A method to provide automatic content-based video indexing from object motion is described. Moving objects in video from a surveillance camera 11 detected in the video sequence using motion segmentation methods by motion segmentor 21. Objects are tracked through segmented data in an object tracker 22. A symbolic representation of the video is generated in the form of an annotated graphics describing the objects and their movement. A motion analyzer 23 analyzes results of object tracking and annotates the graph motion with indices describing several events. The graph is then indexed using a rule based classification scheme to identify events of interest such as appearance/disappearance, deposit/removal, entrance/exit, and motion/rest of objects. Clips of the video identified by spatio-temporal, event, and object-based queries are recalled to view the desired video.

Motion based event detection system and method

Full motion digital video frames, or other indexed data structures, are annotated with text, graphics, and digital audio without modifications to the original video information. The video and annotations are stored separately. An indexing scheme relates the annotations to the video frames. On full motion video playback, the annotations are displayed on the originally annotated frames. The technique involves displaying the file of indexed data structures using a file display routine, and selecting in response to user input an indexed data structure to be annotated from the file of indexed data structures being displayed. Next, an annotation data structure is created in response to user input using an annotation routine without modifying the selected data structure. The annotation data structure includes a graphical element for display overlaying the selected data structure and an indication of an index value for the selected data structure. The annotation data structure is stored in an annotation memory apart from the file of indexed data structures. During playback, the annotation memory is monitored to detect annotation data structure for indexed data structures currently being displayed. If an annotation data structure is detected for the current indexed data structure, a graphical element overlies the indexed data structure on the display without modifying the indexed data structure. Text process documents can be handled much in the same manner. Also, annotation from several users may be merged and viewed in one batch.

Method and apparatus for annotating full motion video and other indexed data structures

Review of Image and Video Indexing Techniques

A Survey on the Automatic Indexing of Video Data

Multiple different versions of the same multimedia content are available to a multimedia server. An annotation server maintains annotations corresponding to the multimedia content, each such annotation corresponding to each of the different versions of the multimedia content.

Annotations for multiple versions of media content

With the progression of multimedia technology and the trend of visualization of man-machine interface, video data will become a kind of fundamental resource of data as general as text and graphics. When the data size is large, retrieving data will become a time-consuming process. Much research has been done to facilitate the retrieval of data, e.g., indexes in a database. Similarly, the video data also encounter the same problem. It is very difficult to generate video indexes automatically, because the index is application-dependent and only the user knows what indexes he actually needs. In this paper a mechanism for video data indexing is proposed which is based on the concept of objects and object motion with interactive annotation. This mechanisms provides an efficient method to access video substance without browsing the whole video data. A motion representation for the track of a moving object is presented. The access methods of video queries are introduced. A prototype of the video indexing system is implemented.

Suh-Yin Lee

Papers

Video indexing: an approach based on moving object and track