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.1076-1094
• /
• 2022

Technology for emotion recognition is an essential part of human personality analysis. To define human personality characteristics, the existing method used the survey method. However, there are many cases where communication cannot make without considering emotions. Hence, emotional recognition technology is an essential element for communication but has also been adopted in many other fields. A person's emotions are revealed in various ways, typically including facial, speech, and biometric responses. Therefore, various methods can recognize emotions, e.g., images, voice signals, and physiological signals. Physiological signals are measured with biological sensors and analyzed to identify emotions. This study employed two sensor types. First, the existing method, the binary arousal-valence method, was subdivided into four levels to classify emotions in more detail. Then, based on the current techniques classified as High/Low, the model was further subdivided into multi-levels. Finally, signal characteristics were extracted using a 1-D Convolution Neural Network (CNN) and classified sixteen feelings. Although CNN was used to learn images in 2D, sensor data in 1D was used as the input in this paper. Finally, the proposed emotional recognition system was evaluated by measuring actual sensors.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.145-146
• /
• 2017

본 논문에서는 남성의 하반신을 촬영한 MRI 영상으로부터 전립선을 분할하는 알고리즘을 제안한다. 우선 3 차원 입체 영상을 학습하기 위해 3D 컨볼루션 계층(convolutional layer) 및 3D 풀링 계층(pooling layer)에 기반한 네트워크를 제안한다. 다음으로 네트워크의 최후단에 해당하는 전연결 계층(fully connected layer)의 강인한 학습을 돕는 잡음 계층을 제안한다. 잡음 계층은 네트워크의 학습 파라미터 혹은 출력 영상에 가우시안 잡음를 더함으로써 드롭 아웃과 같이 훈련 영상에 대한 과적합(overfitting)을 막고 테스트 영상에 강인한 네트워크의 학습을 돕는다. 마지막으로 실험을 통해 제안하는 기법이 기존 기법에 비해 우수한 분할 성능을 보임을 확인한다.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.681-692
• /
• 2019

In this paper, a hybrid deep learning model, called 2D convolution with bidirectional long short-term memory (2DCBLSTM), is presented that can effectively combine both spatial and temporal features for crop classification. In the proposed model, 2D convolution operators are first applied to extract spatial features of crops and the extracted spatial features are then used as inputs for a bidirectional LSTM model that can effectively process temporal features. To evaluate the classification performance of the proposed model, a case study of crop classification was carried out using multi-temporal unmanned aerial vehicle images acquired in Anbandegi, Korea. For comparison purposes, we applied conventional deep learning models including two-dimensional convolutional neural network (CNN) using spatial features, LSTM using temporal features, and three-dimensional CNN using spatio-temporal features. Through the impact analysis of hyper-parameters on the classification performance, the use of both spatial and temporal features greatly reduced misclassification patterns of crops and the proposed hybrid model showed the best classification accuracy, compared to the conventional deep learning models that considered either spatial features or temporal features. Therefore, it is expected that the proposed model can be effectively applied to crop classification owing to its ability to consider spatio-temporal features of crops.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.85-90
• /
• 2021

In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models' validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.