• Journal of Korea Multimedia Society
• /
• v.16 no.5
• /
• pp.619-628
• /
• 2013

In this paper, we describe a strongly improved tracking method using combination of CAMshift and Kalman filter algorithm. CAMshift algorithm doesn't consider the object's moving direction and velocity information when it set the search windows for tracking. However if Kalman filter is combined with CAMshift for setting the search window, it can accurately predict the object's location with the object's present location and velocity information. By using this prediction before CAMshift algorithm, we can track fast moving objects successfully. Also in this research, we show better tracking results than conventional approaches which make use of single color information by using both color information of HSV and YCrCb simultaneously. This modified approach obtains more robust color segmentation than others using single color information.

• Laser Solutions
• /
• v.12 no.1
• /
• pp.19-24
• /
• 2009

Because of its fast and precise welding performance, laser welding is becoming a new excellent welding method. However, the precise focusing and robust seam tracking are required to apply laser welding to the practical fields. In order to laser weld a type of T joint like a circular pipe on a square pipe, which could be met in the three dimensional structure such as an aluminum space frame, a visual sensor system was developed for automation of focusing and seam tracking. The developed sensor system consists of a digital CCD camera, a structured laser, and a vision processor. It is moved and positioned by a 2-axis motorized stage, which is attached to a 6 axis robot manipulator with a laser welding head. After stripe-type structured laser illuminates a target surface, images are captured through the digital CCD camera. From the image, seam error and defocusing error are calculated using image processing algorithms which includes efficient techniques handling continuously changed image patterns. These errors are corrected by the stage off-line during welding or teaching. Laser welding of a circular pipe on a square pipe was successful with the vision tracking system by reducing the path positioning and de focusing errors due to the robot teaching or a geometrical variation of specimens and jig holding.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1396-1406
• /
• 2018

Lane detection is a key function in developing autonomous vehicle technology. In this paper, we propose a lane marker detection algorithm robust to environmental variation targeting low cost embedded computing devices. The proposed algorithm consists of two phases: initialization phase which is slow but has relatively higher accuracy; and the tracking phase which is fast and has the reliable performance in a limited condition. The initialization phase detects lane markers using a set of filters utilizing the various features of lane markers. The tracking phase uses Kalman filter to accelerate the lane marker detection processing. In a tracking phase, we measure the reliability of the detection results and switch it to initialization phase if the confidence level becomes below a threshold. By combining the initialization and tracking phases we achieved high accuracy and acceptable computing speed even under a low cost computing resources in which we cannot use the computing intensive algorithm such as deep learning approach. Experimental results show that the detection accuracy is about 95% on average and the processing speed is about 20 frames per second with Raspberry Pi 3 which is low cost device.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.35-43
• /
• 2019

Template tracking refers to the procedure of finding the most similar image patch corresponding to the given template through an image sequence. In order to obtain more accurate trajectory of the template, the template requires to be updated to reflect various appearance changes as it traverses through an image sequence. To do that, appearance images are used to model appearance variations and these are obtained by the computation of the principal components of the augmented image matrix at every iteration. Unfortunately, it is prohibitively expensive to compute the principal components at every iteration. Thus in this paper, we suggest a new Sliding Window based truncated URV Decomposition (TURVD) algorithm which enables updating their structure by recycling their previous decomposition instead of decomposing the image matrix from the beginning. Specifically, we show an efficient algorithm for updating and downdating the TURVD simultaneously, followed by the rank-one update to the TURVD while tracking the decomposition error accurately and adjusting the truncation level adaptively. Experiments show that the proposed algorithm produces no-meaningful differences but much faster execution speed compared to the typical algorithms in template tracking applications, thereby maintaining a good approximation for the principal components.

• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.861-877
• /
• 2016

This paper first discusses the disadvantages of the existing CamShift Algorithm for real time face tracking, and then proposes a new Camshift Algorithm that performs better than the existing algorithm. The existing CamShift Algorithm shows unstable tracking when tracing similar colors in the background of objects. This drawback of the existing CamShift is resolved by using Kinect’s pixel-by-pixel depth information and the Skin Detection algorithm to extract candidate skin regions based on HSV color space. Additionally, even when the tracking object is not found, or when occlusion occurs, the feature point-based matching algorithm makes it robust to occlusion. By applying the improved CamShift algorithm to face tracking, the proposed real-time face tracking algorithm can be applied to various fields. The results from the experiment prove that the proposed algorithm is superior in tracking performance to that of existing TLD tracking algorithm, and offers faster processing speed. Also, while the proposed algorithm has a slower processing speed than CamShift, it overcomes all the existing shortfalls of the existing CamShift.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.15 no.4
• /
• pp.506-517
• /
• 2015

This paper presents a 1.248 Gb/s - 2.918 Gb/s low-power receiver MIPI-DigRF M-PHY with a fully digital frequency detection loop. MIPI-DigRF M-PHY should be operated in a very short training time which is $0.01{\mu}s$ the for HS-G2B mode. Because of this short SYNC pattern, clock and data recovery (CDR) should have extremely fast locking time. Thus, the quarter rate CDR with a fully digital frequency detection loop is proposed to implement a fast phase tracking loop. Also, a low power CDR architecture, deserializer and voltage controlled oscillator (VCO) are proposed to meet the low power requirement of MIPI-DigRF M-PHY. This chip is fabricated using a $0.11{\mu}m$ CMOS process, and the die area is $600{\mu}m{\times}250{\mu}m$. The power consumption of the receiver is 16 mW from the supply voltage of 1.1 V. The measured lock time of the CDR is less than 20 ns. The measured rms and peak jitter are $35.24ps_{p-p}$ and $4.25ps_{rms}$ respectively for HS-G2 mode.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.728-737
• /
• 2015

Stitching algorithm obtain a descriptor of the feature points extracted from multiple images, and create a single image through the matching process between the each of the feature points. In this paper, a feature extraction and matching techniques for the creation of a high-speed panorama using video input is proposed. Features from Accelerated Segment Test(FAST) is used for the feature extraction at high speed. A new feature point matching process, different from the conventional method is proposed. In the matching process, by tracking region containing the feature point through the Mean shift vector required for matching is obtained. Obtained vector is used to match the extracted feature points. In order to remove the outlier, the RANdom Sample Consensus(RANSAC) method is used. By obtaining a homography transformation matrix of the two input images, a single panoramic image is generated. Through experimental results, we show that the proposed algorithm improve of speed panoramic image generation compared to than the existing method.

• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.123-128
• /
• 2012

In this paper, we propose a landmark-detection system of object for more accurate object recognition. The landmark-detection system of object becomes divided into a learning stage and a detection stage. A learning stage is created an interest-region model to set up a search region of each landmark as pre-information necessary for a detection stage and is created a detector by each landmark to detect a landmark in a search region. A detection stage sets up a search region of each landmark in an input image with an interest-region model created in the learning stage. The proposed system uses Fast Fourier Transform to detect landmark, because the landmark-detection is fast. In addition, the system fails to track objects less likely. After we developed the proposed method was applied to environment video. As a result, the system that you want to track objects moving at an irregular rate, even if it was found that stable tracking. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Smart Structures and Systems
• /
• v.14 no.6
• /
• pp.1197-1220
• /
• 2014

Accurate actuator tracking is critical to achieve reliable real-time hybrid simulation results for earthquake engineering research. The frequency-domain evaluation approach provides an innovative way for more quantitative post-simulation evaluation of actuator tracking errors compared with existing time domain based techniques. Utilizing the Fast Fourier Transform the approach analyzes the actuator error in terms of amplitude and phrase errors. Existing application of the approach requires using the complete length of the experimental data. To improve the computational efficiency, two techniques including data decimation and frequency decimation are analyzed to reduce the amount of data involved in the frequency-domain evaluation. The presented study aims to enhance the computational efficiency of the approach in order to utilize it for future on-line actuator tracking evaluation. Both computational simulation and laboratory experimental results are analyzed and recommendations on the two decimation factors are provided based on the findings from this study.

• Proceedings of the KIPE Conference
• /
• 2001.10a
• /
• pp.622-625
• /
• 2001

Photovoltaic generation systems need MPPT (Maximum Power Point Tracking) control because the output power depends on the operating voltage and current. Therefore, many researchers propose various types of MPPT control methods. A new MPPT control scheme is proposed in this paper in order to realize higher efficiency with simple calculation. The line search algorithm with fibonacci sequence which is one of the optimizing method is employed for the MPPT. The line search method is modified for real-time operation. The method is verified by simulations and experiments. It is concluded that the scheme can respond fast variation of irradiance.