C.C. Jay Kuo - Böcker

This work is an overview of audio and video content analysis. Included is extensive treatment of audiovisual data segmentation, indexing and retrieval based on multimodal media content analysis, and content-based management of audio data. In addition to the commonly studied audio types such as speech and music, the authors have included hybrid types of sounds that contain more than one kind of audio component such as speech or environmental sound with music in the background. Emphasis is also placed on semantic-level identification and classification of environmental sounds. The authors introduce a new generic audio retrieval system on top of the audio archiving schemes. Both theoretical analysis and implementation issues are presented. The developing MPEG-7 standards are explored. This volume should be especially useful to researchers and graduate level students designing and developing fully functional audiovisual systems for audio/video content parsing of multimedia streams.

With the fast growth ofmultimedia information, content-based video anal- ysis, indexing and representation have attracted increasing attention in re- cent years. Many applications have emerged in these areas such as video- on-demand, distributed multimedia systems, digital video libraries, distance learning/education, entertainment, surveillance and geographical information systems. The need for content-based video indexing and retrieval was also rec- ognized by ISOIMPEG, and a new international standard called "Multimedia Content Description Interface" (or in short, MPEG-7)was initialized in 1998 and finalized in September 2001. In this context, a systematic and thorough review ofexisting approaches as well as the state-of-the-art techniques in video content analysis, indexing and representation areas are investigated and studied in this book. In addition, we will specifically elaborate on a system which analyzes, indexes and abstracts movie contents based on the integration ofmultiple media modalities. Content ofeach part ofthis book is briefly previewed below.In the first part, we segment a video sequence into a set ofcascaded shots, where a shot consistsofone or more continuouslyrecorded image frames. Both raw and compressedvideo data will beinvestigated. Moreover, consideringthat there are always non-story units in real TV programs such as commercials, a novel commercial break detection/extraction scheme is developed which ex- ploits both audio and visual cues to achieve robust results. Specifically, we first employ visual cues such as the video data statistics, the camera cut fre- quency, and the existenceofdelimiting black frames between commercials and programs, to obtain coarse-level detection results.

This work presents a review of the state-of-the-art techniques for maintaining QoS support for multimedia services over wireless networks. Several novel ideas and algorithms on integrated connection- and packet-level QoS, dynamic radio resource management, and multimedia QoS-aware services are described. Special emphasis is given to the following: mathematical models for analysing connection-level and packet-level QoS; radio resource management schemes for TDMA and CDMA systems; QoS-aware call admission control and seamless handoff schemes; dynamic call admission control for CBR and VBR traffic; and Markov decision process and linear programming techniques for optimal call admission control policy design. The book should be of interest to research scientists and graduate students working in the areas of wireless networks and QoS issues for multimedia traffic and related areas.

Content-Based Audio Classification and Retrieval for Audiovisual Data Parsing is an up-to-date overview of audio and video content analysis. Included is extensive treatment of audiovisual data segmentation, indexing and retrieval based on multimodal media content analysis, and content-based management of audio data. In addition to the commonly studied audio types such as speech and music, the authors have included hybrid types of sounds that contain more than one kind of audio component such as speech or environmental sound with music in the background. Emphasis is also placed on semantic-level identification and classification of environmental sounds. The authors introduce a new generic audio retrieval system on top of the audio archiving schemes. Both theoretical analysis and implementation issues are presented. The developing MPEG-7 standards are explored. Content-Based Audio Classification and Retrieval for Audiovisual Data Parsing will be especially useful to researchers and graduate level students designing and developing fully functional audiovisual systems for audio/video content parsing of multimedia streams.

With the fast growth ofmultimedia information, content-based video anal- ysis, indexing and representation have attracted increasing attention in re- cent years. Many applications have emerged in these areas such as video- on-demand, distributed multimedia systems, digital video libraries, distance learning/education, entertainment, surveillance and geographical information systems. The need for content-based video indexing and retrieval was also rec- ognized by ISOIMPEG, and a new international standard called "Multimedia Content Description Interface" (or in short, MPEG-7)was initialized in 1998 and finalized in September 2001. In this context, a systematic and thorough review ofexisting approaches as well as the state-of-the-art techniques in video content analysis, indexing and representation areas are investigated and studied in this book. In addition, we will specifically elaborate on a system which analyzes, indexes and abstracts movie contents based on the integration ofmultiple media modalities. Content ofeach part ofthis book is briefly previewed below.In the first part, we segment a video sequence into a set ofcascaded shots, where a shot consistsofone or more continuouslyrecorded image frames. Both raw and compressedvideo data will beinvestigated. Moreover, consideringthat there are always non-story units in real TV programs such as commercials, a novel commercial break detection/extraction scheme is developed which ex- ploits both audio and visual cues to achieve robust results. Specifically, we first employ visual cues such as the video data statistics, the camera cut fre- quency, and the existenceofdelimiting black frames between commercials and programs, to obtain coarse-level detection results.

Due to the great success and enormous impact of IP networks, In­ ternet access (such as sending and receiving e-mails) and web brows­ ing have become the ruling paradigm for next generation wireless systems. On the other hand, great technological and commercial success of services and applications is being witnessed in mobile wire­ less communications with examples of cellular, pes voice telephony and wireless LANs. The service paradigm has thus shifted from the conventional voice service to seamlessly integrated high quality mul­ timedia transmission over broadband wireless mobile networks. The multimedia content may include data, voice, audio, image, video and so on. With availability of more powerful portable devices, such as PDA, portable computer and cellular phone, coupled with the easier access to the core network (using a mobile device), the number of mobile users and the demand for multimedia-based applications is increasing rapidly. As a result, there is an urgent need for a sys­ tem that supports heterogeneous multimedia services and provides seamless access to the desired resources via wireless connections. Therefore, the convergence of multimedia communication and wireless mobile networking technologies into the next generation wireless multimedia (WMM) networks with the vision of "anytime, anywhere, anyform" information system is the certain trend in the foreseeable future. However, successful combination of these two technologies presents many challenges such as available spectral bandwidth, energy efficiency, seamless end-to-end communication, robustness, security, etc.