• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1591-1600
• /
• 2007

Camera position information from 2D face image is very important for that make the virtual 3D face model synchronize to the real face at view point, and it is also very important for any other uses such as: human computer interface (face mouth), automatic camera control etc. We present an algorithm to detect human face region and mouth, based on special color features of face and mouth in $YC_bC_r$ color space. The algorithm constructs a mouth feature image based on $C_b\;and\;C_r$ values, and use pattern method to detect the mouth position. And then we use the geometrical relationship between mouth position information and face side boundary information to determine the camera position. Experimental results demonstrate the validity of the proposed algorithm and the Correct Determination Rate is accredited for applying it into practice.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.95.2-95
• /
• 2002

1. Introduction of Camera Detection system Camera Detection system is an equipment that can detect realtime traffic information by image processing techniques. This information can be used to analyze and control road traffic flow. It is also used as a method to detect and control traffic flow for ITS(Intelligent Transportation System). Traffic information includes speed, head way, traffic flow, occupation time and length of queue. There are many detection systems for traffic data. But video detection system can detect multiple lanes with only one camera and collect various traffic information. So it is thought to be the most efficient method of all detection system. Though the...

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.5
• /
• pp.57-64
• /
• 2004

We proposed the eye gaze tracking system under natural head movements, which consists of one narrow-view field CCD camera, two mirrors which of reflective angles are controlled and active infra-red illumination. The mirrors' angles were computed by geometric and linear algebra calculations to put the pupil images on the optical axis of the camera. Our system allowed the subjects head to move 90cm horizontally and 60cm vertically, and the spatial resolutions were about 6$^{\circ}$ and 7$^{\circ}$, respectively. The frame rate for estimating gaze points was 10～15 frames/sec. As gaze mapping function, we used the hierarchical generalized regression neural networks (H-GRNN) based on the two-pass GRNN. The gaze accuracy showed 94% by H-GRNN improved 9% more than 85% of GRNN even though the head or face was a little rotated. Our system does not have a high spatial gaze resolution, but it allows natural head movements, robust and accurate gaze tracking. In addition there is no need to re-calibrate the system when subjects are changed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1060-1069
• /
• 2019

Pedestrian-based camera self-calibration methods are suitable for video surveillance systems since they do not require complex calibration devices or procedures. However, using arbitrary pedestrians as calibration targets may result in poor calibration accuracy due to the unknown height of each pedestrian. To solve this problem in the real surveillance environments, this paper proposes a novel Bayesian approach. By assuming known statistics on the height of pedestrians, we construct a probabilistic model that takes into account uncertainties in both the foot/head locations and the pedestrian heights, using foot-head homology. Since solving the model directly is infeasible, we use variational Bayesian inference, an approximate inference algorithm. Accordingly, this makes it possible to estimate the height of pedestrians and to obtain accurate camera parameters simultaneously. Experimental results show that the proposed algorithm is robust to noise and provides accurate confidence in the calibration.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.11a
• /
• pp.380-383
• /
• 2003

The purpose of this study is to develope prototype EPID system and improve image quality of radiation therapy field imaging system using CCD camera. For this research we used Linac(Clinac 4/100), Copper metal plate, $Gd_2O_2S_2$ phosphor and CCD camera(Photronic). In this study we find best thickness of buil-up metal plate and acquired projection image of humanoid head phantom. Also we enhanced raw image data using superposition and histogram stretching method. Through the thickness optimized of metal plate and image processing, we confirmed of an improved image quality of an EPID system using CCD camera. As result, highest quality image was acquired at 1mm thickness of Copper metal plate and improved image quality by image processing methods.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.451-454
• /
• 2007

This paper presents the pattern characteristic using the electrostatic drop-on-demand ink-jet printing system. In order to achieve the pattern characteristic of electrostatic inkjet printing, the capillary inkjet head system is fabricated using capillary tube, Pt wire and electrode, and is packaged by acrylic board for the accurate alignment between wire and electrode-hole. The applied DC voltage of 1.4 $\sim$ 2.0 kV used for the observation of electrostatic droplet ejection. Electrostatic droplet ejection is directly observed using a high-speed camera. For investigated pattern characteristic, conductive inkjet silver ink used. The higher voltage has a good condition which has micro dripping mode. Also, the droplet size decreases with increasing the supplied DC voltage. This paper shows the pattern which is formed by about 300um. Also, capillary inkjet head system will be applied industrial area comparing conventional electrostatic inkjet head system.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.11-17
• /
• 2020

This paper proposed the design of a new window signage system architecture, which utilized a window of a building, with attached LED for visible light communication. In this paper, the proposed method using the LED strip to transmit light data and receive the data through a HMD with a smart device camera. The LED strip attached to the existing building window, as a part of semi-transparent signage. Semi-transparent signage based on a controllable LED strip-modules and attached to the window used to provide entertainment contents and the information service to people through optical camera communication (OCC) as well. Also, this work suggests using the camera supplied Head Mounted Device (HMD) as an OCC receiver. The LED attached window signage system structure described in this paper can be utilized in various buildings infrastructure like house, shopping areas, industrial building, etc.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.54-61
• /
• 2015

In recent years, there has been increasing use of automatic surveillance and monitoring systems based on vision sensors. Humans are often the most important target in the systems, but processing human images is difficult due to the small sizes and flexible motions. Particularly, occlusion among pedestrians in camera images brings practical problems. In this paper, we propose a novel method to separate image regions of occluded pedestrians. A camera equipped with a wide angle lens is attached to the ceiling of a building corridor for sensing pedestrians with a wide field of view. The output images of the camera are processed for the human detection, tracking, identification, distortion correction, and occlusion handling. We resolve the occlusion problem adaptively depending on the angles and positions of their heads. Experimental results showed that the proposed method is more efficient and accurate compared with existing methods.