• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.462-464
• /
• 2022

본 논문은 LabVIEW와 MyRIO를 활용하여 유해가스를 측정하여 원격에서 모니터링에 관한 연구이다. 대다수는 Arduino를 이용한 가스측정은 복수의 센서를 사용하는 데 있어 다소 제한적이다. MyRIO는 복수의 센서를 계측할 수 있어 이를 무선으로 전송하여 LabVIEW를 통해 모니터링하는 방안을 제시하는 바이다.

• 정보과학회 논문지
• /
• 제44권12호
• /
• pp.1319-1332
• /
• 2017

최근 스포츠 중계에 동원되는 카메라 대수가 증가함에 따라 수많은 카메라 화면 중 순간적으로 최고의 화면을 고르는데 어려움이 있다. 지금까지 스포츠 경기를 촬영한 영상들에서 자동으로 최고의 화면을 선택하는 방법들이 연구되어 왔지만 배경이 고정된 영상들만을 고려해 배경이 움직이는 영상들을 고려하는 연구가 필요하다. 본 논문에서는 각 영상 별로 관심선수를 추적하여 획득한 영상 내 관심선수 영역을 대상으로 관심선수의 활동량, 얼굴 가시성, 다른 선수와의 겹침 정도, 이미지 블러 현상 정도를 매 프레임 마다 정량적으로 나타내어 정량화된 값을 기반으로 최고의 화면을 선택한다. 이렇게 선택된 베스트 뷰를 20명의 일반 사람들에게 베스트 뷰와 워스트 뷰를 선택하게 하여 사람들이 선택한 베스트 뷰, 워스트 뷰와 비교한 결과 베스트 뷰와 일치율이 54.5%로 낮았지만 반대로 워스트 뷰와 일치율이 9%로 확실히 사람들이 선호하지 않는 화면은 선택하지 않는 것을 알 수 있었다.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1179-1191
• /
• 2019

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집A
• /
• pp.667-672
• /
• 2001

An optimization approach is used to partition the field of view. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between a field of view and one or multiple objects. Partition is achieved by initializing each neuron that represents a possible match and then allowing the network to settle down into a stable state. The network uses the initial inputs and the compatibility measures between a field of view and one or multiple objects to find a stable state.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.120-125
• /
• 2002

An optimization approach is used to partition the field of view. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between a field of view and one or multiple objects. Partition is achieved by initializing each neuron that represents a possible match and then allowing the network to settle down into a stable state. The network uses the initial inputs and the compatibility measures between a field of view and one or multiple objects to find a stable state.

• 방송공학회논문지
• /
• 제13권3호
• /
• pp.328-338
• /
• 2008

H.264/AVC기반의 다시점 영상 부호화 기술은 시점간 상관성을 이용한 새로운 예측 방법을 이용하여 여러 대의 카메라로부터 촬영된 영상을 효율적으로 부호화하는 기술이다. 그러나 다시점 부호화 기술은 시점의 증가와 시점간 예측의 사용으로 인해 부호화 시간이 크게 증가한다. 본 논문은 부호화 시간을 줄이기 위해 다시점 영상에서 시점간에 대응하는 마크로블록 (Macroblock) 기반 영역 분할 정보와 시점간의 전역 변이 벡터를 이용한 고속 모드 결정 방법을 제안한다. 제안하는 방법은 다시점 영상 부호화 표준의 참조 소프트웨어인 joint multi-view video model (JMVM) 4.0에 비해 약 0.04dB의 화질 열화를 보이지만 전체 부호화 시간을 평균적으로 40% 단축할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.559-575
• /
• 2023

3D human pose estimation is widely applied in various fields, including action recognition, sports analysis, and human-computer interaction. 3D human pose estimation has achieved significant progress with the introduction of convolutional neural network (CNN). Recently, several researches have proposed the use of multiview approaches to avoid occlusions in single-view approaches. However, as the number of cameras increases, a 3D pose estimation system relying on a CNN may lack in computational resources. In addition, when a single host system uses multiple cameras, the data transition speed becomes inadequate owing to bandwidth limitations. To address this problem, we propose a distributed real-time 3D pose estimation framework based on asynchronous multiple cameras. The proposed framework comprises a central server and multiple edge devices. Each multiple-edge device estimates a 2D human pose from its view and sendsit to the central server. Subsequently, the central server synchronizes the received 2D human pose data based on the timestamps. Finally, the central server reconstructs a 3D human pose using geometrical triangulation. We demonstrate that the proposed framework increases the percentage of detected joints and successfully estimates 3D human poses in real-time.

• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.381-385
• /
• 2003

본 논문에서는 다면체의 인식을 위하여 사용되는 여러-방향-보기 방법 (multiple-view approach)에서, ART-1 신경망을 이용하여 모델베이스의 탐색공간 크기를 줄이기 위한 방법을 제안한다. 이 방법에서 모델베이스는 물체를 둘러싸고 있는 보기 구체의 미리 정해진 시점에서 관측된 2차원 투영체에서 추출된 특징들로 구성된다.

• 디지털산업정보학회논문지
• /
• 제14권3호
• /
• pp.21-28
• /
• 2018

As computer performance and needs of user convenience increase, computer user interface are also changing. This changes had great effects on software development environment. In past, text editors like vi or emacs on UNIX OS were the main development environment. These editors are very strong to edit source code, but difficult and not intuitive compared to GUI(Graphical User Interface) based environment and were used by only some experts. Moreover, the trends of software development environment was changed from command line to GUI environment and GUI Editor provides usability and efficiency. As a result, the usage of text based editor had decreased. However, because GUI based editor use a lot of computer resources, computer performance and efficiency are decreasing. The more contents are, the more time to verify and display the contents it takes. In this paper, we provide a new parser that provide multi view editing, incremental parsing and multiple entry of abstract syntax tree.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.353-358
• /
• 2022

Due to the limited field of view of the pinhole camera, there is a lack of stability and accuracy in camera pose estimation applications such as visual SLAM. Nowadays, multiple-camera setups and large field of cameras are used to solve such issues. However, a multiple-camera system increases the computation complexity of the algorithm. Therefore, in multiple camera-assisted visual simultaneous localization and mapping (vSLAM) the multi-view tracking algorithm is proposed that can be used to balance the budget of the features in tracking and local mapping. The proposed algorithm is based on PanoSLAM architecture with a panoramic camera model. To avoid the scale issue 3D LiDAR is fused with omnidirectional camera setup. The depth is directly estimated from 3D LiDAR and the remaining features are triangulated from pose information. To validate the method, we collected a dataset from the outdoor environment and performed extensive experiments. The accuracy was measured by the absolute trajectory error which shows comparable robustness in various environments.