• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.711-718
• /
• 2022

In this paper, an accurate segmentation algorithm of video dynamic background image (VDBI) based on improved wavelet transform is proposed. Based on the smooth processing of VDBI, the traditional wavelet transform process is improved, and the two-layer decomposition of dynamic image is realized by using two-dimensional wavelet transform. On the basis of decomposition results and information enhancement processing, image features are detected, feature points are extracted, and quantum ant colony algorithm is adopted to complete accurate segmentation of the image. The maximum SNR of the output results of the proposed algorithm can reach 73.67 dB, the maximum time of the segmentation process is only 7 seconds, the segmentation accuracy shows a trend of decreasing first and then increasing, and the global maximum value can reach 97%, indicating that the proposed algorithm effectively achieves the design expectation.

• 대한인간공학회지
• /
• 제27권3호
• /
• pp.15-22
• /
• 2008

The purpose of this study was to define the effects of noise and background music on the trunk muscle fatigue during dynamic lifting and lowering tasks. Six healthy male subjects with no prior history of low back disorders participated in this study. The participants were exposed to two levels of background noise such as 40dB noise and 90dB noise and three levels of background music such as no music, slow music, and fast music. Six different combinations of background noise and background music were played while the participants were performing the lifting task at 15% level of Maximum Voluntary Contraction. Electromyography signals from six muscles were collected and fatigue levels were analyzed quantitatively. In results, the 90dB noise increased trunk muscle fatigue and slowed down the recovery. The trunk muscle fatigue was the lowest when the fast music was played for as background. After recovery, the 90dB noise increased trunk muscle fatigue. The trunk muscle fatigue was the lowest when the slow music was played for as background. The results can be useful to manage the cumulative fatigue of trunk muscles due to background noise and music during repetitive lifting and lowering tasks in industry.

• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권6호
• /
• pp.685-694
• /
• 2015

In this paper, a new dynamic reference scheme is proposed to improve the read voltage margin better than the previous static reference scheme. The proposed dynamic reference scheme can be helpful in compensating not only the background pattern dependence but also the cell position dependence. The proposed dynamic reference is verified by simulating the CMOS-memristor hybrid circuit using the practical CMOS SPICE and memristor Verilog-A models. In the simulation, the percentage read voltage margin is compared between the previous static reference scheme and the new dynamic reference scheme. Assuming that the critical percentage of read voltage margin is 5%, the memristor array size with the dynamic scheme can be larger by 60%, compared to the array size with the static one. In addition, for the array size of $64{\times}64$, the interconnect resistance in the array with the dynamic scheme can be increased by 30% than the static reference one. For the array size of $128{\times}128$, the interconnect resistance with the proposed scheme can be improved by 38% than the previous static one, allowing more margin on the variation of interconnect resistance.

• 한국지능시스템학회논문지
• /
• 제18권3호
• /
• pp.387-391
• /
• 2008

움직이는 객체를 검출하기 위해서 정확한 배경을 사용하기 위해 널리 사용되는 방법으로는 가우시안 혼합 모델이다. 가우시안 혼합 모델은 확률적 학습 방법을 사용하는데, 이 방법은 움직이는 배경일 경우와 이동하던 물체가 정지하는 경우 배경을 정확히 모델링하지 못한다. 본 논문에서는 확률적 모델링을 통해 혼잡한 배경을 모델링하고 객체의 계층적 처리를 통해 보다 정확한 배경으로 갱신할 수 있는 학습 방법을 제안한다.

• 대한임베디드공학회논문지
• /
• 제11권5호
• /
• 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.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권2호
• /
• pp.52-61
• /
• 2006

For the detection of moving objects, background subtraction methods are widely used. An adaptive Gaussian mixture model combined with probabilistic learning is one of the most popular methods for the real-time update of the complex and dynamic background. However, probabilistic learning approach does not work well in high traffic regions. In this paper, we Propose a reliable learning method of complex and dynamic backgrounds in high traffic regions.

• 전자공학회논문지CI
• /
• 제47권5호
• /
• pp.1-9
• /
• 2010

일반적으로 동적 손동작 인식을 위해서는 전처리, 손 추적, 손 모양 검출의 단계가 필요하다. 본 논문에서는 전처리와 손 모양 검출 방법을 개선함으로써 성능을 향상시킨 동적 손동작 인식 방법을 제안한다. 전처리 단계에서는 동적테이블을 이용하여 노이즈제거 성능을 높이고, YCbCr 컬러공간을 이용한 기존의 피부색 검출 방식에서 피부색의 범위를 조절할 수 있도록 하여 피부색 검출 성능을 높인다. 특히 손 모양 검출 단계에서는 가이드라인을 이용하여 동적 손동작 인식의 요소인 시작이미지(Start Image)와 정지 이미지(Stop Image)를 검출하여 동적 손동작을 인식하기 때문에 학습예제를 사용한 손동작 인식 방법에 비해 인식 속도가 빠르다는 이점이 있다. 가이드라인이란 웹캠을 통해 입력되는 손의 모양과 비교하여 검출하기 위해 화면에 출력하는 손 모양의 라인이다. 가이드라인을 이용한 동적 손동작 인식 방법의 성능을 평가하기 위해 웹캠을 사용하여 복잡한 배경과 단순한 배경으로 구분된 9가지 동영상을 대상으로 실험하였다. 그 결과 CPU 점유율이 낮고, 메모리 사용량도 적기 때문에 시스템 부하가 높은 환경에 효과적임을 알 수 있었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2011년도 춘계학술대회 논문집
• /
• pp.303-304
• /
• 2011

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (C)
• /
• pp.477-481
• /
• 2007

A background is a part where do not vary too much or frequently change in an image sequence. Using this assumption, it is presented a background acquisition algorithm for not only static but also dynamic view in this paper. For generating background, we detect a region, where has high correlation rate compared within selected region in the prior pyramid image, from the searching region in the current image. Between a detected region in the current image and a selected region in the prior image, we calculate movement vector for each regions in time sequence. After we calculate whole movement vectors for two successive images, vector histogram is used to determine the camera movement. The vector which has the highest density in the histogram is determined a camera movement. Using determined camera movement, we classify clusters based on pixel intensities which pixels are matched with prior pixels following camera movement. Finally we eliminate clusters which have lower weight than threshold, and combine remained clusters for each pixel to generate multiple background clusters. Experimental results show that we can automatically detect background whether camera move or not.