• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.2
• /
• pp.124-129
• /
• 2002

Currently, image processing are used widely and have various types of characteristics with the applications of VOD(Video on demand), the web casting services, the video conference systems and virtual realities. Using the scene change, at every time of video image transitions, an editor can classify the video context and also require a function of in(Boxing insertion. Digital watermarking provides a solution to illegal copying of digital contents and has many other useful applications, including web broadcast monitoring, transaction tracking, authentication, copy control and device control. The Purpose of this thesis is to implement of nonlinear moving picture editor for the multiple watermarking. For the effective watermarking performance, this thesis considers the protection of image quality reduction and robustness for hiding information concurrently.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.390-392
• /
• 2003

Video mosaicing techniques have been widely used in virtual reality environments. Especially in GIS field, video mosaics are becoming more and more common in representing urban environments. Such applications mainly use spherical or panoramic mosaics that are based on images taken from a rotating camera around its nodal point. The viewpoint, however, is limited to location within a small area. On the other hand, 2D-mosaics, which are based on images taken from a translating camera, can acquire data in wide area. The 2D-mosaics still have some problems : it can‘t be applied to images taken from a rotational camera in large angle. To compensate those problems , we proposed a novel method for creating video mosaics in 3D space. The proposed algorithm consists of 4 steps: feature -based optical flow detection, camera orientation, 2D-image projection, and image registration in 3D space. All of the processes are fully automatic and successfully implemented and tested with real images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1434-1449
• /
• 2019

Video object segmentation is a significant task in computer vision, but its performance is not very satisfactory. A method of video object segmentation using weakly temporal information is presented in this paper. Motivated by the phenomenon in reality that the motion of the object is a continuous and smooth process and the appearance of the object does not change much between adjacent frames in the video sequences, we use a feed-forward architecture with motion estimation to predict the mask of the current frame. We extend an additional mask channel for the previous frame segmentation result. The mask of the previous frame is treated as the input of the expanded channel after processing, and then we extract the temporal feature of the object and fuse it with other feature maps to generate the final mask. In addition, we introduce multi-mask guidance to improve the stability of the model. Moreover, we enhance segmentation performance by further training with the masks already obtained. Experiments show that our method achieves competitive results on DAVIS-2016 on single object segmentation compared to some state-of-the-art algorithms.

• ETRI Journal
• /
• v.30 no.2
• /
• pp.338-340
• /
• 2008

In this letter, we propose a novel approach to detecting and tracking apartment buildings for the development of a video-based navigation system that provides augmented reality representation of guidance information on live video sequences. For this, we propose a building detector and tracker. The detector is based on the AdaBoost classifier followed by hierarchical clustering. The classifier uses modified Haar-like features as the primitives. The tracker is a motion-adjusted tracker based on pyramid implementation of the Lukas-Kanade tracker, which periodically confirms and consistently adjusts the tracking region. Experiments show that the proposed approach yields robust and reliable results and is far superior to conventional approaches.

• Journal of the Korea Safety Management & Science
• /
• v.3 no.3
• /
• pp.143-149
• /
• 2001

With the development of computer technologies and the increase of internet users, Internet plays an important role in job-recruitment business. However, almost of the sites which provide job offering and job hunting service, merely have the function such as simple inquiry for information corresponding to job offering and job hunting. In this research, the online website whose task is supporting whole procedure of recruitment for real enterprises is constructed to apply the interview procedures of the real enterprises through internet. We utilize the video conference to increase the reality for interview. Also it has functions such as presentation of application form and resume and self introduction using the video conference. Through the online recruitment website we can expect time and cost saving for recruitment for both sides of enterprise to hunt the person and people to seek the job.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.7
• /
• pp.660-665
• /
• 2011

Reconfigurable Flight Simulator for an airborne tactical mission based on virtual reality technology is developed as a software configurable cockpit with computer display as virtual instruments. It can simulate F-15K, KF-16, T/A-50 class fighter and depending on simulated cockpit, control stick and throttle are replaceable. For effective immersion, Video See-Through type HMD is applied.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1329-1336
• /
• 2016

This paper develops a 360 degree video system using multiple off-the-shelf webcams and a set of embedded boards. Existing 360 degree cameras have shortcomings that they do not support real-time video generation since recorded videos should be copied to computers or smartphones which then provide stitching. Another shortcoming is that wide FoV(Field of View) cameras are not able to provide sufficiently high resolution. Moreover, resulting images are visually distorted bending straight lines. By employing an array of 65 degree FoV webcams, we were able to generate videos on the spot and achieve over 6K resolution with much less distortion. We describe the configuration and algorithms of the proposed system. The performance evaluation results of our early stage prototype system are presented.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.229-232
• /
• 2013

영상실감증대를 위한 시각, 청각정보의 제시방식에 대해서는 많은 진보가 이루어 졌다. 반면 후각은 정의하기 어렵고 다루기 까다롭기 때문에 관련연구를 찾아보기 어렵다. 본 연구에서는 후각정보를 통한 영상실감증대 연구의 첫걸음으로 후각정보에 대한 사용자 수용도를 조사한 후 이에 근거하여 다양한 영상을 분류하였다. 이를 위해 먼저 영상에 냄새가 존재하는지 (냄새존재여부), 영상과 함께 해당 냄새를 경험하고 싶은지 (냄새제시선호), 영상에 어울리는 냄새가 내가 좋아하는 냄새인지 (냄새자체선호), 그리고 영상에 어울리는 냄새가 얼마나 구체적인지 (냄새의 구체성)라는 네 가지 질문을 선정하였다. 각 질문들에 높은 혹은 낮은 점수를 받을 만한 다양한 장르의 영상 (51)개를 수집한 후, 참가자들에게 하나씩 영상을 시청하게 한 후 위의 네 가지 질문에 대해 7점 척도로 평정하게 하였다. 영상분류를 위해 두 질문씩 쌍으로 묶어 각 질문의 척도를 2차원 평면의 X, Y축으로 설정한 후 평정값을 이용하여 영상분류를 위한 산포도를 구성하였다. 2차원 평면의 서로 다른 사분면에 위치한 영상군집들은 영상실감증대를 위한 후각정보 제시에 중요한 시사점을 줄 것으로 기대한다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07b
• /
• pp.1611-1614
• /
• 2005

In this paper, a new multi-view 3D video communication system for real-time Reality teleconferencing application is proposed by usin gthe IEEE 1394 digital cameras, Intel Xeon server computer system and Microsoft's DirectShow programming library and its performance is analyzed in terms of image-grabbing frame rate and number of views. The captured two-view image data is compressed by extraction of disparity data between them and transmitted to another client system through the communication network, in which multi-view could be synthesized with this received 2-view data using the intermediate view reconstruction technique and displayed on the multi-view 3D display system. From some experimental results, it is found that the proposed system can display 16-view 3D images with a gray of 8bits and a frame rate of 15fps.