• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1289-1301
• /
• 2015

Pedestrian detection (PD) is an essential task in various applications and sliding window-based methods utilizing HOG (Histogram of Oriented Gradients) or HOG-like descriptors have been shown to be very effective for accurate PD. However, due to exhaustive search across images, PD methods based on sliding window usually require heavy computational time. In this paper, we propose a real-time PD method for embedded visual surveillance with fixed backgrounds. The proposed PD method employs HOG descriptors as many PD methods does, but utilizes selective search so that it can save processing time significantly. The proposed selective search is guided by restricting searching to candidate regions extracted from Adaptive Gaussian Mixture Model (AGMM)-based background subtraction technique. Moreover, approximate computation of HOG descriptor and implementation in fixed-point arithmetic mode contributes to reduction of processing time further. Possible accuracy degradation due to approximate computation is compensated by applying an appropriate one among three offline trained SVM classifiers according to sizes of candidate regions. The experimental results show that the proposed PD method significantly improves processing speed without noticeable accuracy degradation compared to the original HOG-based PD and HOG with cascade SVM so that it is a suitable real-time PD implementation for embedded surveillance systems.

• Journal of Industrial Technology
• /
• v.38 no.1
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.277-285
• /
• 2016

Moving object detection system has been an emerging research field in various advanced driver assistance systems (ADAS) and surveillance system. In this paper, we propose two optical flow based moving object detection methods at dynamic scenes. Both proposed methods consist of three successive steps; pre-processing, foreground segmentation, and post-processing steps. Two proposed methods have the same pre-processing and post-processing steps, but different foreground segmentation step. Pre-processing calculates mainly optical flow map of which each pixel has the amplitude of motion vector. Dense optical flows are estimated by using Farneback technique, and the amplitude of the motion normalized into the range from 0 to 255 is assigned to each pixel of optical flow map. In the foreground segmentation step, moving object and background are classified by using the optical flow map. Here, we proposed two algorithms. One is Gaussian mixture model (GMM) based background subtraction, which is applied on optical map. Another is adaptive thresholding based foreground segmentation, which classifies each pixel into object and background by updating threshold value column by column. Through the simulations, we show that both optical flow based methods can achieve good enough object detection performances in dynamic scenes.

• Korean Journal of Optics and Photonics
• /
• v.15 no.4
• /
• pp.343-348
• /
• 2004

We report the design and basic operating characteristics of an radio frequency excited waveguide $CO_2$ laser. Four picecs of waveguide channels are placed in one laser cavity to increase a power per unit length with the form of a 2 ${\times}$ 2 matrix. Four independent optical outputs are measured from the front of output coupler, and these beams are combined to a Gaussian mode beam far from the output coupler. A 12 W output power has been obtained with $CO_2$ : $N_2$ : He : Xe = 1 : 1 : 3 : 0.2 of the gas mixture and 200 W of radio frequency.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.1
• /
• pp.29-40
• /
• 2012

A challenging research issue that has been one of growing importance to those working in human-computer interaction are to endow a machine with an emotional intelligence. Thus, emotion recognition technology plays an important role in the research area of human-computer interaction, and it allows a more natural and more human-like communication between human and computer. In this paper, we propose the multimodal emotion recognition system using face and speech to improve recognition performance. The distance measurement of the face-based emotion recognition is calculated by 2D-PCA of MCS-LBP image and nearest neighbor classifier, and also the likelihood measurement is obtained by Gaussian mixture model algorithm based on pitch and mel-frequency cepstral coefficient features in speech-based emotion recognition. The individual matching scores obtained from face and speech are combined using a weighted-summation operation, and the fused-score is utilized to classify the human emotion. Through experimental results, the proposed method exhibits improved recognition accuracy of about 11.25% to 19.75% when compared to the most uni-modal approach. From these results, we confirmed that the proposed approach achieved a significant performance improvement and the proposed method was very effective.

• Journal of Communications and Networks
• /
• v.9 no.3
• /
• pp.219-228
• /
• 2007

In this paper, we present a novel blind adaptive multiuser detector structure and three robust recursive filters to improve the performance in CDMA environments: Sigma point kalman filter (SPKF), particle filter (PF), and Gaussian mixture sigma point particle filter (GMSPPF). Our proposed robust recursive filters have superior performance over a conventional extended Kalman filter (EKF). The proposed multiuser detector algorithms initially use Kalman prediction form to estimated channel parameters, and unknown data symbol be predicted. Second, based on this predicted data symbol, the robust recursive filters (e.g., GMSPPF) is a refined estimation of joint multipaths and time delays. With these estimated multipaths and time delays, data symbol detection is carried out (Kalman correction form). Computer simulations show that the proposed algorithms outperform the conventional blind multiuser detector with the EKF. Also we can see it provides a more viable means for tracking time-varying amplitudes and time delays in CDMA communication systems, compared to that of the EKF for near-far ratio of 20 dB. For this reason, it is believed that the proposed channel estimators can replace well-known filter such as the EKF.

• The Korean Journal of Applied Statistics
• /
• v.33 no.6
• /
• pp.665-682
• /
• 2020

This paper introduces numba library in Python, which improves computational efficiency of the provided implemented code written by naive Python language by applying just-in-time (JIT) compilation. To apply just-in-time compilation, the numba only needs to use a decorator on a target Python function. We provide implementation examples with numba for the permutation test and the parameter estimation for Gaussian mixture distribution. We also numerically show the efficiency of numba by comparing the total computation times of the implementation using naive python and the implementation using numba for each application.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.273-276
• /
• 2021

본 논문에서는 사용자의 관심영역(Region of interests, ROI)를 기반 스크롤을 통해 데이터를 좀 더 빠르고 효율적으로 검색할 수 있는 사용자-데이터 인터페이스를 제안한다. 사용자가 관심있는 정보나 콘텐츠를 찾는 행동에서 착안한 우리의 접근 방식은 주어진 콘텐츠에서 ROI를 효율적으로 계산하고, GMM(Gaussian mixture model, 가우시안 혼합 모델)에서 착안해 개발한 커널을 기반으로 사용자가 관심 있어 하는 정보의 위치로 부드럽고 빠르게 화면을 이동시켜 정보를 탐색한다. 과정을 설명하기 앞서, 다수의 ROI가 있을 때 스크롤의 현 위치는 항상 두 ROI의 사이에 있다. 그 두 사이의 거리가 가장 짧은 두 ROI에 각각 우리의 커널을 적용하면 현 위치에서 스크롤 가속에 적용 가능한 두 개의 관성이 생긴다. 여기에 선형 보간법(Linear interpolation)을 적용하여 한층 부드러운 하나의 관성으로 만들고, 이것을 스크롤에 적용한다. 결과적으로, 오직 사용자의 입력에 따라 정보가 검색되는 기존의 접근법과는 달리, ROI와 DOI(Degree of interests, 중요도)를 기반으로 향상된 스크롤을 통해 사용자가 관심 있어 하는 정보나 콘텐츠를 보다 쉽게 직관적으로 찾아줄 수 있기 때문에 사용자는 탐색 시간을 절약할 수 있다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.485-492
• /
• 2017

GMM has been one of the most popular methods for scream sound detection. In the conventional GMM, the whole training data is divided into scream sound and non-scream sound, and the GMM is trained for each of them in the training process. Motivated by the idea that the process of scream sound detection is very similar to that of speaker recognition, the UBM which has been used quite successfully in speaker recognition, is proposed for use in scream sound detection in this study. We could find that UBM shows better performance than the traditional GMM from the experimental results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.1
• /
• pp.21-26
• /
• 2015

In this paper, we propose a system which can detect the smoke in real time from the high-quality IP camera. For real-time processing, open directly the RTSP streams transmitted from the IP camera using the library FFmpeg as opening a video file. To recognize smoke, color information and morphological characteristics of smoke, as well as the dynamic characteristics of the smoke also considered for candidate regions. To combine the characteristics of the various smoke effectively, the Adaboost algorithm, was used as the boosting algorithm finally. Through the experiments with input videos from IP camera, the proposed algorithms were useful to detect smokes.