• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.295-301
• /
• 2021

Digital media technology is gradually developing with the development of convergence quaternary industrial technology and mobile devices. The combination of deep learning and augmented reality can provide more convenient and lively services through the interaction of 3D virtual images with the real world. We combine deep learning-based pose prediction with augmented reality technology. We predict the eight vertices of the bounding box of the object in the image. Using the predicted eight vertices(x,y), eight vertices(x,y,z) of 3D mesh, and the intrinsic parameter of the smartphone camera, we compute the external parameters of the camera through the PnP algorithm. We calculate the distance to the object and the degree of rotation of the object using the external parameter and apply to AR content. Our method provides services in a web environment, making it highly accessible to users and easy to maintain the system. As we provide augmented reality services using consumers' smartphone cameras, we can apply them to various business fields.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권12호
• /
• pp.509-516
• /
• 2022

3차원 공간에서 물체들의 정확한 자세 예측은 실내외 환경에서 장면 이해, 로봇의 물체 조작, 자율 주행, 증강 현실 등과 같은 많은 응용 분야들에서 폭넓게 활용되는 중요한 시각 인식 기술이다. 물체들의 자세 예측을 위한 과거 연구들은 대부분 각 인식 대상 물체마다 정확한 3차원 CAD 모델을 요구한다는 한계점이 있었다. 이러한 과거 연구들과는 달리, 본 논문에서는 3차원 CAD 모델이 없어도 RGB 컬러 영상들만 이용해서 미지 물체들의 자세를 예측해낼 수 있는 새로운 신경망 모델을 제안한다. 제안 모델은 적응형 깊이 추정기인 AdaBins를 이용하여 스스로 미지 물체 자세 예측에 필요한 각 물체의 깊이 지도를 효과적으로 추정해낼 수 있다. 벤치마크 데이터 집합들을 이용한 다양한 실험들을 통해, 본 논문에서 제안한 모델의 유용성과 성능을 평가한다.

• Advances in robotics research
• /
• 제2권2호
• /
• pp.129-140
• /
• 2018

With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.

• 정보처리학회논문지B
• /
• 제18B권1호
• /
• pp.11-20
• /
• 2011

Pictorial Structures(PS)는 동적 프로그래밍을 이용하여 인체의 포즈 추적 및 인식 하는 것에 매우 효과적인 방법으로 알려져 있다. 본 논문에서 상반신 포즈는 PS와 Particle filter(PF)에 의한 동적 프로그래밍 기법으로 추적된다. PF와 같은 동적프로그래밍에서 마코프 연쇄 (Markov Chain) 기반 동적 움직임 모델은 높은 자유도를 갖는 상반신 포즈를 예측하기 어려운 단점이 있다. 본 논문에서 제안하는 방법은 키포즈 기반 예측분포이며, 이것은 상반신 실루엣과 키포즈(Key Pose)들 사이의 유사도를 참고하여 파티클(Particle)을 적절히 예측하는 것이다. 실험 결과를 통해 제안된 방법은 기존 방법 성능을 70.51% 향상시킨 것을 확인하였다.

• 통합자연과학논문집
• /
• 제3권3호
• /
• pp.143-147
• /
• 2010

Since it is of great importance to know how a ligand binds to a receptor, there have been a lot of efforts to improve the quality of prediction of docking poses. Earlier efforts were focused on improving search algorithm and scoring function in a docking program resulting in a partial improvement with a lot of variations. Although these are basically very important and essential, more tangible improvements came from the reduction of search space. In a normal docking study, the approximate active site is assumed to be known. After defining active site, scoring functions and search algorithms are used to locate the expected binding pose within this search space. A good search algorithm will sample wisely toward the correct binding pose. By careful study of receptor structure, it was possible to prioritize sub-space in the active site using "receptor-based pharmacophores" or "hot spots". In a sense, these techniques reduce the search space from the beginning. Further improvements were made when the bound ligand structure is available, i.e., the searching could be directed by molecular similarity using ligand information. This could be very helpful to increase the accuracy of binding pose. In addition, if the biological activity data is available, docking program could be improved to the level of being useful in affinity prediction for a series of congeneric ligands. Since the number of co-crystal structures is increasing in protein databank, "Ligand-Guided Docking" to reduce the search space would be more important to improve the accuracy of docking pose prediction and the efficiency of virtual screening. Further improvements in this area would be useful to produce more reliable docking programs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3182-3198
• /
• 2019

Vision-based Human Pose Estimation has been considered as one of challenging research subjects due to problems including confounding background clutter, diversity of human appearances and illumination changes in scenes. To tackle these problems, we propose to use a new multi-stage convolution machine for estimating human pose. To provide better heatmap prediction of body joints, the proposed machine repeatedly produces multiple predictions according to stages with receptive field large enough for learning the long-range spatial relationship. And stages are composed of various modules according to their strategic purposes. Pyramid stacking module and dilation module are used to handle problem of human pose at multiple scales. Their multi-scale information from different receptive fields are fused with concatenation, which can catch more contextual information from different features. And spatial and channel information of a given input are converted to gating factors by squeezing the feature maps to a single numeric value based on its importance in order to give each of the network channels different weights. Compared with other ConvNet-based architectures, we demonstrated that our proposed architecture achieved higher accuracy on experiments using standard benchmarks of LSP and MPII pose datasets.

• 한국멀티미디어학회논문지
• /
• 제25권9호
• /
• pp.1257-1265
• /
• 2022

Recognition of sign language is challenging due to the occlusion of hands, accuracy of hand gestures, and high computational costs. In recent years, deep learning techniques have made significant advances in this field. Although these methods are larger and more complex, they cannot manage long-term sequential data and lack the ability to capture useful information through efficient information processing with faster convergence. In order to overcome these challenges, we propose a word-level sign language recognition (SLR) system that combines a real-time human pose detection library with the minimized version of the gated recurrent unit (GRU) model. Each gate unit is optimized by discarding the depth-weighted reset gate in GRU cells and considering only current input. Furthermore, we use sigmoid rather than hyperbolic tangent activation in standard GRUs due to performance loss associated with the former in deeper networks. Experimental results demonstrate that our pose-based optimized GRU (Pose-OGRU) outperforms the standard GRU model in terms of prediction accuracy, convergency, and information processing capability.

• 대한임베디드공학회논문지
• /
• 제17권4호
• /
• pp.191-197
• /
• 2022

This study proposes an image-based Pose Intention Network (PIN) algorithm for rehabilitation via patients' intentions. The purpose of the PIN algorithm is for enabling an active rehabilitation exercise, which is implemented by estimating the patient's motion and classifying the intention. Existing rehabilitation involves the inconvenience of attaching a sensor directly to the patient's skin. In addition, the rehabilitation device moves the patient, which is a passive rehabilitation method. Our algorithm consists of two steps. First, we estimate the user's joint position through the OpenPose algorithm, which is efficient in estimating 2D human pose in an image. Second, an intention classifier is constructed for classifying the motions into three categories, and a sequence of images including joint information is used as input. The intention network also learns correlations between joints and changes in joints over a short period of time, which can be easily used to determine the intention of the motion. To implement the proposed algorithm and conduct real-world experiments, we collected our own dataset, which is composed of videos of three classes. The network is trained using short segment clips of the video. Experimental results demonstrate that the proposed algorithm is effective for classifying intentions based on a short video clip.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.800-816
• /
• 2018

In recent years, video surveillance research has been able to recognize various behaviors of pedestrians and analyze the overall situation of objects by combining image analysis technology and deep learning method. Human Activity Recognition (HAR), which is important issue in video surveillance research, is a field to detect abnormal behavior of pedestrians in CCTV environment. In order to recognize human behavior, it is necessary to detect the human in the image and to estimate the pose from the detected human. In this paper, we propose a novel approach for 2D Human Pose Estimation based on object detection using RGB-D information. By adding depth information to the RGB information that has some limitation in detecting object due to lack of topological information, we can improve the detecting accuracy. Subsequently, the rescaled region of the detected object is applied to ConVol.utional Pose Machines (CPM) which is a sequential prediction structure based on ConVol.utional Neural Network. We utilize CPM to generate belief maps to predict the positions of keypoint representing human body parts and to estimate human pose by detecting 14 key body points. From the experimental results, we can prove that the proposed method detects target objects robustly in occlusion. It is also possible to perform 2D human pose estimation by providing an accurately detected region as an input of the CPM. As for the future work, we will estimate the 3D human pose by mapping the 2D coordinate information on the body part onto the 3D space. Consequently, we can provide useful human behavior information in the research of HAR.

• Journal of Computing Science and Engineering
• /
• 제10권3호
• /
• pp.95-101
• /
• 2016

In this study, we propose a new system for constructing parallel corpora for sign languages, which are generally under-resourced in comparison to spoken languages. In order to achieve scalability and accessibility regarding data collection and corpus construction, our system utilizes deep learning-based techniques and predicts depth information to perform pose estimation on hand information obtainable from video recordings by a single RGB camera. These estimated poses are then transcribed into expressions in SignWriting. We evaluate the accuracy of hand tracking and hand pose estimation modules of our system quantitatively, using the American Sign Language Image Dataset and the American Sign Language Lexicon Video Dataset. The evaluation results show that our transcription system has a high potential to be successfully employed in constructing a sizable sign language corpus using various types of video resources.