Dense-View GEIs Set: View Space Covering for Gait Recognition based on Dense-View GAN
This addresses the challenge of limited view angles in gait recognition datasets, which can reduce performance for long-distance human identification, though it is incremental in generating synthetic data to enhance robustness.
The paper tackles the problem of view variance in gait recognition by introducing a Dense-View GEIs Set (DV-GEIs) covering angles from 0 to 180 degrees at 1-degree intervals, synthesized using a Dense-View GAN (DV-GAN), which improves view-invariant feature learning as shown on CASIA-B and OU-ISIR datasets.
Gait recognition has proven to be effective for long-distance human recognition. But view variance of gait features would change human appearance greatly and reduce its performance. Most existing gait datasets usually collect data with a dozen different angles, or even more few. Limited view angles would prevent learning better view invariant feature. It can further improve robustness of gait recognition if we collect data with various angles at 1 degree interval. But it is time consuming and labor consuming to collect this kind of dataset. In this paper, we, therefore, introduce a Dense-View GEIs Set (DV-GEIs) to deal with the challenge of limited view angles. This set can cover the whole view space, view angle from 0 degree to 180 degree with 1 degree interval. In addition, Dense-View GAN (DV-GAN) is proposed to synthesize this dense view set. DV-GAN consists of Generator, Discriminator and Monitor, where Monitor is designed to preserve human identification and view information. The proposed method is evaluated on the CASIA-B and OU-ISIR dataset. The experimental results show that DV-GEIs synthesized by DV-GAN is an effective way to learn better view invariant feature. We believe the idea of dense view generated samples will further improve the development of gait recognition.