• Journal of the Korean Society of Radiology
• /
• v.13 no.6
• /
• pp.825-830
• /
• 2019

A detector module measuring a depth of interaction was developed using silicon photomultiplier (SiPM) and two layers of scintillation crystal array treated with multiple reflectors. When reconstructing an image based on a signal obtained by using different types of reflector of each layer, the interaction positions of scintillation pixels and gamma rays could be tracked by utilizing the feature that all scintillation pixels were recorded at different positions. The bottom layer uses a specular reflector, and the top layer uses a diffuse reflector to differently process the size of the signal obtained from the SiPM. The optical grease was used to recude the sharp refractive index change between the layers of scintillator and the SiPM. The signals obtained from the 16 SiPMs were reduced to four signals using the Anger equations, and the images were reconstructed using them. All the scintillation pixels composed of the two layers appeared in the reconstructed image, which distinguished the layer where the scintillation pixels and gamma rays interacted. If the detectors, which measure the interaction depth of two layers using different reflectors, will be applied to preclinical positron emission tomography, the degradation of spatial resolution appearing outside the field of interest could be solved.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.495-505
• /
• 2019

Typical algorithms of deep learning include CNN(Convolutional Neural Networks), which are mainly used for image recognition, and RNN(Recurrent Neural Networks), which are used mainly for speech recognition and natural language processing. Among them, CNN is able to learn from filters that generate feature maps with algorithms that automatically learn features from data, making it mainstream with excellent performance in image recognition. Since then, various algorithms such as R-CNN and others have appeared in object detection to improve performance of CNN, and algorithms such as YOLO(You Only Look Once) and SSD(Single Shot Multi-box Detector) have been proposed recently. However, since these deep learning-based detection algorithms determine the success of the detection in the still images, stable object tracking and detection in the video requires separate tracking capabilities. Therefore, this paper proposes a method of combining Kalman filters into deep learning-based detection networks for improved object tracking and detection performance in the video. The detection network used YOLO v2, which is capable of real-time processing, and the proposed method resulted in 7.7% IoU performance improvement over the existing YOLO v2 network and 20 fps processing speed in FHD images.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.509-521
• /
• 2016

A novel Samples Balanced Genetic Algorithm combined with Extreme Learning Machine (SBGA-ELM) for Parkinson's Disease diagnosis and detecting bio-markers is presented in this paper. Proposed approach uses genes' expression data of 22,283 genes from open source ParkDB data base for accurate PD diagnosis and detecting bio-markers. Proposed SBGA-ELM includes two major steps: feature (genes) selection and classification. Feature selection procedure is based on proposed Samples Balanced Genetic Algorithm designed specifically for genes expression data from ParkDB. Proposed SBGA searches a robust subset of genes among 22,283 genes available in ParkDB for further analysis. In the "classification" step chosen set of genes is used to train an Extreme Learning Machine (ELM) classifier for an accurate PD diagnosis. Discovered robust subset of genes creates ELM classifier with stable generalization performance for PD diagnosis. In this research the robust subset of genes is also used to discover 24 bio-markers probably responsible for Parkinson's Disease. Discovered robust subset of genes was verified by using existing PD diagnosis approaches such as SVM and PBL-McRBFN. Both tested methods caused maximum generalization performance.

• Journal of Broadcast Engineering
• /
• v.21 no.1
• /
• pp.36-42
• /
• 2016

Recently, many 3D contents have been produced through the multiview camera system. In this system, since a difference of the viewpoint between color and depth cameras is inevitable, the camera parameter plays the important role to adjust the viewpoint as a preprocessing step. The conventional camera calibration method is inconvenient to users since we need to choose pattern features manually after capturing a planar chessboard with various poses. Therefore, we propose a semi-auto camera calibration method using a circular sampling and an homography estimation. Firstly, The proposed method extracts the candidates of the pattern features from the images by FAST corner detector. Next, we reduce the amount of the candidates by the circular sampling and obtain the complete point cloud by the homography estimation. Lastly, we compute the accurate position having the sub-pixel accuracy of the pattern features by the approximation of the hyper parabola surface. We investigated which factor affects the result of the pattern feature detection at each step. Compared to the conventional method, we found the proposed method released the inconvenience of the manual operation but maintained the accuracy of the camera parameters.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.144-152
• /
• 2007

We propose a 3D modeling method for surface inspection of non-linear moving object. The laser lines reflect the surface curvature. We can acquire 3D surface information by analyzing projected laser lines on object. ill this paper, we use multi-line laser to make use of robust of single stripe method and high speed of single frame. Binarization and channel edge extraction method were used for robust laser line extraction. A new labeling method was used for laser line labeling. We acquired sink information between each 3D reconstructed frame by feature point matching, and registered each frame to one whole image. We verified the superiority of proposed method by applying it to container damage inspection system.

• New & Renewable Energy
• /
• v.3 no.1 s.9
• /
• pp.38-45
• /
• 2007

To characterize thermo-chemical feature of sugar conversion of woody biomass, poplar wood ($Populus\;alba{\times}glandulosa$) powder was treated with supercritical water system. Supercritical water treatment (SCWT) was performed for 60 seconds at different temperatures (subcritical zone 350; supercritical zone $300,\;400,\;425^{\circ}C$) under two pressures $230{\pm}10atm$ as well as $330{\pm}10atm$, respectively, using flow type system. After separation of solid residues from SCWT products, the monomeric sugars in aqueous part converted from poplar wood powder were quantitatively determined by high performance anionic exchange chromatography [HPAEC] equipped with PAD detector and Carbo Pac PA10 column. As the temperature treated increased, the degradation of poplar wood powder was enhanced and ca 83% of woody biomass was dissolved into the water at $425^{\circ}C$. However, the pressure didn't help the degradation of biomass components. At subcritical temperature range, xylose was first formed by degradation of xylan, which is main hemicellulose component in hardwood species, while cellulose degradation started at the transition zone between sub and supercritical conditions and was remarkably accelerated at the supercritical temperature. In the supercritical water system the maximum yield of monomeric sugars amounts to ca. 7.3% based on oven dried wood weight at $425^{\circ}C$.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.95-102
• /
• 2004

The COSMOS is an adaptive traffic control systems that can adjust signal timing parameters in response to various traffic conditions. To evaluate the performance of the COSMOS systems, the field study is only practical option because any evaluation tools are not available. To overcome this limitation, a newly integrated interfacing simulator between a microscopic simulation program and COSMOS was developed. In this paper, a detector module and a signal timing module as well as general feature of the simulator were described. A validation test was performed to verify the accuracy of the data flow within the simulator. It was shown that the accuracy level of information from the simulator was high enough for real application. Several practical comments on further studies were also included to enhance the functional specifications of the simulator.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1281-1297
• /
• 2016

In recent years, personal videos have seen a tremendous growth due to the substantial increase in the use of smart devices and networking services in which users create and share video content easily without many restrictions. However, taking both into account would significantly improve event detection performance because videos generally have multiple modalities and the frame data in video varies at different time points. This paper proposes an event detection method. In this method, high-level features are first extracted from multiple modalities in the videos, and the features are rearranged according to time sequence. Then the association of the modalities is learned by means of DNN to produce a personal video event detector. In our proposed method, audio and image data are first synchronized and then extracted. Then, the result is input into GoogLeNet as well as Multi-Layer Perceptron (MLP) to extract high-level features. The results are then re-arranged in time sequence, and every video is processed to extract one feature each for training by means of DNN.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.71-80
• /
• 2012

This paper proposes vehicle detection and tracking algorithm using a CCD camera. The proposed algorithm uses Haar-like wavelet edge detector to detect features of vehicle and estimates vehicle's location using calibration information of an image. After that, extract accumulated vehicle information in continuous k images to improve reliability. Finally, obtained vehicle region becomes a template image to find same object in the next continuous image using SURF(Speeded Up Robust Features). The template image is updated in the every frame. In order to reduce SURF processing time, ROI(Region of Interesting) region is limited on expended area of detected vehicle location in the previous frame image. This algorithm repeats detection and tracking progress until no corresponding points are found. The experimental result shows efficiency of proposed algorithm using images obtained on the road.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.08a
• /
• pp.234-234
• /
• 2010

The PR transitions in asymmetric dot-in-double-quantum-well (DdWELL) photodetector is identified by bias-dependent spectral behaviors. Discrete n-i-n infrared photodetectors were fabricated on a 30-period asymmetric InAs-QD/[InGaAs/GaAs]/AlGaAs DdWELL wafer that was prepared by MBE technique. A 2.0-monolayer (ML) InAs QD ensemble was embedded in upper combined well of InGaAs/GaAs and each stack is separated by a 50-nm AlGaAs barrier. Each pixel has circular aperture of 300 um in diameter, and the mesa cell ($410{\times}410\;{\mu}m^2$) was defined by shallow etching. PR measurements were performed in the spectral range of $3{\sim}13\;{\mu}m$ (~ 100-400 meV) by using a Fourier-transform infrared (FTIR) spectrometer and a low-noise preamplifier. The asymmetric photodetector exhibits unique transition behaviors that near-/far-infrared (NIR/FIR) photoresponse (PR) bands are blue/red shifted by the electric field, contrasted to mid-infrared (MIR) with no dependence. In addition, the MIR-FIR dual-band spectra change into single-band feature by the polarity. A four-level energy band model is proposed for the transition scheme, and the field dependence of FIR bands numerically calculated by a simplified DdWELL structure is in good agreement with that of the PR spectra. The wavelength shift by the field strength and the spectral change by the polarity are discussed on the basis of four-level transition.