• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.232-234
• /
• 2021

본 논문에서는 딥러닝 얼굴 인식을 이용하여 실시간 360 공간 Classroom 과 실시간을 기반으로 한 가상 360 공간 Classroom 을 제안한다. MTCNN 을 이용한 얼굴 검출 및 Inception Resnet V1 모델을 이용한 딥러닝 기법을 통해 얼굴인식을 진행하고 HSV 색공간 기반의 화자 판별, 아바타 Rendering, 출석 체크 등을 진행한다. 이후 시각화를 위해 제작한 Web UI/UX 를 통해 사용자에게 현실과 가상 공간을 넘나드는 Twin Classroom 을 제공한다. 따라서 사용자는 새로운 화상 교육 플랫폼에서 보다 개선되고 생동감 있는 Classroom 에서 교육을 받을 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.407-408
• /
• 2022

In this paper, we will look at the components of the FPGA-based object recognition system one by one. Let's take a look at each function of the components camera, DLM, service system, video output monitor, deep trainer software, and external deep learning software.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.297-299
• /
• 2017

Recently, the application fields of augmented reality(AR) are rapidly increasing, and related contents are also increasing in demand. In this way, object-based marker recognition is required for service of AR contents in mobile environment. At this time, in order to provide information corresponding to the marker, a technique of generating and servicing a virtual object corresponding to a specific marker is used. However, when a virtual object corresponding to a marker is held on the AR screen, a phenomenon occurs that an object of the marker unstably shakes due to various reasons such as camera shake and camera movement. As described above, the AR service based on the mobile device has a problem that it is difficult to represent objects stably. In this paper, we propose a stable marker recognition and tracking technique by applying the filtering technique according to the physical state change of the device when recognizing fixed markers in mobile AR environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.281-284
• /
• 2010

In this paper, we present Hand-gesture recognition for actual computing into color images from camera. Color images are binarization and labeling by using the YCbCr Color model. Respectively label area seeks the center point of the hand from to search Maximum Inscribed Circle which applies Voronoi-Diagram. This time, searched maximum circle and will analyze the elliptic ingredient which is contiguous so a hand territory will be able to extract. we present the presentation contral system using elliptic element and Maximum Inscribed Circle. This algorithm is to recognize the various environmental problems in the hand gesture recognition in the background objects with similar colors has the advantage that can be effectively eliminated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.6B
• /
• pp.663-673
• /
• 2011

Applications of two dimensional image codes like QR and color code on mobile phone are spreading widely and in lieu of that, better decoding technology and platform designs are required. Futhermore "Bokode" technology which recognizes the defocus-blur image information from imperceptible visual tiny code on ordinary digital camera has been announced newly. There is an urgent need for competitive strategies to activate 2D image code industry and R&D under smart environment. This paper focused on suggesting valuable idea and practical task through investigation and analysis required for supporting of thus strategy construction. Description consist of introduction, technological tendency for R&D, patent and market, implementation task, conclusion and suggestion.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.200-204
• /
• 2008

In this paper, to solve localization problem for out-door navigation of robotic vehicles, a particle filter based 3D object recognition framework that can estimate the pose of a building or its entrance is presented. A particle filter framework of multiple evidence fusion and model matching in a sequence of images is presented for robust recognition and pose estimation of 3D objects. The proposed approach features 1) the automatic selection and collection of an optimal set of evidences 2) the derivation of multiple interpretations, as particles representing possible object poses in 3D space, and the assignment of their probabilities based on matching the object model with evidences, and 3) the particle filtering of interpretations in time with the additional evidences obtained from a sequence of images. The proposed approach has been validated by the stereo-camera based experimentation of 3D object recognition and pose estimation, where a combination of photometric and geometric features are used for evidences.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.924-926
• /
• 2017

본 논문에서는 좁고 곡률이 큰 도로에서의 자율 주행을 위한 AVM 시스템 기반의 알고리즘을 제안한다. 기존의 전방을 주시하는 모노/스테레오 카메라를 이용한 차선 인식 방법을 이용한 자율주행 알고리즘은 모노/스테레오 카메라의 제한된 FOV (Field of View)로 인해 좁고 곡률이 큰 도로에서의 자율 주행에 한계가 있다. 제안하는 알고리즘은 AVM 시스템을 기반으로 하여 이 한계를 극복하고자 한다. AVM 시스템에서 얻은 영상을 차선의 색상 정보를 이용해 차선의 영역을 이진화 한다. 이진화 영상으로부터, 차량의 뒷바퀴 주변의 관심영역을 시작으로 재귀적 탐색법을 이용하여 좌, 우 차선을 검출한다. 검출된 좌, 우 차선의 중앙선을 차량의 경로로 삼고 조향각을 산출해 낸다. 제한하는 알고리즘을 실제 차량에 적용시킨 실험을 수행하였고, 운전면허 시험장의 코스를 차선의 이탈없이 주행 가능함을 실험적으로 확인하였다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.258-266
• /
• 2011

AR(Augmented Reality) technology is now easily shown around us with respect to its applicable areas' being spreaded into various shapes since the usage is simply generalized and many-sided. Currently existing camera vision based AR used marker based methods rather than using real world's informations. For the marker based AR technology, there are limitations on applicable areas and its environmental properties that a user could immerse into the usage of application program. In this paper, we proposed a novel AR method which users could recognize objects from the real world's data and the related 3-dimensional contents are also displayed. Those are done using image processing skills and a smart mobile embedded camera for terminal based AR implementations without any markers. Object recognition is done from the comparison of pre-registered and referenced images. In this process, we tried to minimize the amount of computations of similarity measurements for improving working speed by considering features of smart mobile devices. Additionally, the proposed method is designed to perform reciprocal interactions through touch events using smart mobile devices after the 3-dimensional contents are displayed on the screen. Since then, a user is able to acquire object related informations through a web browser with respect to the user's choice. With the system described in this paper, we analyzed and compared a degree of object recognition, working speed, recognition error for functional differences to the existing AR technologies. The experimental results are presented and verified in smart mobile environments to be considered as an alternate and appropriate AR technology.

• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.105-115
• /
• 2014

In this research, we developed video analytic algorithms to detect water-level automatically and a system for proactive alarming using intelligent CCTV cameras. We applied these algorithms and a system to test-beds and verified for practical use. We made camera-selection policies and operation plans to keep the detection accuracy high and to optimize the suitability for the ever-changing weather condition, while the environmental factors such as camera shaking and weather condition can affect to detection accuracy. The estimation result of algorithms showed 90% detection accuracy for all CCTV camera types. For water level detection, NIR camera performed great. NIR camera performed over 95% accuracy in day or night, suitable in natural weather condition such as shaking condition, fog, and low light, needs similar installment skills with common cameras, and spends only 15% high cost. As a result, we practically tested water level detection algorithms and operation system based on intelligent CCTV camera. Furthermore, we expect the positive evidences when it is applied for public use.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.46-57
• /
• 2022

In this paper, multi-region based Radial Graph Convolutional Network (MRGCN) algorithm which can perform end-to-end action recognition using the optical flow and gradient of input image is described. Because this method does not use information of skeleton that is difficult to acquire and complicated to estimate, it can be used in general CCTV environment in which only video camera is used. The novelty of MRGCN is that it expresses the optical flow and gradient of the input image as directional histograms and then converts it into six feature vectors to reduce the amount of computational load and uses a newly developed radial type network model to hierarchically propagate the deformation and shape change of the human body in spatio-temporal space. Another important feature is that the data input areas are arranged being overlapped each other, so that information is not spatially disconnected among input nodes. As a result of performing MRGCN's action recognition performance evaluation experiment for 30 actions, it was possible to obtain Top-1 accuracy of 84.78%, which is superior to the existing GCN-based action recognition method using skeleton data as an input.