A5009259536- Winter Sports Injuries and Performance
- Human Motion and Animation
- Hand Gesture Recognition Systems
- Virtual Reality Applications and Impacts
- Pancreatic function and diabetes
- Infrared Thermography in Medicine
- Ergonomics and Musculoskeletal Disorders
- AI and Multimedia in Education
- MicroRNA in disease regulation
- Robotic Locomotion and Control
- Organ Transplantation Techniques and Outcomes
- Neuroinflammation and Neurodegeneration Mechanisms
- Extracellular vesicles in disease
- Cardiac Ischemia and Reperfusion
- Cryospheric studies and observations
Harbin University
2020-2025
Microglia are the resident immune cells in central nervous system and play an essential role brain homeostasis neuroprotection diseases. Exosomes crucial intercellular communication by transporting bioactive miRNAs. Thus, this study aimed to investigate function of microglial exosome presence ischemic injury related mechanism. Oxygen-glucose deprivation (OGD)-treated neurons transient middle cerebral artery occlusion (TMCAO)-treated mice were applied study. Western blotting, RT-PCR, RNA-seq,...
Rapid human motion pose tracking has extensive applications in fields such as capture, intelligent monitoring, sports training, and physical health management. It can provide accurate data support, enhance safety optimize training outcomes, promote health. Traditional methods predominantly rely on either sensors or images for tracking, which often results issues like low accuracy slow speed. To address these problems, a rapid method based improved deep reinforcement learning multimodal...
Snowboarding is a kind of sport that takes snowboarding as tool, swivels and glides rapidly on the specified slope line, completes all kinds difficult actions in air. Because state high-speed movement, it to direct guidance during sport, which not conducive athletes find problems correct them, so necessary track target snowboarding. The tracking algorithm main solution this task, but there are many existing have been solved, especially accuracy complex scenes insufficient. Therefore, based...
Automatic tracking of three-dimensional (3D) human motion pose has the potential to provide corresponding technical support in various fields. However, existing methods for suffer from significant errors, long times and suboptimal results. To address these issues, an automatic method 3D using contrastive learning is proposed. By feature parameters poses, threshold variation poses are computed. The golden section introduced transform extract features by comparing with parameter variation....
Due to the influence of environmental interference and too fast speed, there are some problems in ski motion capture, such as inaccurate delay, loss, resulting inconsistency between actual later athletes virtual characters. To solve above problems, a real‐time skiing capture method snowboarders based on 3D vision sensor is proposed. This combines Time Fight (TOF) camera high‐speed form acquisition system. The collected images fused complete image, pose solved. data bound with constructed...
There is a lot of noise in the snowboard starting action image, which leads to low accuracy feature extraction. We propose extraction using visual sensor image processing. Firstly, overlapping images are separated by laser fringe technology. After separation, middle point taken as point, and interference factors filtered laser. Secondly, three-dimensional model established sensing technology, input order recognition, all actions reconstructed assembled complete snowboard. The laser, part...