• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.3
• /
• pp.636-642
• /
• 2017

In this paper, We proposed a novel hand-gesture recognition algorithm using concentric-circle expanding and tracing. The proposed algorithm determines region of interest of hand image through preprocessing the original image acquired by web-camera and extracts the feature of hand gesture such as the number of stretched fingers, finger tips and finger bases, angle between the fingers which can be used as intuitive method for of human computer interaction. The proposed algorithm also reduces computational complexity compared with raster scan method through referencing only pixels of concentric-circles. The experimental result shows that the 9 hand gestures can be recognized with an average accuracy of 90.7% and an average algorithm execution time is 78ms. The algorithm is confirmed as a feasible way to a useful input method for virtual reality, augmented reality, mixed reality and perceptual interfaces of human computer interaction.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.3
• /
• pp.20-31
• /
• 2008

In this paper, we propose a single view-based technique for the estimation of human height and position. Conventional techniques for the estimation of 3D geometric information are based on the estimation of geometric cues such as vanishing point and vanishing line. The proposed technique, however, back-projects the image of moving object directly, and estimates the position and the height of the object in 3D space where its coordinate system is designated by a marker. Then, geometric errors are corrected by using geometric constraints provided by the marker. Unlike most of the conventional techniques, the proposed method offers a framework for simultaneous acquisition of height and position of an individual resident in the image. The accuracy and the robustness of our technique is verified on the experimental results of several real video sequences from outdoor environments.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.2
• /
• pp.149-155
• /
• 2007

Recently, various devices requiring text input such as mobile phone IPTV, PDA and UMPC are emerging. The frequency of text entry for them is also increasing. This study was focused on the evaluation of Korean text entry interface. Various models to evaluate text entry interfaces have been proposed. Most of models were based on human cognitive process for text input. The cognitive process was divided into two components; visual scanning process and finger movement process. The time spent for visual scanning process was modeled as Hick-Hyman law, while the time for finger movement was determined as Fitts' law. There are three questions on the model-based evaluation of text entry interface. Firstly, are human cognitive processes (visual scanning and finger movement) during the entry of text sequentially occurring as the models. Secondly, is it possible to predict real text input time by previous models. Thirdly, does the human cognitive process for text input vary according to users' text entry speed. There was time gap between the real measured text input time and predicted time. The time gap was larger in the case of participants with high speed to enter text. The reason was found out investigating Eye-Hand Coordination during text input process. Differently from an assumption that visual scan on the keyboard is followed by a finger movement, the experienced group performed both visual scanning and finger movement simultaneously. Arrival Lead Time was investigated to measure the extent of time overlapping between two processes. 'Arrival Lead Time' is the interval between the eye fixation on the target button and the button click. In addition to the arrival lead time, it was revealed that the experienced group uses the less number of fixations during text entry than the novice group. This result will contribute to the improvement of evaluation model for text entry interface.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.106-123
• /
• 2024

This article takes the talk show "Beast Town" as an example to introduce the overall technical solution, technical difficulties and countermeasures for the combination of cartoon virtual characters and virtual studio technology, providing reference and experience for the multi-scenario application of digital humans. Compared with the live broadcast that combines reality and reality, we have further upgraded our virtual production technology and digital human-driven technology, adopted industry-leading real-time virtual production technology and monocular camera driving technology, and launched a virtual cartoon character talk show - "Beast Town" to achieve real Perfectly combined with virtuality, it further enhances program immersion and audio-visual experience, and expands infinite boundaries for virtual manufacturing. In the talk show, motion capture shooting technology is used for final picture synthesis. The virtual scene needs to present dynamic effects, and at the same time realize the driving of the digital human and the movement with the push, pull and pan of the overall picture. This puts forward very high requirements for multi-party data synchronization, real-time driving of digital people, and synthetic picture rendering. We focus on issues such as virtual and real data docking and monocular camera motion capture effects. We combine camera outward tracking, multi-scene picture perspective, multi-machine rendering and other solutions to effectively solve picture linkage and rendering quality problems in a deeply immersive space environment. , presenting users with visual effects of linkage between digital people and live guests.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.112-118
• /
• 2009

Skin color segmentation techniques have been widely utilized for face/hand detection and tracking in many applications such as a diagnosis system using facial information, human-robot interaction, an image retrieval system. In case of a video image, it is common that the skin color model for a target is updated every frame for the robust target tracking against illumination change. As for a single image, however, most of studies employ a fixed skin color model which may result in low detection rate or high false positive errors. In this paper, we propose a novel method for effective skin color segmentation in a single image, which modifies the conditions for skin color segmentation iteratively by the image feedback of segmented skin color region in a given image.

• Journal of the Korean Geographical Society
• /
• v.47 no.3
• /
• pp.426-439
• /
• 2012

The goal of this study is to propose a new method to capture the qualitative person spatial behavior. Beyond tracking or indexing the change of the location of a person, the changes in the relationships between a person and its environment are considered as the main source for the formal model of this study. Specifically, this paper focuses on the movement behavior of a person near the boundary of a region. To capture the behavior of person near the boundary of regions, a new formal approach for integrating an object's scope of influence is described. Such an object, a spatio-temporally extended point (STEP), is considered here by addressing its scope of influence as potential events or interactions area in conjunction with its location. The formalism presented is based on a topological data model and introduces a 12-intersection model to represent the topological relations between a region and the STEP in 2-dimensional space. From the perspective of STEP concept, a prototype analysis results are provided by using GPS tracking data in real world.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.774-784
• /
• 2017

Occupancy sensors installed in buildings and households turn off the light if the space is vacant. Currently PIR (pyroelectric infra-red) motion sensors have been utilized. Recently, the researches using camera sensors have been carried out in order to overcome the demerit of PIR that can not detect static people. If the tradeoff of cost and performance is satisfied, the camera sensors are expected to replace the current PIRs. In this paper, we propose vision sensor-based occupancy detection being composed of tracking, recognition and detection. Our softeware is designed to meet the real-time processing. In experiments, 14.5fps is achieved at 15fps USB input. Also, the detection accuracy reached 82.0%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1986-1994
• /
• 1999

In this paper, a semi-automatic approach is adopted to extract a semantic object from real-world video sequences human-aided segmentation for the first frame and automatic tracking for the remaining frames. The proposed algorithm has a hierarchical structure using watershed algorithm. Each hierarchy consists of 3 basic steps: First, seeds are extracted from the simplified current frame. Second, region growing bv a modified watershed algorithm is performed to get over-segmented regions. Finally, the segmented regions are classified into 3 categories, i.e., inside, outside or uncertain regions according to region probability values, which are acquired by the probability map calculated from an estimated motion-vector field. Then, for the remaining uncertain regions, the above 3 steps are repeated at lower hierarchies with less simplified frames until every region is classified into a certain region. The proposed algorithm provides prospective results in studio-quality sequences such as 'Claire', 'Miss America', 'Akiyo', and 'Mother and daughter'.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.2
• /
• pp.82-85
• /
• 2014

It is helpful to use Intelligent Video Surveillance to replace and supplement the demerit which can possibly occur due to the mistake that can be made by human management. To accomplish this, it is essential that the system should digitalize image information from surveillance camera so that the system, itself, can be able to locate a object and to analyze the pattern of the object. Also, it is imperative that the system should have ability to operate a alarm and a entrance blocking system and to notify a situation to a security manager. Zooming a small object form a screen, however, requires a exact zooming ratio of the object and a shift of centric coordinate. In this paper, It is able to locate and observe closely a object from flexible background, regardless of the distance, by calculating a zooming ratio according to object moment, pan coordinate, and tilt coordinate.