OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality

2024-05-15

arXiv.org

AI Summary

Existing gait recognition methods exhibit poor generalization on real-world datasets; models trained indoors fail to transfer effectively to outdoor scenarios, severely limiting practical utility. Method: We introduce OpenGait, an open-source benchmark platform focused on enhancing real-world deployability. Through systematic ablation studies, we identify critical weaknesses in appearance-based, skeleton-based, and multimodal modeling paradigms. Based on these insights, we design three lightweight, robust baselines: DeepGaitV2 (RGB-driven), SkeletonGait (skeleton-driven), and SkeletonGait++ (cross-modal alignment and fusion). Contribution/Results: OpenGait provides a modular architecture supporting multiple input modalities, enabling strong extensibility and cross-domain generalization. It establishes the first unified evaluation framework to rigorously characterize the practical boundaries of each paradigm. Evaluated on several newly released real-world datasets, our methods achieve state-of-the-art performance and pinpoint fundamental bottlenecks in indoor-to-outdoor transfer—thereby steering the community toward utility-oriented gait recognition research.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Gait recognition, a rapidly advancing vision technology for person identification from a distance, has made significant strides in indoor settings. However, evidence suggests that existing methods often yield unsatisfactory results when applied to newly released real-world gait datasets. Furthermore, conclusions drawn from indoor gait datasets may not easily generalize to outdoor ones. Therefore, the primary goal of this paper is to present a comprehensive benchmark study aimed at improving practicality rather than solely focusing on enhancing performance. To this end, we developed OpenGait, a flexible and efficient gait recognition platform. Using OpenGait, we conducted in-depth ablation experiments to revisit recent developments in gait recognition. Surprisingly, we detected some imperfect parts of some prior methods and thereby uncovered several critical yet previously neglected insights. These findings led us to develop three structurally simple yet empirically powerful and practically robust baseline models: DeepGaitV2, SkeletonGait, and SkeletonGait++, which represent the appearance-based, model-based, and multi-modal methodologies for gait pattern description, respectively. In addition to achieving state-of-the-art performance, our careful exploration provides new perspectives on the modeling experience of deep gait models and the representational capacity of typical gait modalities. In the end, we discuss the key trends and challenges in current gait recognition, aiming to inspire further advancements towards better practicality. The code is available at https://github.com/ShiqiYu/OpenGait.

Problem

• Improving gait recognition for real-world outdoor scenarios
• Revisiting and refining prior gait recognition methodologies
• Developing robust baseline models for diverse gait modalities

Innovation

• Developed OpenGait for flexible gait recognition
• Created robust baseline models: DeepGaitV2, SkeletonGait++
• Explored deep gait modeling and modality representation