• Journal of the Semiconductor & Display Technology
• /
• v.6 no.3
• /
• pp.65-70
• /
• 2007

A method to focus the object in camera system by applying the Hill climb algorithm from optical lens moving device (VCM; Voice coil motor) is proposed. The focusing algorithm from VCM is focus on the object but in these criteria is a well-known drawback; the focus is good only at same distance objects but the focus is bad (blur image) at different distance objects because of the DOF (Depth of focus) or DOF (Depth of field) at the optical characteristic. Here, the new camera system that describes the Reflector of free curvature systems (or Diffractive Fresnel lens) and the partition of focusing window area is proposed. The method to improve the focus in all areas (different distance objects) is proposed by new optical system (discrete auto in-focus) using the Reflector of free curvature systems (or Diffractive Fresnel lens) and by applying the partition of all areas. The proposal is able to obtain good focus in all areas.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.90-95
• /
• 2010

This paper describes the development of integrated head and eye tracker system. Vision based head tracker is performed and it has 7mm error in 300mm translation. The epi-polar method and point matching are used for determining a position of head and rotational degree. High brightness LEDs are installed on helmet and the installed pattern is very important to match the points of stereo system. Eye tracker also uses LED for constant illumination. A Position of gazed object(3m distance) is determined by pupil tracking and eye tracker has 1~5 pixel error. Integration of result data of each tracking system is important. RS-232C communication is applied to integrated system and triggering signal is used for synchronization.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.4
• /
• pp.208-215
• /
• 2013

Early iterations of the existing Global Positioning System (GPS)-based or radio lateration technique-based vehicle localization algorithms suffer from flip ambiguities, forged relative location information and location information exchange overhead, which affect the subsequent iterations. This, in turn, results in an erroneous neighbor-vehicle map. This paper proposes an extended information overlap measure (EIOM) algorithm to reduce the flip error rates by exchanging the neighbor-vehicle presence features in binary information. This algorithm shifts and associates three pieces of information in the Moore neighborhood format: 1) feature information of the neighboring vehicles from a vision-based environment sensor system; 2) cardinal locations of the neighboring vehicles in its Moore neighborhood; and 3) identification information (MAC/IP addresses). Simulations were conducted for multi-lane highway scenarios to compare the proposed algorithm with the existing algorithm. The results showed that the flip error rates were reduced by up to 50%.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.787-790
• /
• 1995

This paper proposes a method to recognize object with 2-dimension image. In most cases, it takes too many processes, complicate algorithm and time to recognize object with expert system because of inherent comfiguration of the object. This paper includes some processing steps such as pre-processing method, recognition method with neural network and learing algorithm of multi-layer perceptron using error backpropagation.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2001.05a
• /
• pp.28-33
• /
• 2001

Animation understanding and time-resolved analysis of the wake characteristic of 2-D sharp plane flows were executed by applying the multi-vision PIV to a sharp plane(three angle of attacks : $15^{\circ}, \; 30^{\circ}, \; 45^{\circ}$) submerged within a circulating water channel($Re = 2{\times}10^4$). The macroscopic shedding patterns were discussed in terms of instantaneous velocity, vorticity, velocity profile, kinetic energy, turbulent intensity, frequency analysis. Particularly, the time-averaged distribution of turbulent intensity in each experimental cases revealed separate island-like small regions magnitude of turbulent intensity was always strengthened.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.8
• /
• pp.689-695
• /
• 2004

This paper presents a robot system that combines computer network and an autonomous mobile robot where RTOS is installed. We propose a wireless communication protocol, and also implement it on the RTOS of the robot system. Main controller of the robot processes the control program as a task type in the real-time operating system. Peripheral devices are driven by the device driver functions with the dependency of the hardware. Because the client and server program was implemented to support the multi-platforms by Java SDK and Java JMF, it is easy to analyze programs, maintain system, and correct the errors in the system. End-user can control a robot with a vision showing remote sight over the Internet in real time, and the robot is moved keeping away from the obstacles by itself and command of the server received from end-user at the local client.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.68-75
• /
• 1999

Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn't often considered in conventional in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments.

• Smart Media Journal
• /
• v.2 no.1
• /
• pp.31-36
• /
• 2013

A robust and efficient text extraction is very important for an accuracy of Optical Character Recognition (OCR) systems. Natural scene images with degradations such as uneven illumination, perspective distortion, complex background and multi color text give many challenges to computer vision task, especially in text extraction. In this paper, we propose a method for extraction of the text in signboard images based on a combination of mean shift algorithm and weighting scheme of hue and saturation in HSI color space for clustering algorithm. The number of clusters is determined automatically by mean shift-based density estimation, in which local clusters are estimated by repeatedly searching for higher density points in feature vector space. Weighting scheme of hue and saturation is used for formulation a new distance measure in cylindrical coordinate for text extraction. The obtained experimental results through various natural scene images are presented to demonstrate the effectiveness of our approach.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.12
• /
• pp.1229-1236
• /
• 2008

A set of modal parameters of a stay-cable have been extracted fi:on a moving picture captured by a digital camera supported by shaking hands. It is hard to identify the center of targets attached on the cable surface from the blurred cable motion image, because of the high speed motion of cable, low sampling frequency of camera, and the shaking effect of camera. This study proposes a multi-template matching algorithm to resolve such difficulties. In addition, a sensitivity-based system identification algorithm is introduced to extract the natural frequencies and damping ratios from the ambient cable vibration data. Three sets of vibration tests are conducted to examine the validity of the proposed algorithms. The results show that the proposed technique is pretty feasible for extracting modal parameters from the severely shaking motion pictures.