Guest
12-07-2012, 11:35 AM
Sir/Madam,
this project is to be implemented in either java or matlab. In normal content based video retrieval (CBVR)all features are independently stored in database and when a piece of video(clip of video) is provided to the system, system again collects features from that clip or piece of video and try to match it with stored feature. Videos those match with it are get retrieved. but in domain specific retrieval, we have to store only specific (e.g. all basketball videos ) in database, instead of storing their features independently, we will draw associations among videos and will use them to index video. for example for goal, first camera follows player i.e. it get panned horizontally, then get zoomed , then audience applause for goal. these sequences can give us one index for the video.
this kind of implementation reduces irrelevancy as in normal CBVR even one feature matches that video get retrieved, here we are not comparing features independently , instead association among events or features is forming index.
hereby i am attaching the corresponding abstract:
Abstract
Advances in the media and entertainment industries, including streaming audio and digital TV, present new challenges for managing and accessing large audio-visual collections. Current content management systems support retrieval using low-level features, such as motion, color, and texture. However, low-level features often have little meaning for naive users, who much prefer to identify content using high-level semantics or concepts. This creates a gap between systems and their users that must be bridged for these systems to be used effectively. To this end, in this paper, we first present a knowledge-based video indexing and content management framework for domain specific videos (using basketball video as an example). We will provide a solution to explore video knowledge by mining associations from video data. The explicit definitions and evaluation measures (e.g., temporal support and confidence) for video associations are proposed by integrating the distinct feature of video data. Our approach uses video processing techniques to find visual and audio cues (e.g., court field, camera motion activities, and applause), introduces multilevel sequential association mining to explore associations among the audio and visual cues, classifies the associations by assigning each of them with a class label, and uses their appearances in the video to construct video indices.
this project is to be implemented in either java or matlab. In normal content based video retrieval (CBVR)all features are independently stored in database and when a piece of video(clip of video) is provided to the system, system again collects features from that clip or piece of video and try to match it with stored feature. Videos those match with it are get retrieved. but in domain specific retrieval, we have to store only specific (e.g. all basketball videos ) in database, instead of storing their features independently, we will draw associations among videos and will use them to index video. for example for goal, first camera follows player i.e. it get panned horizontally, then get zoomed , then audience applause for goal. these sequences can give us one index for the video.
this kind of implementation reduces irrelevancy as in normal CBVR even one feature matches that video get retrieved, here we are not comparing features independently , instead association among events or features is forming index.
hereby i am attaching the corresponding abstract:
Abstract
Advances in the media and entertainment industries, including streaming audio and digital TV, present new challenges for managing and accessing large audio-visual collections. Current content management systems support retrieval using low-level features, such as motion, color, and texture. However, low-level features often have little meaning for naive users, who much prefer to identify content using high-level semantics or concepts. This creates a gap between systems and their users that must be bridged for these systems to be used effectively. To this end, in this paper, we first present a knowledge-based video indexing and content management framework for domain specific videos (using basketball video as an example). We will provide a solution to explore video knowledge by mining associations from video data. The explicit definitions and evaluation measures (e.g., temporal support and confidence) for video associations are proposed by integrating the distinct feature of video data. Our approach uses video processing techniques to find visual and audio cues (e.g., court field, camera motion activities, and applause), introduces multilevel sequential association mining to explore associations among the audio and visual cues, classifies the associations by assigning each of them with a class label, and uses their appearances in the video to construct video indices.