A5059048799- Gait Recognition and Analysis
- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Indoor and Outdoor Localization Technologies
- Context-Aware Activity Recognition Systems
- Hand Gesture Recognition Systems
- Non-Invasive Vital Sign Monitoring
- Anomaly Detection Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
Universidad de Málaga
2018-2023
People identification using gait information (i.e., the way a person walks) obtained from inertial sensors is robust approach that can be used in multiple situations where vision-based systems are not applicable. Typically, previous methods use hand-crafted features or deep learning approaches with pre-processed as input. In contrast, we present new learning-based end-to-end employs raw data By this way, our able to automatically learn best representations without any constraint introduced...
Gait recognition systems typically rely solely on silhouettes for extracting gait signatures. Nevertheless, these approaches struggle with changes in body shape and dynamic backgrounds; a problem that can be alleviated by learning from multiple modalities. However, many real-life some modalities missing, therefore most existing multimodal frameworks fail to cope missing To tackle this problem, work, we propose UGaitNet, unifying framework recognition, robust UGaitNet handles mingles various...
Gait recognition is being employed as an effective approach to identify people without requiring subject collaboration. Nowadays, developed techniques for this task are obtaining high performance on current datasets (usually more than 90 % of accuracy). However, those simple they only contain one in the scene at same time. This fact limits extrapolation results real world conditions where, usually, multiple subjects simultaneously present scene, generating different types occlusions and...
This paper addresses the problem of gait-based people identification by copying optical flowbased signatures.The proposed model, coined as GaitCopy, receives input a stack gray images and returns gait signature represented subject.The novel property this network is that it not trained to only generate discriminative signatures, but copy signatures generated Master on flow inputs.Then, GaitCopy enforced extract based motion appearance, despite having been with pixel inputs.We implement two...
Multimodal systems for gait recognition have gained a lot of attention. However, there is clear gap in the study missing modalities, which represents real-life scenarios where sensors fail or data get corrupted. Here, we investigate how to handle modalities recognition. We propose single and flexible framework that uses variable number input modalities. For each modality, it consists branch binary unit indicating whether modality available; these are gated merged together. Finally, generates...