Crowd Analysis

Application Fields of Depth Image Processing

Depth images can be used for detection and tracking of individuals, and to calculate the densities among crowds of people. Different depth sensors are placed perpendicular to the ground in order to provide distance information from a top-view position. Usage of intrinsic and extrinsic camera parameters allows estimation of a ground plane and comparison to the measured distances of the sensors in every pixel. Differences to the expected ground plane define foreground information, that is subsequently combined to associated regions. These regions of interest (ROI) are analyzed to distinguish persons from other objects by using a matched filter that is applied the height segmented depth information of each of these regions.

The proposed method separates crowds into individuals and facilitates a multi-object tracking system based on Kalman filtering. Depth images and a model plane are projected into a 3D voxel scene. The occupied space is defined by voxels that comply the model plane’s constraints and are located above the model plane’s height. Finally, density is measured by the relation of occluded space in contrast to the space provided by the model plane. Experiments with different crowding situations – from very low to very high density – and different heights of camera placements have proven the applicability and practicability of the system.

Share this project:
Share on Pinterest