The Petri net model has good description and detection capabilities for complex time-series events. This paper proposes an automatic recognition method for surveillance video event information based on Petri net description and reasoning. The spatial relationship between moving targets and their features is represented by the Petri net library, and the temporal relationship and other reasoning rules are represented by transitions. Combined with the moving target features and basic event information obtained by low-level computer vision algorithms, the interactive query of complex semantic events in surveillance videos is realized through Petri net reasoning and execution. The effectiveness of this method is verified by experiments.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore