Overview / Usage

We introduce a novel yet challenging research problem, interactive crowd video generation, committed to producing diverse and continuous crowd video, and relieving the difficulty of insufficient annotated real-world datasets in crowd analysis.

Methodology / Approach

We propose a deep network architecture specifically designed for crowd video generation that is composed of two modules. Unlike previous works, we generate continuous crowd behaviors beyond identity annotations or matching. Extensive experiments show that our method is effective for crowd video generation. More importantly, we demonstrate the generated video can produce diverse crowd behaviors and be used for augmenting different crowd analysis tasks, i.e., crowd counting, anomaly detection, crowd video prediction.

Technologies Used

Convolutional Neural Network

Optical Flow

Other links

• Demo Video (YouTube)