VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Running

Luis F. Gomez; Julian Fierrez; Roberto Daza; Ruben Tolosana; Aythami Morales; Gonzalo Garrido; Javier Rueda; Enrique Navarro

cs.CVAug 19, 2026

VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Running

Authors: Luis F. Gomez, Julian Fierrez, Roberto Daza, Ruben Tolosana, Aythami Morales, Gonzalo Garrido, Javier Rueda, Enrique Navarro

Organizations: BiometricsAI, Universidad Autonoma de Madrid (UAM), Spain

Abstract

Human pose estimation has advanced significantly due to the development of deep learning models, increased data availability, and improved computing resources. These developments have led to highly accurate body tracking systems with direct applications in sports analysis and performance evaluation. The VideoRun2D Demo performs a biomechanical analysis during sprints using different human pose estimators. The proposed framework was evaluated using human pose trackers and expert manual annotations. The tested framework uses 314 sprints from 44 professional runners, focusing on two key joint angles in sprint biomechanics: 1) hip flexion/extension and 2) knee flexion/extension. The framework also includes a post-processing module for outlier detection. The tested results demonstrate that the average root-mean-square errors range from 11.46° to 5.83° for the best trackers. When integrated with the post-processing modules, these errors can be reduced to 9.87° and 5.30°, respectively. The VideoRun2D Demo findings suggest that human pose-tracking approaches can be valuable resources for the biomechanical analysis of running.

Figures & tables

Fig. 1: Block diagram of the VideoRun2D system. The system has five modules that estimate joint angles.

Fig. 2: Graphical example of the correction of the left knee angle in all the thirteen strides from the sprinter two, both before (on the left) and after (on the right) post-processing

Tracker	Hip angle [°]		Knee angle [°]		Mean [°]
Tracker	Right	Left	Right	Left	Mean [°]
ViTPose-B	7.39	9.74	7.94	6.79	7.96
ViTPose-L	7.00	9.53	5.75	6.54	7.21
RTMPose-M	6.67	9.36	5.37	6.55	6.99
RTMPose-L	6.94	9.75	5.30	6.60	7.15
RTMPose-L ∗	7.01	9.73	5.36	6.39	7.12

TABLE I: RMSE values for all evaluated trackers (Section II-A2 ). Boldface indicates the best result in each column.

Trackers	Hip angle [°]		Knee angle [°]		Mean [°]
Trackers	Right	Left	Right	Left	Mean [°]
VL + RM + RL + RL ∗	6.77	9.23	5.24	6.31	6.89
VL + RM + RL	6.75	9.24	5.28	6.37	6.91
VL + RM + RL ∗	6.76	9.17	5.29	6.29	6.88
VL + RL + RL ∗	6.87	9.36	5.27	6.32	6.96
RM + RL + RL ∗	6.77	9.29	5.24	6.33	6.91

TABLE II: RMSE values obtained by averaging the pose estimates across trackers. Abbreviations: VL = ViTPose-L, RM = RTMPose-M, RL = RTMPose-L, and RL ∗ = RTMPose-L ∗ (

384\times 288

input). Boldface indicates the best result in each column.

Fig. 3: Block diagram of the VideoRun2D Demo platform operation.

Fig. 4: Graphical representation of joint points and angles calculated for four sprinters using the RTMPose model after the proposed tracking postprocessing. The orange lines and dots represent the right side of the corridor, while the purple lines and dots represent the left side. (Color image.)

Explore similar work

Markerless Pose Estimation for Resistance Training Technique Assessment
Aug 25, 2026Joseph Turner, Jeff Clark, Nawid KeshtmandAction Quality Assessment Human Pose Estimation
School of Engineering Mathematics and Technology, University of Bristol, UK
Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization
Apr 23, 2026Parth Agrawal, Ronit, Sagar Kumar +1Markerless Motion Capture Sports Video Analysis
Department of Computer Science and Engineering, Chandigarh University Punjab, India
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
Jul 9, 2026Ayda Eghbalian, Kevin Desai3D Human Pose Estimation
Department of Computer Science, University of Texas at San Antonio, One UTSA Circle, San Antonio, 78249, Texas, United States.

Aug 25, 2026J/K move · Enter open · S save

Markerless Pose Estimation for Resistance Training Technique Assessment

Joseph Turner, Jeff Clark, Nawid Keshtmand

School of Engineering Mathematics and Technology, University of Bristol, UK

Action Quality Assessment Human Pose Estimation

Open paper AskPDF arXiv

Resistance training can be a high risk activity, and safe form is essential to avoiding injury. Laboratory-based movement analysis provides quantitive technique assessment, yet is not easily accessible. Markerless pose estimation infers body landmarks from images or video without physical markers and could offer a feasible alternative for technique assessment. We present a pose estimation framework to evaluate resistance-training technique from ordinary video footage. Using BlazePose, anatomical landmarks were extracted from squat, bench press, and deadlift videos and converted into joint-angle trajectories, with the squat serving as the primary case study. Trajectories were assessed against a defined reference repetition using root mean square error (RMSE). Results show that the framework recovers meaningful kinematic patterns for the squat and deadlift, enabling quantitative comparison between repetitions and identification of technique variability within a set. Performance depended strongly on camera orientation and visual occlusion, with non-sagittal views distorting 2D joint-angle estimates. The findings demonstrate that markerless pose estimation can support accessible biomechanical assessment outside laboratory environments.

Abstract

Explore similar work

Markerless Pose Estimation for Resistance Training Technique Assessment

Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization

Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction