# Human Pose Estimation for Real-World Crowded Scenarios

arXiv: https://arxiv.org/abs/1907.06922 · HTML: https://mlsanity.com/paper/1907.06922/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?](https://mlsanity.com/paper/2108.09518/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2101.02471/) (2021)
- [Reconstructing Groups of People with Hypergraph Relational Reasoning](https://mlsanity.com/paper/2308.15844/) (2023)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation](https://mlsanity.com/paper/2207.02425/) (2022)
- [Do as we do: Multiple Person Video-To-Video Transfer](https://mlsanity.com/paper/2104.04721/) (2021)
- [Computer Vision-based Social Distancing Surveillance Solution with Optional Automated Camera Calibration for Large Scale Deployment](https://mlsanity.com/paper/2104.10891/) (2021)
- [Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation](https://mlsanity.com/paper/2505.12130/) (2025)

## Abstract (arXiv)

Human pose estimation has recently made significant progress with the adoption of deep convolutional neural networks. Its many applications have attracted tremendous interest in recent years. However, many practical applications require pose estimation for human crowds, which still is a rarely addressed problem. In this work, we explore methods to optimize pose estimation for human crowds, focusing on challenges introduced with dense crowds, such as occlusions, people in close proximity to each other, and partial visibility of people. In order to address these challenges, we evaluate three aspects of a pose detection approach: i) a data augmentation method to introduce robustness to occlusions, ii) the explicit detection of occluded body parts, and iii) the use of the synthetic generated datasets. The first approach to improve the accuracy in crowded scenarios is to generate occlusions at training time using person and object cutouts from the object recognition dataset COCO (Common Objects in Context). Furthermore, the synthetically generated dataset JTA (Joint Track Auto) is evaluated for the use in real-world crowd applications. In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications. Additionally, the occlusion flags provided with JTA are utilized to train a model, which explicitly distinguishes between occluded and visible body parts in two distinct branches. The combination of the proposed additions to the baseline method help to improve the overall accuracy by 4.7% AP and thereby provide comparable results to current state-of-the-art approaches on the respective dataset.