Method and system for metadata extraction from master-slave cameras tracking system

摘要

An embodiment of the present invention includes a master camera that may record master metadata regarding an object of interest and communicate the master metadata to a slave camera. The slave camera may zoom, pan, or tilt to isolate and record more detailed image data regarding the object of interest based on the master metadata. In addition, the slave camera may record slave metadata regarding the object of interest. The master and slave metadata may be stored associated with the recorded image data enabling a later search for the object of interest to be expedited. The recorded image data including the object of interest may be identified with greater ease as it may be guided by the master or slave metadata, or a combination thereof. According to embodiments presented herein, processing time for searching and identifying an object of interest may be reduced by enabling a search on the metadata associated with image data, rather than by searching the image data itself.

主权项

1. A method of enabling retrieval of information from a video surveillance system, the method comprising:
automatically identifying an object of interest in a video scene of a master camera or a slave camera; automatically classifying at least one feature of the object of interest to produce master and slave metadata, the object of interest for the slave camera being determined as a function of the master metadata; tracking the object of interest by adjusting the slave camera's field of view based on object information included in the master metadata, wherein adjusting the slave camera's field of view is further based on processing the video scene at the slave camera based on the master metadata; and storing the master and slave metadata in association with video of at least the slave camera in a manner that enables retrieval, of information about the object of interest, through use of the master or slave metadata, wherein the slave metadata includes detailed object information extracted from the video scene by the slave camera.