Crowd Event Perception Based on Spatiotemporal Weber Field

الملخص EN

Over the past decade, a wide attention has been paid to the crowd control and management inintelligent video surveillance area.

Among the tasks of automatic video-based crowd management, crowdmotion modeling is recognized as one of the most critical components, since it lays a crucial foundationfor numerous subsequent analyses.

However, it still encounters many unsolved challenges due toocclusions among pedestrians, complicated motion patterns in crowded scenarios, and so forth.

Addressing theseissues, we propose a novel spatiotemporal Weber field, which integrates both appearance characteristicsand stimulus of crowd motion patterns, to recognize the large-scale crowd event.

On the one hand,crowd motion is recognized as variations of spatiotemporal signal, and we then measure the variationbased on Weber law.

The result is referred to as spatiotemporal Weber variation feature.

On the otherhand, motivated by the achievements in crowd dynamics that crowd motion has a close relationshipwith interaction force, we propose a spatiotemporal Weber force feature to exploit the stimulus ofcrowd behaviors.

Finally, we utilize the latent Dirichlet allocation model to establish the relationshipbetween crowd events and crowd motion patterns.

Experiments on PETS2009 and UMN databasesdemonstrate that our proposed method outperforms the previous methods for the large-scale crowdbehavior perception.