LCrowdV: Generating Labeled Videos for Simulation-based Crowd Behavior Learning

TL;DR

LCrowdV is a procedural framework that generates large, labeled crowd videos with customizable behaviors and environments, enhancing training datasets for crowd analysis algorithms.

Contribution

The paper introduces a novel procedural framework for generating labeled crowd videos, combining simulation and rendering to improve dataset diversity and realism for crowd behavior understanding.

Findings

Improved pedestrian detection accuracy using LCrowdV datasets

Enhanced crowd behavior classification performance

Ability to generate diverse, labeled crowd videos with controllable parameters

Abstract

We present a novel procedural framework to generate an arbitrary number of labeled crowd videos (LCrowdV). The resulting crowd video datasets are used to design accurate algorithms or training models for crowded scene understanding. Our overall approach is composed of two components: a procedural simulation framework for generating crowd movements and behaviors, and a procedural rendering framework to generate different videos or images. Each video or image is automatically labeled based on the environment, number of pedestrians, density, behavior, flow, lighting conditions, viewpoint, noise, etc. Furthermore, we can increase the realism by combining synthetically-generated behaviors with real-world background videos. We demonstrate the benefits of LCrowdV over prior lableled crowd datasets by improving the accuracy of pedestrian detection and crowd behavior classification algorithms. LCrowdV would be released on the WWW.