A5101734929- Gait Recognition and Analysis
- Human Pose and Action Recognition
- Hand Gesture Recognition Systems
- Video Surveillance and Tracking Methods
- Image Processing and 3D Reconstruction
- Multi-Criteria Decision Making
- Stability and Control of Uncertain Systems
- Matrix Theory and Algorithms
- Control Systems and Identification
- Handwritten Text Recognition Techniques
- Advanced Neural Network Applications
- Vehicle License Plate Recognition
- Human Motion and Animation
- Advanced Vision and Imaging
- Color perception and design
- Robot Manipulation and Learning
State Grid Corporation of China (China)
2025
Beijing Normal University
2023-2024
Chongqing University
2023
Fuzhou University
2006-2014
Recent works on pose-based gait recognition have demonstrated the potential of using such simple information to achieve results comparable silhouette-based methods. However, generalization ability methods different datasets is undesirably inferior that ones, which has received little attention but hinders application these in real-world scenarios. To improve across datasets, we propose a Generalized Pose-based Gait (GPGait) framework. First, Human-Oriented Transformation (HOT) and series...
Gait recognition aims to obtain people's identity through body shape and walking posture. Existing gait studies focus on low vertical view recognition, in which the person camera are nearly at same height. Differently, this work, we high views. To facilitate research, propose a new dataset named DroneGait, where drones used collect data. This contains 22 k sequences of 96 subjects taken different views, varying from about 0 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML"...
The vulnerable road users (VRUs), being small and exhibiting random movements, increase the difficulty of object detection autonomous emergency braking system for AEBS-VRUs, with their behaviors highly random. To overcome existing problems AEBS-VRU detection, an enhanced YOLOv5 algorithm is proposed. While Complete Intersection over Union-Loss (CIoU-Loss) Distance Union-Non-Maximum Suppression (DIoU-NMS) are fused to improve model’s convergent speed, also incorporates a minor layer...
An open problem in mobile manipulation is how to represent objects and scenes a unified manner, so that robots can use it both for navigating the environment manipulating objects. The latter requires capturing intricate geometry while understanding fine-grained semantics, whereas former involves complexity inherit an expansive physical scale. In this work, we present GeFF (Generalizable Feature Fields), scene-level generalizable neural feature field acts as representation navigation performs...