• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.1
• /
• pp.426-445
• /
• 2012

Conventional rate control (RC) schemes for H.264 video coding usually regulate output bit rate to match channel bandwidth by adjusting quantization parameter (QP) at fixed full frame rate, and the passive frame skipping to avoid buffer overflow usually occurs when scene changes or high motions exist in video sequences especially at low bit rate, which degrades spatial-temporal quality and causes jerky effect. In this paper, an active content adaptive frame skipping scheme is proposed instead of passive methods, which skips subjectively trivial frames by structural similarity (SSIM) measurement between the original frame and the interpolated frame via motion vector (MV) copy scheme. The saved bits from skipped frames are allocated to coded key ones to enhance their spatial quality, and the skipped frames are well recovered based on MV copy scheme from adjacent key ones at the decoder side to maintain constant frame rate. Experimental results show that the proposed active SSIM-based frameskip scheme acquires better and more consistent spatial-temporal quality both in objective (PSNR) and subjective (SSIM) sense with low complexity compared to classic fixed frame rate control method JVT-G012 and prior objective metric based frameskip method.

• Journal of Korea Multimedia Society
• /
• v.17 no.8
• /
• pp.923-936
• /
• 2014

Images can be contaminated with different types of noise, for different reasons. The neighborhood averaging and smoothing by image averaging are the classical image processing techniques for noise removal. The classical spatial filtering refers to the aggregate of pixels composing an image and operating directly on these pixels. To reduce or remove effectively noise in image sequences, it usually needs to use noise reduction filter based on space or time domain such as method of spatial or temporal filter. However, the method of spatial filter can generally cause that signals of objects as the target are also blurred. In this paper, we propose temporal filter using the piece-wise quadratic function model and enhancement algorithm of image quality for the performance improvement of target detection and tracking by heterogeneous noise reduction. Image tracking simulation that utilizes real IIR(Imaging Infra-Red) images is employed to evaluate the performance of the proposed image processing algorithm.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.217-220
• /
• 2001

In this paper, we propose a segmentation method of moving object using the spatio-temporal information in image sequences. Proposed method consists of motion detection step using difference image, region segmentation step using k-means algorithm, motion estimation step and segmenting step using intensity and motion information. Experimental results show that the method is capable of segmenting variously moving objects in image sequences.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.5
• /
• pp.449-457
• /
• 2011

As automated image processing techniques have been required in multi-temporal/multi-sensor geospatial image applications, use of automated but highly invariant image matching technique has been a critical ingredient. Note that there is high possibility of geometric and spectral differences between multi-temporal/multi-sensor geospatial images due to differences in sensor, acquisition geometry, season, and weather, etc. Among many image matching techniques, the SIFT (Scale Invariant Feature Transform) is a popular method since it has been recognized to be very robust to diverse imaging conditions. Therefore, the SIFT has high potential for the geospatial image processing. This paper presents a performance test results of the SIFT on geospatial imagery by simulating various image differences such as shear, scale, rotation, intensity, noise, and spectral differences. Since a geospatial image application often requires a number of good matching points over the images, the number of matching points was analyzed with its matching positional accuracy. The test results show that the SIFT is highly invariant but could not overcome significant image differences. In addition, it guarantees no outlier-free matching such that it is highly recommended to use outlier removal techniques such as RANSAC (RANdom SAmple Consensus).

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1534-1542
• /
• 2004

A novel vision-based scheme of extracting real-time traffic information parameters is presented. The method is based on a region classification followed by a spatio-temporal image analysis. The detection region images for each traffic lane are classified into one of the three categories: the road, the vehicle, and the shadow, using statistical and structural features. Misclassification in a frame is corrected by using temporally correlated features of vehicles in the spatio-temporal image. Since only local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized without using dedicated parallel processors, while ensuring detection performance robust to the variation of weather conditions, shadows, and traffic load.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1661-1664
• /
• 2000

내용 기반의 비디오 검색에 있어 텍스처는 중요한 변수로 사용될 수 있다. 모든 물체의 표면은 독특한 성질을 보유하고 있으므로, 텍스처는 형상이나 색과 더불어 중요한 변수로 사용될 수 있다. 어떤 영상의 특징을 올바르게 추출하고 잘 분류하여 표현하는 것은 비디오 검색에 있어서 매우 중요하다. Temporal texture는 무한한 시공간적 범위의 복잡하고, 추상적인 움직임 패턴이며 자연 세계에 흔히 나타난다. 그러므로 이를 특징화시킬 수 있고, temporal texture 패턴을 얼마나 잘 이용할 수 있느냐는 비디오 검색의 성능에 많은 영향을 끼칠 수 있다. 본 논문은 temporal texture 모델링들 중 서로 다른 특징을 가진 세 가지의 모델을 선정하여 비교, 분석한다. 특히, 특징 추출의 분류가 정확하게 이루어지느냐에 초점을 맞추어서 분석하였다. 분류의 성능은 두 가지 변수 즉, 어떤 성질의 모델이며 비디오 데이터인가에 따라 달라지게 된다. 이들 모델링이 분류하기까지 걸리는 시간의 차이는 무시할 수 있을 정도의 시간차이므로, 정확도를 위주로 성능을 분석했다.

• ETRI Journal
• /
• v.31 no.1
• /
• pp.1-9
• /
• 2009

Frequency domain analysis is a fundamental procedure for understanding the characteristics of visual data. Several studies have been conducted with 2D videos, but analysis of stereoscopic 3D videos is rarely carried out. In this paper, we derive the Fourier transform of a simplified 3D video signal and analyze how a 3D video is influenced by disparity and motion in terms of temporal aliasing. It is already known that object motion affects temporal frequency characteristics of a time-varying image sequence. In our analysis, we show that a 3D video is influenced not only by motion but also by disparity. Based on this conclusion, we present a temporal anti-aliasing filter for a 3D video. Since the human process of depth perception mainly determines the quality of a reproduced 3D image, 2D image processing techniques are not directly applicable to 3D images. The analysis presented in this paper will be useful for reducing undesirable visual artifacts in 3D video as well as for assisting the development of relevant technologies.

• Korean Journal of Remote Sensing
• /
• v.18 no.1
• /
• pp.13-23
• /
• 2002

A radiometric correction method is developed to apply multi-temporal KOMPSAT-1 EOC satellite images for the detection of land-cover changes b\ulcorner recognizing changes in reflection pattern. Radiometric correction was carried out to eliminate the atmospheric effects that could interfere with the image properly of the satellite data acquired at different multi-times. Four invariant features of water, sand, paved road, and roofs of building are selected and a linear regression relationship among the control set images is used as a correction scheme. It is found that the utilization of panchromatic multi-temporal imagery requires the radiometric scene standardization process to correct radiometric errors that include atmospheric effects and digital image processing errors. Land-cover with specific change pattern such as paddy field is extracted by seasonal change recognition process.

• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.399-409
• /
• 2019

Three-dimensional (3D) human pose reconstruction from single-view image is a difficult and challenging topic. Existing approaches mostly process frame-by-frame independently while inter-frames are highly correlated in a sequence. In contrast, we introduce a novel spatial-temporal 3D human pose reconstruction framework that leverages both intra and inter-frame relationships in consecutive 2D pose sequences. Orthogonal matching pursuit (OMP) algorithm, pre-trained pose-angle limits and temporal models have been implemented. Several quantitative comparisons between our proposed framework and recent works have been studied on CMU motion capture dataset and Vietnamese traditional dance sequences. Our framework outperforms others by 10% lower of Euclidean reconstruction error and more robust against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are more natural and smoother than others.