研究目的
To develop an autonomous in‐water visual inspection system for checking the structural integrity and biofouling of the ship hull surface to improve the operational safety and efficiency of ships and floating vessels.
研究成果
The developed H‐AUV system demonstrated practical feasibility for autonomous visual ship hull inspection in real sea environments. The system's performance was validated through field experiments, showing precise navigation and robust visual mapping capabilities. Future work may focus on improving lighting compensation and incorporating additional sensor data for enhanced hull‐relative pose estimation.
研究不足
Challenges include varying lighting conditions affecting image quality, the need for systematic lighting compensation schemes, and the difficulty in local plane estimation using sparse features due to non-uniform distribution on the hull surface.
1：Experimental Design and Method Selection:
The study involves the development of a hover‐capable autonomous underwater vehicle (H‐AUV) equipped with a stereo camera for visual perception and mapping. The vehicle's autonomy is achieved through guidance, navigation, and control algorithms.
2：Sample Selection and Data Sources:
The system was tested in a real sea environment with a full‐scale ship, R/V Onnuri, to validate its performance.
3：List of Experimental Equipment and Materials:
The vehicle platform includes navigation sensors (DVL, IMU), a stereo camera unit, an acoustic altimeter, lights, and propulsion systems.
4：Experimental Procedures and Operational Workflow:
The vehicle autonomously navigates along the ship's hull following a predefined path, maintaining a constant distance and normal direction to the hull surface.
5：Data Analysis Methods:
The study employs computer vision and optimization algorithms for vision‐based navigation and visual mapping, including stereo matching, feature extraction, and visual SLAM.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
