DeepAI AI Chat
Log In Sign Up

VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios

by   Huanzhang Dou, et al.

With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of 11,000 subjects with fine-grained attributes in various complicated scenarios. Compared with existing real gait datasets with limited samples and simple scenarios, the proposed VersatileGait dataset possesses several nice properties, including huge dataset size, high sample diversity, high-quality annotations, multi-pitch angles, small domain gap with the real one, etc. Furthermore, we investigate the effectiveness of our dataset (e.g., domain transfer after pretraining). Then, we use the fine-grained attributes from VersatileGait to promote gait recognition in both accuracy and speed, and meanwhile justify the gait recognition performance under multi-pitch angle settings. Additionally, we explore a variety of potential applications for research.Extensive experiments demonstrate the value and effective-ness of the proposed VersatileGait in gait recognition along with its associated applications. We will release both VersatileGait and its corresponding data generation toolkit for further studies.


page 1

page 3

page 4

page 5

page 7

page 8


VersatileGait: A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation

Gait recognition has a rapid development in recent years. However, gait ...

Parsing is All You Need for Accurate Gait Recognition in the Wild

Binary silhouettes and keypoint-based skeletons have dominated human gai...

Gait Recognition in the Wild: A Benchmark

Gait benchmarks empower the research community to train and evaluate hig...

Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark

Gait depicts individuals' unique and distinguishing walking patterns and...

Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification

Person re-identification (re-ID) plays an important role in applications...

BB-MAS: A Very Large Dataset for Typing, Gait and Swipe of the Same Person on Desktop, Tablet and Phone

Behavioral biometrics are key components in the landscape of research in...