• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.11
• /
• pp.1645-1654
• /
• 1993

Unlike a noise removal recursive temporal filter, this paper presents a temporal filter which improves visual quality and data compression efficiency. In general, for the temporal band-limitation, temporal aliasing should be considered. Since most of a video signal has temporally aliased components, it is desirable to consider them. From a signal processing point of view, it is impossible to realize the filtering not afeced by the aliasings. However, in this paper, efficient filtering with de-aliasing characteristics is proposed. Considering the location of a video signal, temporal filtering can be accomplished by the spatial filtering along the motion vector trajectory (Motion Adaptive Spatial Filter). This filtered result dose not include the aliasings. Besides the efficient band-limitation, temporal noise is also reduced. For the evaluation of the MASF, its realization and filtering characteristics will be discussed in ditail.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.127-135
• /
• 2010

In motion adaptive temporal noise reduction filtering used for reducing video noises, the strength of motion adaptive temporal filtering should be carefully controlled according to temporal movement. This paper presents a motion adaptive temporal filtering scheme based on least-square training. Each pixel is classified to a specific class code according to temporal movement, and then, an iterative least-square training method is applied for each class code to find optimal filtering coefficients. The iterative least-square training is an off-line procedure, and the trained filter coefficients are stored in a lookup table (LUT). In actual noise reduction filtering operation, after each pixel is classified by temporal movement, simple filtering operation is applied with the filter coefficients stored in the LUT according to the class code. Experiment results show that the proposed method efficiently reduces video noises without introducing blurring.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.60-67
• /
• 1996

In this paper, we propose a new temporal interpolation method based on spatial filtering. Compared with the conventional method, the proposed one may use a few adjacent frames and apply temporal lowpass filtering. To develop this method, we follow the basic approach of sampling rate conversion. Additionally, we use some assumption of video sequence : moving object has constant velocity rigid translational motion. From them, spatial filtering for temporal sampling rate conversion is described. This method has a lot of noise immunity on a motion vector and doesn't make a great difference from the original frame. The interpolated frame shows moderate change even there is a great time difference. This method has exactly same description of motion adaptive spatial filter which has an efficient temporal band-limiting characteristics. It imposes the possibility to make video sequence with good pictural quality.

• ETRI Journal
• /
• v.28 no.4
• /
• pp.509-512
• /
• 2006

In a real environment, sound recordings are commonly distorted by channel and background noise, and the performance of audio identification is mainly degraded by them. Recently, Philips introduced a robust and efficient audio fingerprinting scheme applying a differential (high-pass filtering) to the frequency-time sequence of the perceptual filter-bank energies. In practice, however, the robustness of the audio fingerprinting scheme is still important in a real environment. In this letter, we introduce alternatives to the frequency-temporal filtering combination for an extension method of Philips' audio fingerprinting scheme to achieve robustness to channel and background noise under the conditions of a real situation. Our experimental results show that the proposed filtering combination improves noise robustness in audio identification.

• MALSORI
• /
• no.53
• /
• pp.93-102
• /
• 2005

The performance of a speech recognition system is generally degraded in telephone environment because of distortions caused by background noise and various channel characteristics. In this paper, data-driven temporal filters are investigated to improve the performance of a specific recognition task such as telephone speech. Three different temporal filtering methods are presented with recognition results for Korean connected-digit telephone speech. Filter coefficients are derived from the cepstral domain feature vectors using the principal component analysis. According to experimental results, the proposed temporal filtering method has shown slightly better performance than the previous ones.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.365-374
• /
• 2011

Recently, malicious video classification and filtering techniques are of practical interest as ones can easily access to malicious multimedia contents through the Internet, IPTV, online social network, and etc. Considerable research efforts have been made to developing malicious video classification and filtering systems. However, the malicious video classification and filtering is not still being from mature in terms of reliable classification/filtering performance. In particular, the most of conventional approaches have been limited to using only the spatial features (such as a ratio of skin regions and bag of visual words) for the purpose of malicious image classification. Hence, previous approaches have been restricted to achieving acceptable classification and filtering performance. In order to overcome the aforementioned limitation, we propose new malicious video classification framework that takes advantage of using both the spatial and temporal features that are readily extracted from a sequence of video frames. In particular, we develop the effective temporal features based on the motion periodicity feature and temporal correlation. In addition, to exploit the best data fusion approach aiming to combine the spatial and temporal features, the representative data fusion approaches are applied to the proposed framework. To demonstrate the effectiveness of our method, we collect 200 sexual intercourse videos and 200 non-sexual intercourse videos. Experimental results show that the proposed method increases 3.75% (from 92.25% to 96%) for classification of sexual intercourse video in terms of accuracy. Further, based on our experimental results, feature-level fusion approach (for fusing spatial and temporal features) is found to achieve the best classification accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.520-529
• /
• 2007

In this paper, we study the characteristics of parameters which are related to performance of MCTF which is a key technique for wavelet-based scalable video coding, and propose an improved MCTF method. The proposed MCTF method adopts the motion estimation of which motion vector field is distributed more uniformly using variable block sizes. By using the proposed method, the decomposition performance of temporal filter is improved, and the energy in high-frequency frames is reduced. It can help the entropy coder to generate lower bitrate. From simulation results, we verify the decomposed energy on high-frequency frame using the proposed method is reduced by 25.86% at the most in terms of variance of the high-frequency frame.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.764-767
• /
• 2004

The performance of a speech recognition system is generally degraded in telephone environment because of distortions caused by background noise and various channel characteristics. In this paper, data-driven temporal filters are investigated to improve the performance of a specific recognition task such as telephone speech. Three different temporal filtering methods are presented with recognition results for Korean connected-digit telephone speech. Filter coefficients are derived from the cepstral domain feature vectors using the principal component analysis.

• Journal of Broadcast Engineering
• /
• v.11 no.2 s.31
• /
• pp.153-163
• /
• 2006

We propose a new video compression method based on MCTF(motion compensated temporal filtering) with constant quality. SPECK is an efficient image compression coding method of encoding DWT coefficients. Especially SPECK method is very efficient for coding the motion compensated residual image which usually has larger amounts of high frequency components than the natural images. And proposed multi block size hierarchical motion estimation technique is more efficient than classical block matching algorithm with fixed block size both in estimation precision and operation costs. Proposed video method based on MCTF video compression can also support multi-frame rate decoding with reasonable complexity. Simulation results showed that proposed method outperforms H.263 video compression standard.

• The Journal of Korea Robotics Society
• /
• v.6 no.1
• /
• pp.18-26
• /
• 2011

This paper presents a method, Exposure Controlled Temporal Filtering (ECF), applied to visual motion tracking, that can cancel the temporal aliasing of periodic vibrations of cameras and fluctuations in illumination through the control of exposure time. We first present a theoretical analysis of the exposure induced image time integration process and how it samples sensor impingent light that is periodically fluctuating. Based on this analysis we develop a simple method to cancel high frequency vibrations that are temporally aliased onto sampled image sequences and thus to subsequent motion tracking measurements. Simulations and experiments using the 'Center of Gravity' and Normalized Cross-Correlation motion tracking methods were performed on a microscopic motion tracking system to validate the analytical predictions.