Detecting Events in Surveillance Videos
Mapping Low-level Analysis Data to High-level Scene Descriptions
Versandkostenfrei!
Versandfertig in 6-10 Tagen
32,99 €
inkl. MwSt.
PAYBACK Punkte
16 °P sammeln!
Along with the growing need for security, an increasing amount of surveillance content is created. It is indispensable to index the content in advance in order to enable quick and reliable searches on the output of hundreds or thousands of surveillance sensors installed at a single facility. The generation of this meta data has to be done automatically, based on the low-level features extracted by content analysis algorithms. Creating it manually becomes more and more difficult to handle in reasonable time at reasonable costs. Whereas formerly proposed approaches have been strongly application...
Along with the growing need for security, an increasing amount of surveillance content is created. It is indispensable to index the content in advance in order to enable quick and reliable searches on the output of hundreds or thousands of surveillance sensors installed at a single facility. The generation of this meta data has to be done automatically, based on the low-level features extracted by content analysis algorithms. Creating it manually becomes more and more difficult to handle in reasonable time at reasonable costs. Whereas formerly proposed approaches have been strongly application dependent, this work presents a generic concept for mapping the results of the low-level content analysis data to semantic event descriptions and its application. The main contribution of the presented approach are its generality and the early stage at which the step from low-level to high-level representation is taken. This reasoning in the meta data domain is performed on small time frames while the reasoning on complexer scenes is done in the semantic space. Even an unsupervised self-assessment is possible using the semantic approach.
Andere Kunden interessierten sich für
