• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.252-255
• /
• 2019

본 논문에서 Equirectangular projection(ERP) 영상을 행동 인식 모델에 입력하기전 제안하는 전처리를 통하여 성능을 향상시키는 것을 보인다. ERP 영상의 특성상 행동 인식을 하는데 불필요한 영역이 일반적인 2D 카메라로 촬영한 영상보다 많다. 또한 행동 인식은 사람이 Object of Interest(OOI)이다. 따라서 객체 인식모델로 인간 객체를 인식한 후 Region of Interest(ROI)를 추출하여 불필요한 영역을 없애고, 왜곡 또한 줄어든다. 본 논문에서 제안하는 기법으로 전처리 후 CNN-LSTM 모델로 성능을 테스트했다. 제안하는 방법으로 전처리를 한 데이터와 하지 않은 데이터로 행동 인식을 한 정확도로 비교하였으며 제안하는 기법으로 전처리 한 데이터로 행동 인식을 한 경우 데이터의 특성에 따라 다르지만, 최대 61%까지 성능향상을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.504-508
• /
• 2018

최근 ICT 산업게는 가상현실에 주목하고 있다. 시공간의 제약을 극복하고 실제 체험하는것과 비슷한 효과를 제공하는 VR 콘텐츠는 향후 유통 분야에도 폭넓은 활용이 예상된다. 대부분의 O2O 서비스에서 사용하고 있는 VR 기술은 단순히 360도 파노라마 형식의 사진을 보여주거나 VR 카메라로 중계 방송을 하는 콘텐츠가 대부분이었다. 따라서 본 논문에서는 3차원 VR 영상 스트리밍 서비스를 이용한 콘텐츠를 O2O 부동산 중개 서비스에 접목하여 360VR 컨텐츠 확장 가능성을 제시하고자 한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.2
• /
• pp.27-32
• /
• 2001

In this paper, the three dimension scanner system employing the parallel camera model is discussed. The camera calibration process and the three dimension scanning algorithm are developed. The laser strip line is utilized for assisting stereo matching. An object being scanned rotates on the plate which is activated by a stepping motor, The world coordinate which is. the measured distance from the camera to the object is converted into the model coordinate. The facets created from the point. cloud of the model coordinate is used for rendering the scanned model by using the graphic library such as OpenGL. The unmatched points having no validate matching points are interpolated from the validate matching points of the vicinity epipolar lines.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.463-470
• /
• 2017

Currently, virtual reality contents using VR images are spotlighted since they can be easily created and utilized. But because VR images are in a state of lack of interaction, there are limitations in their applications and usability.In order to overcome this problem, we propose a new method in which 360 degree panorama image and game engine are utilized to develop a high resolution of interactive VR service in real time. In particular, since the background image, which is represented by a form of panorama image, is pre-generated through a heavy rendering computation, it can be used to provide a immersive VR service with a relatively small amount of computation in run time on a low performance device. In order to show the effectiveness of our proposed method, an interactive game of a virtual zoo environment was implemented and illustrated showing that it can improve user interaction and immersion experience in a pretty good way.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.685-697
• /
• 2020

Immersive media videos, such as panorama and 360-degree videos, must provide a sense of realism as if the user visited the space in the video, so they should be able to represent the reality of the real world. However, in panorama and 360-degree videos, objects appear to overlap or disappear due to parallax between cameras, and such parallax distortion may interfere with immersion of the user's content. Accordingly, although many video stitching algorithms have been proposed to overcome parallax distortion, parallax distortion still occurs due to the low performance of the Object detection module and limitations of the Seam generation method. Therefore, this paper analyzes the limitations of the existing video stitching technology and proposes a method for detecting and correcting parallax distortion of video stitching using the LDPM (Local Differential Pixel Mean) image evaluation method that overcomes the limitations of the video stitching technique.

• Progress in Medical Physics
• /
• v.26 no.1
• /
• pp.18-27
• /
• 2015

Since a Compton camera has high detection sensitivity due to electronic collimation and a good energy resolution, it is a potential imaging system for nuclear medicine. In this study, we investigated the feasibility of a Compton camera for multi-tracer imaging and proposed a rotating Compton camera to satisfy Orlov's condition for 3D imaging. Two software phantoms of 140 and 511 keV radiation sources were used for Monte-Carlo simulation and then the simulation data were reconstructed by listmode ordered subset expectation maximization to evaluate the capability of multi-tracer imaging in a Compton camera. And the Compton camera rotating around the object was proposed and tested with different rotation angle steps for improving the limited coverage of the fixed conventional Compton camera over the field-of-view in terms of histogram of angles in spherical coordinates. The simulation data showed the separate 140 and 511 keV images from simultaneous multi-tracer detection in both 2D and 3D imaging and the number of valid projection lines on the conical surfaces was inversely proportional to the decrease of rotation angle. Considering computation load and proper number of projection lines on the conical surface, the rotation angle of 30 degree was sufficient for 3D imaging of the Compton camera in terms of 26 min of computation time and 5 million of detected event number and the increased detection time can be solved with multiple Compton camera system. The Compton camera proposed in this study can be effective system for multi-tracer imaging and is a potential system for development of various disease diagnosis and therapy approaches.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.197-205
• /
• 2018

Panoramic image is one of the technologies that are commonly used today. However, technical difficulties still exist in panoramic video production. Without a special camera such as a 360-degree camera, making panoramic video becomes more difficult. In order to make a panoramic video, it is necessary to synchronize the timeline of multiple videos shot at multiple locations. However, the timeline synchronization method using the internal clock of the camera may cause an error due to the difference of the internal hardware. In order to solve this problem, timeline synchronization between multiple videos using visual information or auditory information has been studied. However, there is a problem in accuracy and processing time when using video information, and there is a problem in that, when using audio information, there is no synchronization when there is sensitivity to noise or there is no melody. Therefore, in this paper, we propose a timeline synchronization method between multiple video using audio waveform. It shows higher synchronization accuracy and temporal efficiency than the video information based time synchronization method.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.309-314
• /
• 2014

To generate a complete 3D model from depth images of multiple RGB-D cameras, it is necessary to find 3D transformations between RGB-D cameras. This paper proposes a convenient view calibration technique using a spherical object. Conventional view calibration methods use either planar checkerboards or 3D objects with coded-pattern. In these conventional methods, detection and matching of pattern features and codes takes a significant time. In this paper, we propose a convenient view calibration method using both 3D depth and 2D texture images of a spherical object simultaneously. First, while moving the spherical object freely in the modeling space, depth and texture images of the object are acquired from all RGB-D camera simultaneously. Then, the external parameters of each RGB-D camera is calibrated so that the coordinates of the sphere center coincide in the world coordinate system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.47-50
• /
• 2020

최근 Panorama와 360도 영상이 대표되는 몰입형(Immersive) 미디어 콘텐츠의 사용이 증가하고 있다. 몰입형 영상 콘텐츠는 사용자에게 현장감을 제공해야 하지만, 촬영 카메라 간의 시차(Parallax)로 인해 영상 콘텐츠에서 시차 왜곡이 발생할 수 있고, 이는 사용자의 콘텐츠 몰입을 제한하기 때문에 해당 영상 콘텐츠의 제작 기술인 영상 스티칭의 높은 정확도가 요구되고 있다. 지금까지 스티칭 영상의 시차 왜곡을 줄이기 위하여 다중 호모그래피 추정 방법과 Seam Optimization 방법이 제안되었지만, 영상 내 사물 배치에 따라 기술 적용이 제한될 수 있다. 이에 본 논문에서는 Mask R-CNN을 활용하여 사물을 세그먼트화하고, 사물의 종류에 따라 각각 다른 가중치 적용을 통해 시차 왜곡을 방지하며, 영상 내 사물의 배치에 따라 시차 왜곡이 발생할 상황에서는 사용자의 인지 중요도가 낮은 사물로 시차 왜곡을 유도하는 영상 스티칭 방법을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.11-20
• /
• 2015

In this paper, we develop an intelligent mobile surveillance system based on binary CDMA for the unmanned automatic tracking and surveillance. That is, we implement a intelligent surveillance system using the binary CDMA wireless communication technology which is applied the merit of CDMA and TDMA on it complexly. This system is able to monitor the site of the accident on network in real time and process the various situations by implementing the security surveillance system. This system pursues an object by the 360-degree using camera, expands image using a PTZ(Pan/Tilt/Zoom) camera zooming function, identifies the mobile objects image within a screen and transfers the identified image to the remote site. Finally, we show the efficiency of the implemented system through the simulation of the controlled situations, such as tracking coverage on objects, object expansion, object detection number, monitoring the remote transferred image, number of frame per second by the image output signal etc..