A5048960766- Dam Engineering and Safety
- Infrastructure Maintenance and Monitoring
- Advanced Neural Network Applications
- Music and Audio Processing
- Concrete Corrosion and Durability
- Optical Systems and Laser Technology
- Vehicle License Plate Recognition
- Hydrology and Sediment Transport Processes
- Robotics and Sensor-Based Localization
- Advanced Image Fusion Techniques
- Industrial Vision Systems and Defect Detection
- Image and Video Stabilization
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Winter Sports Injuries and Performance
- Image Enhancement Techniques
- Robotic Locomotion and Control
- Diverse Musicological Studies
- Speech and Audio Processing
Southwest University of Science and Technology
2022-2024
In this article, a dam crack detection method based on the YOLOv8 algorithm for image collection during unmanned aerial vehicle (UAV) inspections is proposed, aiming to achieve efficient, fast, and accurate visual safety of dam. The deep learning framework used annotate public dataset cracks train model detection. trained then applied recognition UAV inspection images automatic positioning cracks. experimental environment built by capturing high-definition (4000×3000) surface concrete...
Quadruped robots possess significant mobility in complex and uneven terrains due to their outstanding stability flexibility, making them highly suitable rescue missions, environmental monitoring, smart agriculture. With the increasing use of quadruped more demanding scenarios, ensuring accurate stable state estimation environments has become particularly important. Existing algorithms relying on multi-sensor fusion, such as those using IMU, LiDAR, visual data, often face challenges...
In daily life, tool management has always been a serious problem faced by maintenance enterprises such as aircraft production and plants, automobile manufacturing plants or precision instrument factories. With the rapid development of artificial intelligence technology, machines also have strong learning ability can achieve many things that humans do. face recognition function our mobile phones, fingerprint unlock on gate, even iris secret place checkpoint are embodiment in life. Taking YOLO...
As the UAV is susceptible to its own engine vibration and irregular airflow in inspection process, image sequence collected has jitter, which affects reliability of results. To solve this problem, paper proposes an improved Shi-Tomasi algorithm combined with a selective mechanistic motion model for stabilization eliminate jitter component images produce stable images. Firstly, feature points are extracted by using algorithm, point matching performed optical flow tracking. Then determined...