Corrosion Detection for Large Steel Structure base on UAV Integrated with Image Processing System

3rd International Conference on Aeronautical Materials and Aerospace Engineering

航空航天工程

Chen, Qingcheng^1 ; Wen, Xiang^1 ; Lu, Shujie^2 ; Sun, Dongxiao^2

Shanghai Institute of Special Equipment Inspection and Technical Research, China^1

Shanghai Jiao Tong University, Shanghai, China^2

关键词: Background noise;    Corrosion detection;    Detection accuracy;    Image processing system;    Labour intensity;    Large steel structures;    Manual inspection;    Recognition algorithm;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/608/1/012020/pdf
DOI  :  10.1088/1757-899X/608/1/012020

学科分类：航空航天科学

来源: IOP

【 摘 要 】

Large cranes and other outdoor large steel structures need to be checked regularly to ensure their safety, and corrosion detection is one of the most important inspection item. Traditional manual inspection has many disadvantages including high labour intensity, low efficiency and low detection accuracy. In this paper, a novel corrosion detection method based on UAV intelligent image recognition is proposed. The six-rotor UAV can collect the photos of the steel structure device safely and reliably. With the intelligent corrosion recognition algorithm proposed in this paper, infection such as background noise can be eliminated, and the corrosion area in the image can be identified automatically with high precision. A test device has been built and the results show that the device and method can identify the corrosion area effectively.