GaitFFDA: Feature Fusion and Dual Attention Gait Recognition Model

Abstract

Gait recognition has a wide range of application scenarios in the fields of intelligent security and transportation. Gait recognition currently faces challenges: inadequate feature methods for environmental interferences and insufficient local-global information correlation. To address these issues, we propose a gait recognition model based on feature fusion and dual attention. Our model utilizes the ResNet architecture as the backbone network for fundamental gait features extraction. Subsequently, the features from different network layers are passed through the feature pyramid for feature fusion, so that multi-scale local information can be fused into global information, providing a more complete feature representation. The dual attention module enhances the fused features in multiple dimensions, enabling the model to capture information from different semantics and scale information. Our model proves effective and competitive results on CASIA-B (NM: 95.6%, BG: 90.9%, CL: 73.7%) and OU-MVLP (88.1%). The results of related ablation experiments show that the model design is effective and has strong competitiveness.