# Estimating People Flows to Better Count Them in Crowded Scenes

arXiv: https://arxiv.org/abs/1911.10782 · HTML: https://mlsanity.com/paper/1911.10782/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [DR.VIC: Decomposition and Reasoning for Video Individual Counting](https://mlsanity.com/paper/2203.12335/) (2022)
- [Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark](https://mlsanity.com/paper/2107.08645/) (2021)
- [Multi-view Tracking Using Weakly Supervised Human Motion Prediction](https://mlsanity.com/paper/2210.10771/) (2022)
- [A Spatio-Temporal Attentive Network for Video-Based Crowd Counting](https://mlsanity.com/paper/2208.11339/) (2022)
- [International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines](https://mlsanity.com/paper/2110.14613/) (2021)
- [Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks](https://mlsanity.com/paper/2212.11542/) (2022)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark](https://mlsanity.com/paper/2411.13056/) (2024)
- [Spatiotemporal Event Graphs for Dynamic Scene Understanding](https://mlsanity.com/paper/2312.07621/) (2023)
- [Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges](https://mlsanity.com/paper/2608.23845/) (2026)

## Abstract (arXiv)

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it also enables us to exploit the correlation between people flow and optical flow to further improve the results. We will demonstrate that we consistently outperform state-of-the-art methods on five benchmark datasets.