Walking Further: Semantic-aware Multimodal Gait Recognition Under Long-Range Conditions

TL;DR

This paper introduces LRGait, a new multimodal benchmark for long-range gait recognition, and proposes EMGaitNet, a novel framework that fuses semantic cues from RGB and LiDAR data to improve recognition accuracy in outdoor environments.

Contribution

The paper presents the first long-range multimodal gait recognition benchmark and a semantic-guided fusion framework that effectively aligns and integrates 2D and 3D gait features.

Findings

Effective long-range gait recognition demonstrated on new benchmark

Semantic-guided fusion improves cross-modal feature alignment

Hierarchical feature integration enhances recognition accuracy

Abstract

Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range, unimodal settings and fail to generalize to long-range and cross-distance scenarios under real-world conditions. To address this gap, we present \textbf{LRGait}, the first LiDAR-Camera multimodal benchmark designed for robust long-range gait recognition across diverse outdoor distances and environments. We further propose \textbf{EMGaitNet}, an end-to-end framework tailored for long-range multimodal gait recognition. To bridge the modality gap between RGB images and point clouds, we introduce a semantic-guided fusion pipeline. A CLIP-based Semantic Mining (SeMi) module first extracts human body-part-aware semantic cues, which are then employed to align 2D and 3D features via a Semantic-Guided Alignment (SGA) module within a unified embedding space. A Symmetric Cross-Attention Fusion (SCAF) module hierarchically integrates visual contours and 3D geometric features, and a Spatio-Temporal (ST) module captures global gait dynamics. Extensive experiments on various gait datasets validate the effectiveness of our method.