• Journal of Broadcast Engineering
• /
• v.4 no.2
• /
• pp.155-163
• /
• 1999

In this paper, we propose novel scene change detection and key frame selection techniques, which use two feature images, i.e., DC and edge images, extracted directly from MPEG compressed video. For fast edge image extraction. we suggest to utilize 5 lower AC coefficients of each DCT. Based on this scheme, we present another edge image extraction technique using AC prediction. Although the former is superior to the latter in terms of visual quality, both methods all can extract important edge features well. Simulation results indicate that scene changes such as cut. fades, and dissolves can be correctly detected by using the edge energy diagram obtained from edge images and histograms from DC images. In addition. we find that our edge images are comparable to those obtained in the spatial domain while keeping much lower computational cost. And based on HVS, a key frame of each scene can also be selected. In comparison with an existing method using optical flow. our scheme can select semantic key frames because we only use the above edge and DC images.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.92-97
• /
• 1998

For the efficient searching and browsing of digital video, it is essential to extract the internal structure of the video contents. As an example, a news video consists of several sections such as politics, economics, sports and others, and also each section consists of individual topics. With this information in hand, users can ore easily access the required video frames. This paper addresses the problem of automatic shot boundary detection and selection of representative frames (R-frames), which are the essential step in recognizing the internal structure of video contents. In the shot boundary detection, a new algorithm that have dual detectors which are designed specifically for the abrupt boundaries (cuts) and gradually changing bounaries respectively is proposed. Compared to the existing 미algorithms that mostly have tried to detect both types by a single mechanism, the proposed algorithm is proved to be more robust and accurate. Also in the problem of R-frame selection, simple mechanical approaches such as selecting one frame every other second have been adopted. However this approach often selects too many R-frames in static short, while drops important frames in dynamic shots. To improve the selection mechanism, a new R-frame selection algorithm that uses motion information extracted from pixel difference is proposed.

• Korean Journal of Optics and Photonics
• /
• v.27 no.4
• /
• pp.133-142
• /
• 2016

This paper presents the design and simulation of a three-dimensional pixel-by-pixel scanning light detection and ranging (LIDAR) system with a microelectromechanical system (MEMS) scanning mirror and direct sequence optical code division multiple access (DS-OCDMA) techniques. It measures a frame with $848{\times}480$ pixels at a refresh rate of 60 fps. The emitted laser pulse waves of each pixel are coded with DS-OCDMA techniques. The coded laser pulse waves include the pixel's position in the frame, and a checksum. The LIDAR emits the coded laser pulse waves periodically, without idle listening time to receive returning light at the receiver. The MEMS scanning mirror is used to deflect and steer the coded laser pulse waves to a specific target point. When all the pixels in a frame have been processed, the travel time is used by the pixel-by-pixel scanning LIDAR to generate point cloud data as the measured result.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.331-333
• /
• 2012

동영상 데이터에는 요약을 통하여 한눈에 알 수 있도록 하는 기술을 필요로 한다. 그 중 방송용 스트림(stream) 서비스의 경우 그 활용을 더욱 필요로 하고 있다. 여러 채널을 공유하는 TV에서는 각 채널이 무슨 방송을 하고 있는지 중요한 이슈가 된다. 이런 동영상 요약에서 키 프레임(key frame)을 찾는 기술이나 키 프레임과 거리가 먼 프레임을 찾아내는 기술이 필요하다. 이 논문에서는 키 프레임과 비 중요 프레임을 정의하고 그 프레임들을 검출하는 연구에 대하여 소개한다. 비 중요 프레임의 경우 칼라 히스토그램(color histogram)을 분석하여 실제 테스트 이미지들과의 차이점을 분석한다. 키 프레임의 경우 얼굴 검출(face detection)과 샷 변경 검출(shot change detection)의 기술을 이용하여 자동으로 추출하도록 하고 그 성능을 측정하도록 한다.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.55 no.1
• /
• pp.21-25
• /
• 2006

This paper describes the novel control techniques design of VSC(Voltage Sag Corrector) for the purpose of power line quality enhancement. A fast detecting technique of voltage sag is implemented through the detection of instantaneous value on synchronous rotating do-reference frame. The first order digital filter is added in the detection algorithm to protect the insensitive characteristics against the noise. The relationship between the total detection time and cut-off frequency of the filter is described. The size of the capacitor bank used as the energy storage element is designed from the point of view of input/output energy with circuit analysis. Finally, the validity of the proposed scheme is proven through the simulated results.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.959-962
• /
• 1998

In this paper, we propose an efficient vehicle detection and classification algorithm for an electronic toll collection, which is based on shadow robust vehicle presence test. In order to improve the performance of vehicle presence test, we use correlation coefficients between wavelet transformed input and reference images, which takes advanage of textural similarity. We compare the performance of the vehicle presence test with those of some conventional approaches that use variance of frame difference. Experimental results from field test show that the proposed vehicl detection and classification algorithm performs well even under abrupt intensity change due to the characteristics of sensor and occurrence of shadow.

• Phonetics and Speech Sciences
• /
• v.5 no.1
• /
• pp.11-16
• /
• 2013

This paper proposes robust feature extraction for accurate voice activity detection (VAD). VAD is one of the principal modules for speech signal processing such as speech codec, speech enhancement, and speech recognition. Noisy environments contain nonstationary noises causing the accuracy of the VAD to drastically decline because the fluctuation of features in the noise intervals results in increased false alarm rates. In this paper, in order to improve the VAD performance, harmonic-weighted energy is proposed. This feature extraction method focuses on voiced speech intervals and weighted harmonic-to-noise ratios to determine the amount of the harmonicity to frame energy. For performance evaluation, the receiver operating characteristic curves and equal error rate are measured.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.6
• /
• pp.1199-1203
• /
• 2012

This paper proposes a Scene Change Detection method using the local decision tree and clustering. The local decision tree detects cluster boundaries wherein local scenes occur, in such a way as to compare time similarity distributions among the difference values between detected scenes and their adjacent frames, and group an unbroken sequence of frames with similarities in difference value into a cluster unit.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1973-1979
• /
• 2000

Driving the need for machine vision system is growing consumer demand for quality and defect-free products. Especially it is the most important in tarpaulin's manufacturing process achieves automatically by machine vision instead of by man vision. In this paper pinholes detection is performed by using morphology algorithms. Top hat transform is one of morphology applications. This transform take high performance of defect detection in the case that unexpected changes occur in some non-uniform background. For pinholes defect, automatic visual inspection system has been developed, which was composed by a line-scan camera, illumination, a frame grabber, a motor driver and control units. This system has excellent capacity to defect pinholes to the 0.1 mm by 0.5 mm in size and to work in moving objects by maximum 20 m/min in speed.

• Journal of Biosystems Engineering
• /
• v.20 no.4
• /
• pp.368-375
• /
• 1995

A computer vision system was built to generate images of a stationary egg. This system includes a. CCD camera, a frame grabber, and an incandescent back lighting system An image processing algorithm was developed to accurately detect surface holes and surface cracks on eggs. With 20W of incandescent back light, the detection rate was shown to be the highest. The Sobel operator was found to be the best among various enhancing filters examined. The threshold value to distinguish between the crack and the translucent spots was found to be linear with the average gray level of a whole egg image. Those values of both gray level and area were used as criteria to detect holes in egg and those values of both area and roundness were used to detect cracks in egg. For a sample of 300 eggs, this system was able to correctly analyze an egg for the presence of a defect 97.5% of the time. On the average, it took 59.5 seconds to analyze an egg image and determine whether or not it was defected.