• Journal of the Korea Computer Graphics Society
• /
• v.8 no.3
• /
• pp.17-23
• /
• 2002

Motion capture system is widely used nowadays in the entertainment industry like movies, computer games and broadcasting. This system consist of several high resolution and high speed CCD cameras and expensive frame grabbing hardware for image acquisition. KAIST VR laboratory focused on low cost system for a few years and have been developed a LAN based optical motion capture system. But, by using low cost system some problems like occlusion, noise and swapping of markers' trajectory can be occurred. And more labor intensive work is needed for post-processing process. In this thesis, we propose a trajectory rectification algorithm by confidence model of markers attached on actor. Confidence model is based on graph structure and consist of linkage, marker and frame confidence. To reduce the manual work in post-processing, we have to reconstruct the marker graph by maximizing the frame confidence.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.34 no.1
• /
• pp.41-52
• /
• 2012

Purpose: Triangulation is the process of determining the location of a point by measuring angles to it from known points at either end of a fixed baseline. This point can be fixed as the third point of a triangle with one known side and two known angles. The aim of this study was to find a clinically adaptable method for applying an optical tracking navigation system to orthognathic surgery and to estimate its accuracy of measuring the bone displacement by use of triangulation methods. Methods: In orthognathic surgery, the head position is not fixed as in neurosurgery, so that a head tracker is needed to establish the reference point on the head surface byusing an optical tracking system. However, the operation field is interfered by its bulkiness that makes its clinical use difficult. To solve this problem, we designed a method using an Aquaplast splinting material and a mini-screw in applying a head tracker on a patient's forehead. After that, we estimated the accuracy of measuring displacements of the ball marker by an optical tracking system with a conventional head tracker (Group A) and with a newly designed head tracker (Group B). Measured values of ball markers' displacements by each optical tracking system were compared with values obtained from fusion CT images for an estimation of accuracy. Results: The accuracy of the optical tracking system with a conventional head tracker (Group A) is not suitable for clinical usage. Measured and predictable errors are larger than 10 mm. The optical tracking system with a newly designed head tracker (Group B) shows 1.59 mm, 6.34 mm, and 9.52 mm errorsin threeclinical cases. Conclusion: Most errors were brought on mainly from a lack of reproducibility of the head tracker position. The accuracy of the optical tracking system with a newly designed head tracker can be a useful method in further orthognathic navigation surgery even though the average error is higher than 2.0 mm.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.345-354
• /
• 2010

Visual tracking techniques for Augmented Reality are classified as either a marker tracking approach or a natural feature tracking approach. Marker-based tracking algorithms can be efficiently implemented sufficient to work in real-time on mobile devices. On the other hand, natural feature tracking methods require a lot of computationally expensive procedures. Most previous natural feature tracking methods include heavy feature extraction and pattern matching procedures for each of the input image frame. It is difficult to implement real-time augmented reality applications including the capability of natural feature tracking on low performance devices. The required computational time cost is also in proportion to the number of patterns to be matched. To speed up the natural feature tracking process, we propose a novel fast tracking method based on optical flow. We implemented the proposed method on mobile devices to run in real-time and be appropriately used with mobile augmented reality applications. Moreover, during tracking, we keep up the total number of feature points by inserting new feature points proportional to the number of vanished feature points. Experimental results showed that the proposed method reduces the computational cost and also stabilizes the camera pose estimation results.

• Journal of the Optical Society of Korea
• /
• v.17 no.2
• /
• pp.188-199
• /
• 2013

This paper presents a novel algorithm for nighttime detection of the lane markers painted on a road at night. First of all, the proposed algorithm uses neighborhood average filtering, 8-directional Sobel operator and thresholding segmentation based on OTSU's to handle raw lane images taken from a digital CCD camera. Secondly, combining intensity map and gradient map, we analyze the distribution features of pixels on boundaries of lanes in the nighttime and construct 4 feature sets for these points, which are helpful to supply with sufficient data related to lane boundaries to detect lane markers much more robustly. Then, the searching method in multiple directions- horizontal, vertical and diagonal directions, is conducted to eliminate the noise points on lane boundaries. Adapted Hough transformation is utilized to obtain the feature parameters related to the lane edge. The proposed algorithm can not only significantly improve detection performance for the lane marker, but it requires less computational power. Finally, the algorithm is proved to be reliable and robust in lane detection in a nighttime scenario.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.73-83
• /
• 2019

In this paper, we propose the augmented reality(AR) based driving navigation based on robust lane detection method to dynamic environment changes. The proposed technique uses the detected lane position as a marker which is a key element for enhancing driving information. We propose Symmetrical Local Threshold(SLT) algorithm which is able to robustly detect lane to dynamic illumination environment change such as shadows. In addition, by using Morphology operation and Connected Component Analysis(CCA) algorithm, it is possible to minimize noises in the image, and Region Of Interest(ROI) is defined through region division using a straight line passing through several vanishing points We also propose the augmented reality aided visualization method for Interchange(IC) and driving navigation using reference point detection based on the detected lane coordinates inside and outside the ROI. Validation experiments were carried out to assess the accuracy and robustness of the proposed system in vairous environment changes. The average accuracy of the proposed system in daytime, nighttime, rainy day, and cloudy day is 79.3% on 4600 images. The results of the proposed system for AR based IC and driving navigation were also presented. We are hopeful that the proposed research will open a new discussion on AR based driving navigation platforms, and thus, that such efforts will enrich the autonomous vehicle services in the near future.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.583-585
• /
• 2004

In this paper we will deal with a calibration method for low cost motion capture system using psd(position sensitive detection) optical sensor. To measure the incident direction of the light from LED emitted marker, the PSD is used the output current ratio on the electrode of PSD is proportional with the incident position of the light focused by lens. In order to defect the direction of the light, the current output is converted into digital voltage value by opamp circuits peak detector and AD converter with the digital value the incident position is measured. Unfortunately, due to the non-linearly problem of the circuit poor position accuracy is shown. To overcome such problems, we compensated the non-linearly by using least-square fitting method. After compensated the non-linearly in the circuit, the system showed more enhanced position accuracy.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.3 s.180
• /
• pp.179-186
• /
• 2006

Single-walled carbon nanotubes (SWNT) exhibit strong Raman signals as well as fluorescence emissions in the near infrared regions where most biomolecules are transparent. Such signals do not blink or photobleach under prolonged excitation. which is advantageous to optical nano-bio marker applications. In this paper, single walled carbon nanotubes are conjugated with specific types of single-stranded DNA in order to detect oligonucleotides of corresponding complimentary sequences. Dot blotting experiments and comparative Raman spectroscopy observations demonstrated excellent sensitivity and specificity of carbon nanotube-DNA probes. The results show the possibility of using SWNT as generic nano-bio markers for the precise detection of specific kinds of genes.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.8-13
• /
• 2008

At present many research projects on high-speed spindles are being conducted. These projects require a measurement technique which includes heat expansion, vibration and displacement measurement according to angular velocity. This paper presents the development of a measurement system for high-speed spindle displacement. The measurement system is based on $LabView^{(R)}$ and features the following sensors: optical sensor which reacts to the position of a marker on the spindle and enables two Laser Displacement Sensors(LDS). These Laser Displacement Sensors send their data to a DAQ(Data Acquisition Device). It is important that the delay time caused by the response times of the sensors as well as the sampling rate of the DAQ is considered because the spindle revolves at very high speeds.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.272-277
• /
• 2010

AR(Augmented Reality) needs medium between real and virtual, world, and recognition techniques are necessary to track an object continuously. Optical tracking using marker is mainly used, but it takes time and is inconvenient to attach marker onto the target objects. Therefore, many researchers try to develop markerless tracking techniques nowaday. In this paper, we extract features and 3D position from 3D objects and suggest realtime tracking based on these features and positions, which do not use just coplanar features and 2D position. We extract features using SURF, get rotation matrix and translation vector of 3D object using POSIT with these features and track the object in real time. If the extracted features are nor enough and it fail to track the object, then new features are extracted and re-matched to recover the tracking. Also, we get rotation in matrix and translation vector of 3D object using POSIT and track the object in real time.