July 23, 2025

Multi-Person 2D Human Pose Estimation: A Benchmark for Real-Time Applications

Key Points

Multi-person human pose estimation is essential for real-time computer vision applications.
Six frameworks, including OpenPose and YOLO, were benchmarked using the Panoptic dataset.
Metrics like Average Precision and Average Recall were used to assess the models' performance effectively.
Findings assist practitioners in selecting optimal frameworks for real-world implementation of pose estimation.

Abstract

Abstract Human pose estimation (HPE) is a criticalcomponent of computer vision, enabling real-time ap-plications across various fields. This study benchmarkssix state-of-the-art frameworks — OpenPose, YOLO,RTMO, RTMPose, Sapiens, and MoveNet—in the context of 2D multi-person pose estimation in videos for real-time applications. Using the Panoptic dataset and standardized metrics, including Object Keypoint Similarity (OKS), Average Precision (AP), and Average Recall (AR), we evaluate their accuracy, speed, and hardware efficiency under realistic conditions such as occlusion and crowded scenes. Our analysis highlights the strengths and limitations of each framework, providing valuable insights to help practitioners select and deploy reliable HPE solutions in real-world applications. Mathematics Subject Classification (2020) MSC code1 · MSC code2 · more

Bookmark

Multi-Person 2D Human Pose Estimation: A Benchmark for Real-Time Applications

Key Points

Abstract

Cite This Study