Automation of Pedestrian Tracking in a Crowded Situation

TL;DR

This paper presents an automated system for tracking pedestrians in crowded, occluded scenes using video data, employing probabilistic methods to improve accuracy in challenging conditions.

Contribution

It introduces a two-module tracking system that effectively handles heavy occlusions and clutter in crowded pedestrian scenes using Bayesian updates.

Findings

Successfully tracks large crowds under occlusion

Achieves high accuracy in top-angled crowded scenes

Generates comprehensive pedestrian trajectory databases

Abstract

Studies on microscopic pedestrian requires large amounts of trajectory data from real-world pedestrian crowds. Such data collection, if done manually, needs tremendous effort and is very time consuming. Though many studies have asserted the possibility of automating this task using video cameras, we found that only a few have demonstrated good performance in very crowded situations or from a top-angled view scene. This paper deals with tracking pedestrian crowd under heavy occlusions from an angular scene. Our automated tracking system consists of two modules that perform sequentially. The first module detects moving objects as blobs. The second module is a tracking system. We employ probability distribution from the detection of each pedestrian and use Bayesian update to track the next position. The result of such tracking is a database of pedestrian trajectories over time and space. With certain prior information, we showed that the system can track a large number of people under occlusion and clutter scene.