The Unmanned Aerial Vehicle (UAV) has become increasingly affordable in the market and has been reduced to smaller sizes, providing an entry level UAV for any beginner. For this paper we have utilized the GoPro action...
详细信息
ISBN:
(纸本)9781479972272
The Unmanned Aerial Vehicle (UAV) has become increasingly affordable in the market and has been reduced to smaller sizes, providing an entry level UAV for any beginner. For this paper we have utilized the GoPro action camera as the chosen camera, since DJI has an established gimbal for it and also the fact that the GoPro setup is considered the entry level, which is available to anyone and also produces good quality. Recent research collaboration has identified built heritage in Malaysia with a scope of being built after the nation's independence between 1957 and 1970. Three buildings from this category were shot with the UAV, the National Mosque, Tun Abdul Razak Apartments or famously known as the Pekeliling Flats, and the Rifle Range Flats in Penang. This research will present the utilization of UAV in documenting a built heritage, its challenges in operating the machine, and documenting the sites. This study also briefly describes how aerial videography can be beneficial for visualization artists. In addition to aerial capturing, one aspect of built heritage documentation deals with e-reconstruction including digital drawings, 3D modeling, virtual reality, etc. This can be achieved by using existing visual materials as a reference to generate a virtualized version of the building. In some points visualization artist needs full access to the building, as existing reference images are insufficient. But as mentioned above, sometimes access is limited to terms and conditions mostly related to safety. In this situation one of the best alternatives is to use UAV drones. Aerial videography can be beneficial for visualization artists, first as the reference, and secondly to be combined with virtualized materials for augmented reality purposes as the land where flats were located on, will be covered by newly built skyscrapers in the near future.
In this paper we describe music retrieval in ICOR (Intelligent content Retrieval), a project of Darmstadt TU. It is the goal of ICOR to find new interfaces to support applications of music video and music CDs. Althoug...
详细信息
ISBN:
(纸本)0819434396
In this paper we describe music retrieval in ICOR (Intelligent content Retrieval), a project of Darmstadt TU. It is the goal of ICOR to find new interfaces to support applications of music video and music CDs. Although the project consists of audio and video analysis we concentrate on a description of the audio algorithms in this paper. We describe our MPEG-7 like data structure to store meta information for music pieces and explain which algorithms we use to analyze the content of music pieces automatically. We currently use an applause detection to distinguish live music from studio recordings, a genre classifier to distinguish pieces with beats (for example disco music) from classical music, and a singer recognition.
Spatial audio becomes increasingly popular in domestic and mobile multimedia applications. Evaluating quality of experience (QoE) of such applications requires the development of algorithms capable of identification a...
详细信息
ISBN:
(纸本)9783319986784;9783319986777
Spatial audio becomes increasingly popular in domestic and mobile multimedia applications. Evaluating quality of experience (QoE) of such applications requires the development of algorithms capable of identification and quantification of perceptual characteristics of spatial audio scenes. This paper introduces a method for the automatic categorization of surround sound recordings using a criterion based on the distribution of foreground and background audio content around a listener. The principles of the method were demonstrated using a study in which a corpus of 110 five-channel surround sound recordings was computationally classified according to the two basic spatial audio scene categories. In order to develop the proposed method a novel metric, representing spatial audio characteristics, was identified. Moreover, five machine learning algorithms, including neural networks, random forests and support vector machines, were employed and their performance compared. According to the obtained results, the proposed method was capable of categorization of surround sound recordings reaching accuracy of 99%.
Future multimedia satellite will provide a multitude of services to end users ranging from narrow band to broad band (voice, video, internet access...). We consider here users sharing a common access carrier through t...
详细信息
Audible content has become an effective tool for shaping one's personality and character due to the ease of accessibility to a huge audible content that could be an independent audio files or an audio of online vi...
详细信息
Audible content has become an effective tool for shaping one's personality and character due to the ease of accessibility to a huge audible content that could be an independent audio files or an audio of online videos, movies, and television programs. There is a huge necessity to filter inappropriate audible content of the easily accessible videos and films that are likely to contain an inappropriate speech content. With this in view, all the broadcasting and online video/audio platform companies hire a lot of manpower to detect the foul voices prior to censorship. The process has a large cost in terms of manpower, time and financial resources. In addition to inaccurate detection of foul voices due to fatigue of manpower and weakness of human visual and hearing system in long time and monotonous tasks. As such, this paper proposes an intelligent deep learning-based system for film censorship through a fast and accurate detection and localization approach using advanced deep Convolutional Neural Networks (CNNs). The dataset of foul language containing isolated words samples and continuous speech were collected, annotated, processed, and analyzed for the development of automated detection of inappropriate speech content. The results indicated the feasibility of the suggested systems by reporting a high volume of inappropriate spoken terms detection. The proposed system outperformed state-of-the-art baseline algorithms on the novel foul language dataset evaluation metrics in terms of macro average AUC (93.85%), weighted average AUC (94.58%), and all other metrics such as F1-score. Additionally, proposed acoustic system outperformed ASR-based system for profanity detection based on the evaluation metrics including AUC, accuracy, precision, and F1-score. Additionally, proposed system was proven to be faster than human manual screening and detection of audible content for films' censorship.
作者:
KAHAN, JCCETT AMS/ARM
4 rue du Clos-Courtel BP 59 35512 Cesson-Sevigne Cedex France
Existing authorization schemes for the WWW present a client administration problem when hyperlinked documents and contents are stored in different servers. A new distributed authorization model is proposed where infor...
详细信息
Existing authorization schemes for the WWW present a client administration problem when hyperlinked documents and contents are stored in different servers. A new distributed authorization model is proposed where information servers are grouped into authorization domains. User administration is simplified as only one server in the domain needs to know its potential clients. Extensions to the model provide support document and content migration and implementation of user groups. A prototype of the model was implemented over an existing WWW system.
This paper presents our latest work oil identifying frame content types for understanding learning media content. In particular, we categorize frames into six classes namely, slide, web-page, instructor, audience, pic...
详细信息
ISBN:
(纸本)0780393317
This paper presents our latest work oil identifying frame content types for understanding learning media content. In particular, we categorize frames into six classes namely, slide, web-page, instructor, audience, picture-in-picture and miscellaneous, which make up salient narrative modes in learning videos. Various image and video analysis approaches are explored to achieve this task. Preliminary experiments carried out on three recorded seminars have yielded encouraging results. The identification of fine-grained visual content types can assist us in content understanding, access, browsing and searching of generic learning videos.
The distribution of multimedia files brings new challenges to the problem of replica placement in content distribution networks (CDN) and invalidates several assumptions underlying the existing solutions. In this pape...
详细信息
ISBN:
(纸本)0780378024
The distribution of multimedia files brings new challenges to the problem of replica placement in content distribution networks (CDN) and invalidates several assumptions underlying the existing solutions. In this paper we formulate a new model for the problem of replica placement to accommodate these new characteristics. We perform a theoretical analysis of the cost of distributing multimedia files over CDNs and find out that, contrary to the intuition, deploying as many replicas as possible is not always a good strategy. We then propose several replica placement algorithms that can determine the optimal number of replicas we should select from a given set of potential sites. By simulation we demonstrate that the performance of clients may degrade if we choose too many sites for replica placement.
Distributed multimedia Database systems (DMDB) have gained in popularity for today's database system design due to their fault-tolerance, resource-sharing capacity, and reliable performance. Reliability performanc...
详细信息
Distributed multimedia Database systems (DMDB) have gained in popularity for today's database system design due to their fault-tolerance, resource-sharing capacity, and reliable performance. Reliability performance is an important issue in DMDB design. The reliability of a DMDB depends on the reliability of its communication links and nodes as well as the distribution of its resources, such as various media. The distribution of media is an important factor that affect the multimedia query and access reliability (MQAR). The reliability-oriented media assignment problem is to find a media distribution such that the MQAR is maximal. In this paper, we attempt to develop a reliability model and algorithms to achieve reliability-oriented media allocation.
This paper is on the scope of the use of virtual learning environments in higher education institutions. The aim is to understand between the school year of 2009/2010 to 2013/2014 the use of a virtual learning environ...
详细信息
ISBN:
(纸本)9781479983308
This paper is on the scope of the use of virtual learning environments in higher education institutions. The aim is to understand between the school year of 2009/2010 to 2013/2014 the use of a virtual learning environment of a Portuguese higher education institution in terms of publishing of contents by teachers, the type of contents published, the students access to these contents as well as the exploration of relationships between published content and access to these contents. The data were obtained by document analysis, using databases to retrieve the records of publication of contents and access, during the study period. The contents published by teachers were integrated into categories: PDF, Text Documents, Spreadsheets, Presentations, Images, Compressed Files and multimedia. Most of the contents were published in PDF format.
暂无评论