Collective behavior recognition using compact descriptors
This work addresses the problem of recognizing collective behaviors in surveillance or social analysis, but it is incremental as it builds on existing trajectory-based methods with new descriptors.
The paper tackles collective behavior recognition from pedestrian trajectories by introducing a hierarchical classifier with novel Personal Interaction and Collective Behavior Descriptors, achieving results on par with state-of-the-art techniques and better class error balance while generalizing across camera setups.
This paper presents a novel hierarchical approach for collective behavior recognition based solely on ground-plane trajectories. In the first layer of our classifier, we introduce a novel feature called Personal Interaction Descriptor (PID), which combines the spatial distribution of a pair of pedestrians within a temporal window with a pyramidal representation of the relative speed to detect pairwise interactions. These interactions are then combined with higher level features related to the mean speed and shape formed by the pedestrians in the scene, generating a Collective Behavior Descriptor (CBD) that is used to identify collective behaviors in a second stage. In both layers, Random Forests were used as classifiers, since they allow features of different natures to be combined seamlessly. Our experimental results indicate that the proposed method achieves results on par with state of the art techniques with a better balance of class errors. Moreover, we show that our method can generalize well across different camera setups through cross-dataset experiments.