• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

• International Commerce and Information Review
• /
• v.7 no.4
• /
• pp.77-94
• /
• 2005

The successful knowledge and information based companies facilitate to restructure the industry and strengthen the national competitiveness in the future. The advent of information age provides us new challenge because the information breakthrough can play a pivotal role in terms of knowledge transfer in the human resource management. This research focuses on best practices of human management and contrasting the human resource strategy of Japanese and American firms respectively, Based on this, we suggest the strategic alternatives of the described HR problems as well as the way of effective human resource management for Korean venture firms. We have reviewed the previous international and domestic literatures in details to understand HR liabilities of newness of venture firms in terms of the population ecology. The objective of this research is to solve the HR problems that Korean firms faced with.

• 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 the Korea Institute of Information and Communication Engineering
• /
• v.16 no.6
• /
• pp.1179-1186
• /
• 2012

In this paper, we propose an algorithm that recognizes human activity patterns using the human body's joints and the information of the joints. The proposed method extracts the object from inputted video, automatically extracts joints using the ratio of the human body, applies block-matching algorithm for each joint and gets the motion information of joints. The proposed method uses the joints to move, the directional vector of motions of joints, and the sign to represent the increase or decrease of x and y coordinates of joints as basic parameters for human recognition of activity. The proposed method was tested for 8 human activities of inputted video from a web camera and had the good result for the ration of recognition of the human activities.

• Journal of Sport and Applied Science
• /
• v.5 no.2
• /
• pp.31-38
• /
• 2021

Purpose: A new form of sports human rights platform is needed for policy-related officials, athletes, leaders, and parents to easily share information on sports human rights and to promote communication between the sports community and the outside. Research design, data, and methodology: Participants were collected from athletes (n=3,007) who were registered in Korean Sport & Olympic Committee. Participants were asked to respond the survey items measuring their experiences of human right violations in sport. Descriptive analysis, t-test, and ANOVA were used to analyze data. Results: The platform should include information on prevention and safety of human rights violations during sports activities, procedures and methods for reporting damage, countermeasures, leader education programs, human rights protection guidelines, roles and supervision of sports organizations and institutions, and related statues. It can form a community as well as exchange information in the Internet space through the operation of bulletin boards by professional athletes, student athletes, parents, and leaders, and plays a role in crisis counseling or information provision. Given the reality that players can be blocked from the outside world, information communication channels on SNS can be a useful means of protecting and improving players' human rights. Conclusions: Therefore, it is necessary to provide a foundation for creating related platforms so that sports human rights sites or SNS can be operated voluntarily. Implications and future directions were discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.637-640
• /
• 2023

This paper presents multimodal image fusion with human pose for detecting abnormal human behaviors in low illumination conditions. Detecting human behaviors in low illumination conditions is challenging due to its limited visibility of the objects of interest in the scene. Multimodal image fusion simultaneously combines visual information in the visible spectrum and thermal radiation information in the long-wave infrared spectrum. We propose an abnormal event detection scheme based on the multimodal fused image and the human poses using the keypoints to characterize the action of the human body. Our method assumes that human behaviors are well correlated to body keypoints such as shoulders, elbows, wrists, hips. In detail, we extracted the human keypoint coordinates from human targets in multimodal fused videos. The coordinate values are used as inputs to train a multilayer perceptron network to classify human behaviors as normal or abnormal. Our experiment demonstrates a significant result on multimodal imaging dataset. The proposed model can capture the complex distribution pattern for both normal and abnormal behaviors.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1046-1048
• /
• 2003

Recently, various researches in respect of the positioning technologies using satellites and the other sensors have made location-based services (LBS) more common and accurate. Consequently, concern about position information has been increasing. However, since these positioning systems only focus on user's position, it is difficult to know the user's attitude or detailed behaviors at the specific position. It is worthy to study on how to acquire such human attitude or behavior, because those information is useful to know the context of the user. In this paper, the sensor unit consisting of three dimensional accelerometer was attached to human body, and autonomously measured the perpendicular acceleration of ordinary human behaviors including activity modes such as walking, running, and transportation mode using transportation such as a train, a bus, and an elevator. Subsequently, using the classified measurement results, the method to identify the human activity modes was proposed.

• Journal of Computing Science and Engineering
• /
• v.9 no.1
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.

• Journal of the Ergonomics Society of Korea
• /
• v.23 no.2
• /
• pp.13-24
• /
• 2004

Human error has brought about accidents more than 50% in system of a large size and complicated expecially in nuclear power plants(NPPs). The technology of Man Machine Interface(MMI) has been changed to the digitalized controls employing computer-based technology. According to this trend. the human factors guidelines are becoming main issue for reliable supports to digitalized information displays. However. the existing human factors guidelines is not enough for advanced information display on NPPs. The purpose of this research is to develop the reliable design and evaluation guidelines for advanced information display in main control room (MCR) of NPPs. In this study. the various general human factors guidelines concerning information display on CRT are integrated on data base management system. unified based on the integration rules. and applied in computer based procedures. The use of the integrated guidelines are expected to evaluate the existing information display on MCR in NPPs from the human factors point of view.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.743-746
• /
• 2002

바이오 인포매틱스(bioinformatics) 분야 중 한 분야인 셀 기반 분석(cell-based assay) 시스템 구축의 필요성이 최근 대두되고 있다. 특정 시약 또는 시험 물질을 셀 세포에 투여했을 때 시간 축 변화에 따라 변화하는 세포의 변화를 감지하기 위해서 세포 영상의 영역 분할이 선행되어야 한다. 본 논문에서는 전체 영상에 대하여 셀 공통 영역을 추출하고, 추출된 공통영역을 스네이크(snake) 기법을 이용하여 세포 영역을 분할하는 방법을 제안하고자 한다.