A5070571539- Video Surveillance and Tracking Methods
- Fire Detection and Safety Systems
- Image Enhancement Techniques
- Infrared Target Detection Methodologies
- Musculoskeletal pain and rehabilitation
- Advanced Image and Video Retrieval Techniques
- Ergonomics and Musculoskeletal Disorders
- Virtual Reality Applications and Impacts
- Visual Attention and Saliency Detection
- Advanced Vision and Imaging
- UAV Applications and Optimization
Beihang University
2012-2024
According to Darwinian evolutionary theory, numerous species in the wild have developed remarkable adaptive mechanisms, involving pattern rearrangement and environmental assimilation, evade predators. These obfuscation strategies pose significant challenges for both individuals algorithms when performing Camouflage Object Detection (COD) task complex intricate scenarios. Inspired by human COD task, which involve assigning uncertainties entire input then focusing on highly uncertain areas...
Recently, by virtue of the high computational efficiency and accuracy, discriminative correlation filter (DCF)- based tracking methods have gained attraction in field unmanned aerial vehicle (UAV). However, conventional DCF-based merely rely on cyclic shift to produce training samples. As a result, trained these samples owns limited ability, ineffectively addressing various challenges stage. Here, promote filter's we develop feature block-aware (CF) method. Specifically, extracted is divided...
As a significant research direction in remote sensing fields, unmanned aerial vehicles (UAVs) tracking has achieved rapid development recent years. However, due to limited power and computation resources on platforms, the methods deployed UAVs usually require high computational efficiency performance. In addition, various challenges (i.e., similar object, background clutter occlusion) have inevitably occurred during UAV phase. Therefore, considering above issues comprehensively, this paper...
With the advantages of discriminative correlation filter (DCF) in tracking accuracy and computational efficiency, DCF-based methods have been widely used field unmanned aerial vehicles (UAV) for target tracking. However, UAV inevitably encounters various challenging scenarios, such as background clutter, similar target, partial/full occlusion, fast motion, etc. These challenges generally lead to multi-peak interferences response map that cause drift or even loss. To tackle this problem, a...
With the high computation efficiency and tracking accuracy, discriminative correlation filters (DCF) have been applied to UAV tracking. However, in scenarios ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., complex background temporary occlusion), DCF-based trackers usually generate low credibility response under influence of distractors, which contains multiple side peaks declines performance. Motivated by consistency adjacent...
Ground-based preflight training utilizing unusual visual stimuli is useful for decreasing the susceptibility to space motion sickness (SMS). The effectiveness of sensorimotor adaptation affected by tasks, but what kind task more effective remains unknown. Whether complexity decisive factor consider designing and if other factors are important need be analyzed. results from analysis can help optimize tasks astronauts. Twenty right-handed subjects were asked draw right path 45° rotated maze...