OptiGait-LGBM: An Efficient Approach of Gait-based Person Re-identification in Non-Overlapping Regions

TL;DR

This work tackles gait-based person re-identification in uncontrolled outdoor environments with non-overlapping camera views. It proposes OptiGait-LGBM, a lightweight gait recognizer that uses skeletal landmark features extracted by MediaPipe and a LightGBM classifier, evaluated on the RUET-GAIT dataset. The approach demonstrates that LGBM outperforms Random Forest and CatBoost in accuracy, training time, and memory usage, while maintaining robustness to illumination and clutter; a camera-correction factor further improves cross-view consistency. Collectively, the method delivers a low-cost, memory-efficient solution for real-world gait Re-ID and points to future enhancements through 3D gait analysis and multi-modal fusion.

Abstract

Gait recognition, known for its ability to identify individuals from a distance, has gained significant attention in recent times due to its non-intrusive verification. While video-based gait identification systems perform well on large public datasets, their performance drops when applied to real-world, unconstrained gait data due to various factors. Among these, uncontrolled outdoor environments, non-overlapping camera views, varying illumination, and computational efficiency are core challenges in gait-based authentication. Currently, no dataset addresses all these challenges simultaneously. In this paper, we propose an OptiGait-LGBM model capable of recognizing person re-identification under these constraints using a skeletal model approach, which helps mitigate inconsistencies in a person's appearance. The model constructs a dataset from landmark positions, minimizing memory usage by using non-sequential data. A benchmark dataset, RUET-GAIT, is introduced to represent uncontrolled gait sequences in complex outdoor environments. The process involves extracting skeletal joint landmarks, generating numerical datasets, and developing an OptiGait-LGBM gait classification model. Our aim is to address the aforementioned challenges with minimal computational cost compared to existing methods. A comparative analysis with ensemble techniques such as Random Forest and CatBoost demonstrates that the proposed approach outperforms them in terms of accuracy, memory usage, and training time. This method provides a novel, low-cost, and memory-efficient video-based gait recognition solution for real-world scenarios.

Figures (12)

• Figure 1: Human Gait Cycle
• Figure 2: Overlapping vs Non-Overlapping Camera
• Figure 3: Map of Surveillance Camera Setup
• Figure 4: The Flow Diagram of Proposed Methodology
• Figure 5: Camera to Subject Distance Comparison with CASIA-B