• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.413-415
• /
• 2021

This paper proposes a nail detection algorithm using OpenPose and implements virtual nail art using it. Based on the key points detected by OpenPose, the finger area is detected using skin color characteristics for each finger. The nail region is detected from the edge image of the detected finger region. Then, a virtual nail art is implemented by synthesizing nail tips in the nail area. In a somewhat controlled shooting environment, simulation results show that the proposed algorithm detects nail areas well and implements virtual nail art well.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.735-740
• /
• 2022

The construction is the industry with the highest fatalities, and the fatalities has not decreased despite various institutional improvements. Accordingly, real-time safety management by applying artificial intelligence (AI) to CCTV images is emerging. Although some research on worker detection by applying AI to images of construction sites is being conducted, there are limitations in performance expression due to problems such as complex background due to the nature of the construction industry. In this study, the YOLO model and the OpenPose model were fused to improve the performance of worker detection and posture estimation to improve the detection performance of workers in various complex conditions. This is expected to be highly useful in terms of unsafe behavior and health management of workers in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.282-290
• /
• 2019

Recently child abuse has occurred frequently in educational institutions such as daycare center and kindergarten. Therefore, government made it mandatory to install CCTVs, but it is not easy to inspect the CCTV images. In this paper, we propose a model for judging child abuse using CCTV images. First of all, child abuse is a physical abuse of children by adults, thus a model for classifying adults and children is needed. The existing Haar scheme uses the frontal image to classify adults and children. However, the OpenPose allows to classify adults and children regardless of frontal and side image. In this research, a child abuse judgment model was designed and implemented by applying characteristics of adult and child posture when a child was abused. Since the implemented system utilizes the currently installed CCTV image, it is possible to monitor the child abuse in real time without any additional installation, which enables us to cope with the abuse promptly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.811-812
• /
• 2018

딥러닝 기술의 발전에 따라, 딥러닝을 Human Pose Estimation에 적용하는 연구가 활발하게 수행되고 있다. 본 논문에서는 딥러닝을 이용한 여러 기술 중 가장 활발하게 사용이 되고 있는 Open Pose 와 Deeper Cut 기술의 특성을 분석한다.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.2
• /
• pp.221-235
• /
• 2007

Open problems can provide experiences for students to yield originative and various products in their level, because it is open with respect to its departure situation, goal situation, or solving method. Teachers need to pose and utilize open problems in forms of solution-finding or proving problems. For this we first have to specify which resource and method to use by concrete examples. In this article, we exemplify a method and procedure of posing an open problem by the two cases in which we pose open problems by reorganizing given closed problems. And we analyze students' responses for the two posed open problems. On the basis of these, we reflect implications for mathematical education of open problems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• Korean Journal of Applied Biomechanics
• /
• v.12 no.2
• /
• pp.179-195
• /
• 2002

The purpose of this research is to provide a proper model by analyzing the sports biomechanical of physical movements on the basis of the two patterns(open-stance and cross-stance) at the ready-to-start pose. The subjects for this study are composed of five male handball players from P university and five female shooting players from S university. Three-way moving actions at start(right, left, and forward) are recorded with two high-speed video cameras and measured with two Force platforms and a EMG system. Three-dimensional action analyzer, GRF system, and Whole body reaction movement system are used to figure out the moving mechanisms at the start pose. The analytic results of the moving mechanism at the start pose were as follows. 1. Through examining the three-way moving actions at start, I have found the cross-stance pose is better for the moving speed of body weight balance than the open-stance one. 175 degree of knee joint angle at "take-off" and 172 degree of hip joint angle were best for the start pose. 2. The Support time and GRF data shows that the quickest center of gravity shift was occurred when cross-stanced male subjects started to move toward his lefthand side. The quickest male's average supporting time of left and right foot is 0.19${\pm}$0.07 sec., 0.26${\pm}$0.06sec. respectively. The supporting time difference between two feet is 0.07sec. 3. Through analyzing GRF of moving actions at start pose, I have concluded that more than 1550N are overloaded on one foot at the open-stance start, and the overloaded force may cause physical injury. However, at the cross-stance pose, The GRF are properly dispersed on both feet, and maximum 1350N are loaded on one foot.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• 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.