Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis

Mritula Chandrasekaran, Sanket Kachole, Jarek Francik, Dimitrios Makris

Abstract

Pathological gait analysis is constrained by limited and variable clinical datasets, which restrict the modeling of diverse gait impairments. To address this challenge, we propose a Pathological Gait-conditioned Generative Adversarial Network (PGcGAN) that synthesises pathology-specific gait sequences directly from observed 3D pose keypoint trajectories data. The framework incorporates one-hot encoded pathology labels within both the generator and discriminator, enabling controlled synthesis across six gait categories. The generator adopts a conditional autoencoder architecture trained with adversarial and reconstruction objectives to preserve structural and temporal gait characteristics. Experiments on the Pathological Gait Dataset demonstrate strong alignment between real and synthetic sequences through PCA and t-SNE analyses, visual kinematic inspection, and downstream classification tasks. Augmenting real data with synthetic sequences improved pathological gait recognition across GRU, LSTM, and CNN models, indicating that pathology-conditioned gait synthesis can effectively support data augmentation in pathological gait analysis.

PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis

Abstract

Pathological gait analysis is constrained by limited and variable clinical datasets, which restrict the modeling of diverse gait impairments. To address this challenge, we propose a Pathological Gait-conditioned Generative Adversarial Network (PGcGAN) that synthesises pathology-specific gait sequences directly from observed 3D pose keypoint trajectories data. The framework incorporates one-hot encoded pathology labels within both the generator and discriminator, enabling controlled synthesis across six gait categories. The generator adopts a conditional autoencoder architecture trained with adversarial and reconstruction objectives to preserve structural and temporal gait characteristics. Experiments on the Pathological Gait Dataset demonstrate strong alignment between real and synthetic sequences through PCA and t-SNE analyses, visual kinematic inspection, and downstream classification tasks. Augmenting real data with synthetic sequences improved pathological gait recognition across GRU, LSTM, and CNN models, indicating that pathology-conditioned gait synthesis can effectively support data augmentation in pathological gait analysis.
Paper Structure (13 sections, 5 equations, 2 figures, 3 tables)

This paper contains 13 sections, 5 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Problem Formulation
  5. Conditional Generator
  6. Conditional Discriminator
  7. Training Objective
  8. Training Procedure
  9. Experimental Evaluation
  10. tSNE Analysis of Joint Angle Trajectories
  11. Classifier Performance
  12. Comparison with Existing Synthetic Gait Generation Approaches
  13. Conclusion

Figures (2)

  • Figure 1: Overview of the proposed Pathological Gait Conditioned GAN (PGcGAN) architecture. Gaussian noise and one-hot encoded pathology labels are used to condition the generator, which produces synthetic gait sequences through an encoder–decoder structure. Both real and generated sequences are combined with pathology labels and evaluated by the discriminator to distinguish real from synthetic motion patterns.
  • Figure 2: t-SNE visualization comparing the distribution of real and PGcGAN-generated gait features.