Browsing by Author "Chen, DY"

Now showing 1 - 9 of 9

Automatic video summary and description
(2000)
Lee, SY
;
Lee, ST
;
Chen, DY
;
資訊工程學系
;
Department of Computer Science
Multimedia technology has been applied to many kinds of applications and the amount of multimedia data is growing dramatically. Especially the usage of digital video data is very popular today. Thus, content-based indexing and retrieval in video is getting more important in the future. In this paper, we investigate an efficient and reasonable solution to describe video contents, and propose an automatic generation of the summary of video contents with as least manual interaction as possible. Based on the summary of video contents, we extract the key features of the summary to represent its content and produce the description of the video content in MPEG-7 format using XML. We illustrate our approach by developing a system that can support content-based browsing and querying on the WWW.
Motion activity based semantic video similarity retrieval
(2002)
Chen, DY
;
Lee, SY
;
Chen, HT
;
資訊工程學系
;
Department of Computer Science
Semantic feature extraction of video shots and fast video sequence matching are important and required for efficient retrieval in a large video database. In this paper, a novel mechanism of similarity retrieval is proposed. Similarity measure between video sequences considering the spatio-temporal variation through consecutive frames is presented. For bridging the semantic gap between low-level features and the rich meaning that users desire to capture, video shots are analyzed and characterized by the high-level feature of motion activity in compressed domain. The extracted features of motion activity are further described by the 2D-histogram that is sensitive to the spatio-temporal variation of moving objects. In order to reduce the dimensions of feature vector space in sequence matching, Discrete Cosine Transform (DCT) is exploited to map semantic features of consecutive frames to the frequency domain while retains the discriminatory information and preserves the Euclidean distance between feature vectors. Experiments are performed oil MPEG-7 testing videos, and the results of sequence matching show that a few DCT transformed coefficients are adequate and thus reveal the effectiveness of the proposed mechanism of video retrieval.
Motion-based semantic event detection for video content description in MPEG-7
(2001)
Chen, DY
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper, we proposed an automatic two-level approach to segment videos into abstracted shots that are semantically meaningful mainly based on inferred video events. In the first level, we detect scene changes in sports videos by using GOP-based approach that would assist to fast segment a video sequence into shots. In the second level, each of the shots generated from level-1 is analyzed by utilizing the information of camera operations and object motion that are computed directly from motion vectors of MPEG-2 video streams in compressed domain. Events in tennis videos are then infer-red from both object trajectories and applied specific domain knowledge. Video shots are further segmented based on detected video events and hence semantically meaningful video clips can be generated and can assist to annotate video shots, summarize video content, and generate descriptions and description schemes in MPEG-7 standard.(1).
Object based video similarity retrieval and its application to detecting anchorperson shots in news video
(2003)
Chen, HT
;
Chen, DY
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
Semantic feature extraction of video shots and fast video sequence matching are important and required for efficient retrieval in a large video database. In this paper, a novel mechanism of similarity retrieval is proposed Similarity measure between video sequences considering the spatio-temporal variation through consecutive frames is presented. For bridging the semantic gap between low-level features and the rich meaning that users desire to capture, video shots are analyzed and characterized by the high-level feature of motion activity in compressed domain. The extracted features of motion activity, are further described by the 2D-histogram that is sensitive to the spatio-temporal variation of moving objects. In order to reduce the dimensions of feature vector space in sequence matching, Discrete Cosine Transform (DCT) is exploited to map semantic features of consecutive frames to the frequency domain while retains the discriminatory, information and preserves the Euclidean distance between feature vectors. Experiments are performed on MPEG-7 testing video streams, and the results of sequence matching show that a few DCT transformed coefficients are adequate and thus reveal the effectiveness of the proposed mechanism of video retrieval.
Phase diagram of crystals of dusty plasma
(1997-10-01)
Lee, HC
;
Chen, DY
;
Rosenstein, B
;
電子物理學系
;
Department of Electrophysics
Dust particles effectively charged by plasma recently have been optically observed to exhibit crystalline phases not expected of Wigner or Yukawa crystals. Under varying conditions the crystal sometimes appears as deformed and oriented three-dimensional close-packed lattices of bcc, fcc, or hcp type, but mostly as a triangular array of vertical chains of particles. The unusual phases are shown to be caused by dipole-dipole interactions. The dipole moments are induced on the dust particles by gravity and by drag forces generated by ion stream. We describe in detail stable lattice structures and present the highly complex phase diagram of the dusty plasma. It turns out that in large parts of the phase diagram the stable phases indeed correspond to chains, but particles in neighboring chains belong to different sublattices. The stability of the lattices against excitations due to compression (i.e., aspect ratio variations) and vibration (i.e., phonons or charge density waves) is established.
Robust object detection using cascade filter in MPEG videos
(2003)
Ahmad, AMA
;
Chen, DY
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper we propose a novel approach for Motion Vector (MV) based object detection in MPEG-2 video streams. Rather than processing the extracted MV fields that are directly extracted from MPEG-2 video streams in the compressed domain, we perform MV smoothing, perform MV noise reduction, obtain more robust object information, and refine this information through a cascaded filter composed of a Gaussian filter and a median filter. As a result, the object detection algorithm is more capable of accurately detecting objects. We compare the performance of our proposed system with the popular and commonly used spatial filter processing techniques: median filter, mean filter, Gaussian filter, and no filter. Based on experimental results performed over the MPEG7 testing dataset and measuring performance using the standard recall and precision metrics, object detection using the cascade filter is remarkably superior to the alternative filtering techniques. In addition to these results, we describe a user system interface that we developed, where users can maintain the filter parameters interactively.
Robust video retrieval using temporal MVMB moments
(2005)
Chen, DY
;
Liao, HYM
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose motion pattern-based descriptor which exploits both spatial and temporal features to characterize video sequences in a semantics-based manner. The Discrete Cosine Transform (DCT) is applied to convert the high-level features from the time domain to the frequency domain. The energy concentration property of DCT allows us to use only a few DCT coefficients to precisely capture the variations of moving blobs. In comparison with the frequently used motion activity descriptors, the RLD and SAH of MPEG-7, the proposed descriptor yields 38% and 19% average gains over RLD and SAH, respectively.
Robust video sequence retrieval using a novel object-based T2D-histogram descriptor
(2005-04-01)
Chen, DY
;
Lee, SY
;
Liao, HYM
;
資訊工程學系
;
Department of Computer Science
Due to the tremendous growth in the number of digital videos, the development of video retrieval algorithms that can perform efficient and effective retrieval task is indispensable. In this paper, we propose a high-level motion activity descriptor, object-based transformed 2D-histogram (T2D-histogram), which exploits both spatial and temporal features to characterize video sequences in a semantics-based manner. The discrete cosine transform (DCT) is applied to convert the object-based 2D-histogram sequences from the time domain to the frequency domain. Using this transform, the original high-dimensional time domain features used to represent successive frames are significantly reduced to a set of low-dimensional features in frequency domain. The energy concentration property of DCT allows us to use only a few DCT coefficients to effectively capture the variations of moving objects. Having the efficient scheme for video representation, one can perform video retrieval in an accurate and efficient way. (c) 2004 Elsevier Inc. All rights reserved.
Robust video similarity retrieval using temporal MIMB moments
(2004)
Chen, DY
;
Lee, SY
;
資訊工程學系
;
Department of Computer Science
Due to the tremendous growth in the number of digital videos, the development of video retrieval algorithms that can perform efficient and effective retrieval task is indispensable. In this paper, we propose a high-level motion-pattern descriptor, temporal motion intensity of moving blobs (MIMB) moments, which exploits spatial and temporal features to characterize video sequences in a semantics-based manner. The Discrete Cosine Transform (DCT) is applied to convert the high-level features from the time domain to the frequency domain. The energy concentration property of DCT allows us to use only a few DCT coefficients to precisely capture the variations of moving blobs. Compared to the motion activity descriptors, RLD and SAH in MPEG-7, the proposed descriptor yield 41% and 20% average performance gains over RLD and SAH, respectively. Having the efficient scheme for video representation, one can perform video retrieval in an accurate and efficient way.