Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods

TL;DR

This paper introduces MovingDroneCrowd++, a large drone-captured dataset for dense crowd counting and tracking, and proposes GD3A and DVTrack methods that significantly improve accuracy in complex, large-scale scenes.

Contribution

The paper presents the first large-scale drone-based dataset and novel density map and descriptor-based methods for crowd counting and tracking in dynamic scenes.

Findings

GD3A reduces counting error by 47.4%

DVTrack improves tracking performance by 39.2%

Methods outperform existing approaches in dense, complex scenes

Abstract

Counting and tracking dense crowds in large-scale scenes is highly challenging, yet existing methods mainly rely on datasets captured by fixed cameras, which provide limited spatial coverage and are inadequate for large-scale dense crowd analysis. To address this limitation, we propose a flexible solution using moving drones to capture videos and perform video-level crowd counting and tracking of unique pedestrians across entire scenes. We introduce MovingDroneCrowd++, the largest video-level dataset for dense crowd counting and tracking captured by moving drones, covering diverse and complex conditions with varying flight altitudes, camera angles, and illumination. Existing methods fail to achieve satisfactory performance on this dataset. To this end, we propose GD3A (Global Density Map Decomposition via Descriptor Association), a density map-based video individual counting method that avoids explicit localization. GD3A establishes pixel-level correspondences between pedestrian descriptors across consecutive frames via optimal transport with an adaptive dustbin score, enabling the decomposition of global density maps into shared, inflow, and outflow components. Building on this framework, we further introduce DVTrack, which converts descriptor-level matching into instance-level associations through a descriptor voting mechanism for pedestrian tracking. Experimental results show that our methods significantly outperform existing approaches under dense crowds and complex motion, reducing counting error by 47.4 percent and improving tracking performance by 39.2 percent.