MPEG-7 description of generic video objects for scene reconstruction

Abstract

We present an MPEG-7 compliant description of generic video sequences aiming at their scalable transmission and reconstruction. The proposed method allows efficient and flexible video coding while keeping the advantages of textual descriptions in database applications. Visual objects are described in terms of their shape, color, texture and motion; these features can be extracted automatically and are sufficient in a wide range of applications. To permit partial sequence reconstruction, at least one simple qualitative as well as a quantitative descriptor is provided for each feature. In addition, we propose a structure for the organization of the descriptors into objects and scenes and some possible applications for our method. Experimental results obtained with news and video surveillance sequences validate our method and highlight its main features.

Semantic segmentation and description for video transcoding

“…Semantic segmentation is used in methods (4) and (5) that still use a frame-based coder (MPEG-1). Semantic segmentation and an object-based coder (MPEG-4) are employed for methods (6) and (7). Finally, the combination of a JPEG2000 encoded background and MPEG-7 BiM encoded descriptors are used in the methods (8) to (10).…”

“…In our specific implementation we use an object identifier and a shape descriptor [6]. The object identifier is a unique numerical identifier for each object in the scene (Fig.…”

Semantic video analysis for adaptive content delivery and automatic description

“…Moreover, the descriptors can be transmitted instead of the video content itself and superimposed by the terminal on a still background. For example, an object identifier and a shape descriptor are used in [21]. The object identifier is a unique numerical identifier describing the spatial location of each object in the scene.…”