# Monocular Person Localization under Camera Ego-motion

arXiv: https://arxiv.org/abs/2503.02916 · HTML: https://mlsanity.com/paper/2503.02916/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019)
- [Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot](https://mlsanity.com/paper/2402.14654/) (2024)
- [6-DoF Object Pose from Semantic Keypoints](https://mlsanity.com/paper/1703.04670/) (2017)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation](https://mlsanity.com/paper/1906.06059/) (2019)
- [Cerberus: Low-Drift Visual-Inertial-Leg Odometry For Agile Locomotion](https://mlsanity.com/paper/2209.07654/) (2022)
- [Survey on video anomaly detection in dynamic scenes with moving cameras](https://mlsanity.com/paper/2308.07050/) (2023)
- [Single Image Human Proxemics Estimation for Visual Social Distancing](https://mlsanity.com/paper/2011.02018/) (2020)
- [BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking](https://mlsanity.com/paper/2309.01236/) (2023)
- [FieldSAFE: Dataset for Obstacle Detection in Agriculture](https://mlsanity.com/paper/1709.03526/) (2017)
- [Person Following by Autonomous Robots: A Categorical Overview](https://mlsanity.com/paper/1803.08202/) (2018)
- [Perceiving Humans: from Monocular 3D Localization to Social Distancing](https://mlsanity.com/paper/2009.00984/) (2020)
- [Single View Physical Distance Estimation using Human Pose](https://mlsanity.com/paper/2106.10335/) (2021)
- [Person Re-Identification for Robot Person Following with Online Continual Learning](https://mlsanity.com/paper/2309.11727/) (2023)
- [Perception for Humanoid Robots](https://mlsanity.com/paper/2309.15616/) (2023)
- [Robot Person Following Under Partial Occlusion](https://mlsanity.com/paper/2302.02121/) (2023)
- [People Tracking in Panoramic Video for Guiding Robots](https://mlsanity.com/paper/2206.02735/) (2022)
- [Human Orientation Estimation under Partial Observation](https://mlsanity.com/paper/2404.14139/) (2024)

## Built on by (most cited first, 1 of 1)

- [Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?](https://mlsanity.com/paper/2606.22987/) (2026)

## Abstract (arXiv)

Localizing a person from a moving monocular camera is critical for Human-Robot Interaction (HRI). To estimate the 3D human position from a 2D image, existing methods either depend on the geometric assumption of a fixed camera or use a position regression model trained on datasets containing little camera ego-motion. These methods are vulnerable to severe camera ego-motion, resulting in inaccurate person localization. We consider person localization as a part of a pose estimation problem. By representing a human with a four-point model, our method jointly estimates the 2D camera attitude and the person's 3D location through optimization. Evaluations on both public datasets and real robot experiments demonstrate our method outperforms baselines in person localization accuracy. Our method is further implemented into a person-following system and deployed on an agile quadruped robot.