• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.129-130
• /
• 2023

본 논문에서는 키넥트 센서 기반의 산업 현장 사고 모니터링 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 기존 산업 현장 사고 모니터링 인력의 의존을 줄이고, 사고 발생 자동 감지로 인한 알림 기능과 현장 기록 기능을 구현한다. 사고 발생 감지 기능은 키넥트 센서 기반으로 스켈레톤 인식 기능을 활용하여 기존에 설정된 좌표 값 이하로 헤드 조인트 좌표가 떨어질 경우 관리자에게 알림을 보내도록 구현한다. 사고감지 및 알림 시스템은 기존 모니터링 시스템을 보완하는 방식으로 감지 인력의 한계를 극복할 수 있는 기능을 제공한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.601-602
• /
• 2023

유치장은 피의자나 경범죄를 지은 사람 등을 잠시 수감하는 곳으로, 질서가 유지되어야 하는 공간이지만 수감자 간의 폭행과 같은 사건이 발생하는 문제가 있다. 따라서 유치장 내 폭행 사건의 신속한 대응은 질서를 유지하기 위한 핵심 과제 중 하나이다. 이 문제를 해결하기 위해 본 연구에서는 수감자들의 객체를 통합 바운딩박스의 변화율을 통해 격렬한 움직임을 포착하고 스켈레톤 키-포인트의 속도를 측정해 폭행인지 판단한다. 연구 결과, 제안하는 알고리즘의 정확도는 91%로 실시간 폭행 탐지에 유의미하다는 것을 확인할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.287-288
• /
• 2023

우리 사회가 고령화시대로 접어들면서 낙상은 매우 심각한 사회문제가 되고 있으며 정확한 낙상 감지 기술의 수요도 늘고 있다. 본 연구는 웹 캠을 이용한 개선된 낙상감지 기법을 제안한다. 제안하는 기법은 RGB 영상을 기반으로 스켈레톤 포즈 추출, 데이터 가공, GRU(Gated Recurrent Unit) 신경망 알고리즘을 적용한 낙상 감지 실험 및 감지 결과 분석의 과정이 포함된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.231-232
• /
• 2024

본 논문에서는 키넥트 센서 기반의 쓰레기 분리수거 게임을 설계하고 구현한다. 이 애플리케이션은 키넥트 센서의 스켈레톤 인식 기능을 통해 사용자를 게임 속 분리 수거통으로 표현하게 하여 분리 수거 대상 품목에 해당하는 개체에 닿으면 점수를 증가시킨다. 만일 일반 쓰레기에 닿을 시 3회의 기회가 카운트 되어 전부 소진히게 되면 게임이 종료되도록 구현한다. 해당 게임을 시행함으로써 분리수거에 적극적인 참여를 도모하여 이에 따른 행동을 취함으로 쓰레기 문제에 대한 인식을 높이고, 분리수거에 대한 재미와 도전을 제공한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.229-230
• /
• 2024

본 논문에서는 키넥트 센서 기반의 치매 예방 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 노년층의 치매 예방을 위해 기억력을 향상시키고 간단한 동작으로 운동을 촉진할 수 있는 햄버거 만들기 게임을 구현한다. 햄버거 만들기 게임은 키넥트 센서 기반으로 조인트와 스켈레톤 기능을 활용하여 하늘에서 떨어지는 재료들을 순서에 맞게 획득하여 햄버거를 완성함으로써 점수를 얻는다. 사용자들은 제한 시간이 끝날 때까지 계속 진행하며 순서를 기억해 내는 과정을 통해 기억력을 향상시키고, 재료를 잡기 위한 활동적인 움직임으로 치매 예방에 도움이 되는 운동 기능을 제공한다.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.3
• /
• pp.1-10
• /
• 2015

One way to create a visually immersive environment is to utilize a front projection system. Especially, when enough space is not available behind the screen, it becomes difficult to install a back projection system, making the front projection an appropriate choice. A drawback associated with the front projection is, however, the interference of shadow. The shadow can be cast on the screen when the user is located between the screen and the projector. This shadow can negatively affect the user experience and reduce the sense of immersion by removing important information. There have been various attempts to eliminating shadows cast on the screen by using multiple projectors that compensate for each other with missing information. There is trade-off between calculataion time and desired accuracy in this mutual compensation. Accurate estimation of the shadow usually requires heavy computation while simple approaches suffer from inclusion of non-shadow regions in the result. We propose a novel approach to removing shadows created in the front projection system using the skeleton data obtained from a depth camera. The skeleton data helps accurately extract the shape of the shadow that the user cast without requiring much computation. Our method also utilizes a distance field to remove the afterimage of shadow that may occur when the user moves. We verify the effectiveness of our system by performing various experiments in an interactive environment created by a front projection system.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.279-286
• /
• 2021

Recently, We are carrying out a policy of physical distancing of at least 1m from each other to prevent the spreading of COVID-19 disease in public places. In this paper, we propose a method for measuring distances between people in real time and an automation system that recognizes objects that are within 1 meter of each other from stereo images acquired by drones or CCTVs according to the estimated distance. A problem with existing methods used to estimate distances between multiple objects is that they do not obtain three-dimensional information of objects using only one CCTV. his is because three-dimensional information is necessary to measure distances between people when they are right next to each other or overlap in two dimensional image. Furthermore, they use only the Bounding Box information to obtain the exact coordinates of human existence. Therefore, in this paper, to obtain the exact two-dimensional coordinate value in which a person exists, we extract a person's key point to detect the location, convert it to a three-dimensional coordinate value using Stereo Vision and Camera Calibration, and estimate the Euclidean distance between people. As a result of performing an experiment for estimating the accuracy of 3D coordinates and the distance between objects (persons), the average error within 0.098m was shown in the estimation of the distance between multiple people within 1m.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.43-50
• /
• 2021

In this paper, we design and implement KITNESS, a windows application that feeds back the accuracy of fitness motions based on Kinect sensors. The feature of this application is to use Kinect's camera and joint recognition sensor to give feedback to the user to exercise in the correct fitness position. At this time, the distance between the user and the Kinect is measured using Kinect's IR Emitter and IR Depth Sensor, and the joint, which is the user's joint position, and the Skeleton data of each joint are measured. Using this data, a certain distance is calculated for each joint position and posture of the user, and the accuracy of the posture is determined. And it is implemented so that users can check their posture through Kinect's RGB camera. That is, if the user's posture is correct, the skeleton information is displayed as a green line, and if it is not correct, the inaccurate part is displayed as a red line to inform intuitively. Through this application, the user receives feedback on the accuracy of the exercise position, so he can exercise himself in the correct position. This application classifies the exercise area into three areas: neck, waist, and leg, and increases the recognition rate of Kinect by excluding positions that Kinect does not recognize due to overlapping joints in the position of each exercise area. And at the end of the application, the last exercise is shown as an image for 5 seconds to inspire a sense of accomplishment and to continuously exercise.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.10
• /
• pp.1103-1109
• /
• 2014

The latest CCTV camera are network camera in many cases. In this case when transmitting high-quality image by internet, it could be a large load on the internet because the amount of image data is very large. In this study, we propose a method which can reduce the video traffic in this case, and evaluate its performance. We used a method for transmitting and extracting a gesture information using ToF camera such as Kinect in certain circumstances. There may be restrictions on the application of the proposed method because it depends on the performance of the ToF camera. However, it can be applied efficiently to the security or safety management of a small interior space such as a home or office.

• Journal of Korea Game Society
• /
• v.8 no.2
• /
• pp.47-55
• /
• 2008

This paper introduces that SSFE(Skeleton System for Facial Expression) to deform facial expressions by rigging of skeletons does same functions with 14 facial muscles based on anatomy. A three dimensional animation tool (MAYA 8.5) is utilized for making the SSFE that presents deformation of mesh models implementing facial expressions around eyes, nose and mouse. The SSFE has a good reusability within diverse human mesh models. The reusability of SSFE can be understood as OSMU(One Source Multi Use) of three dimensional animation production method. It can be a good alternative technique for reducing production budget of animations. It can also be used for three dimensional animation industries such as virtual reality and game.