Deep inspection method for automatic identification of ship corrosion area

Abstract

The invention relates to a deep inspection method for automatic identification of a ship corrosion area, wherein the method comprises the steps: building a pre-training image identification model and a corrosion image automatic identification model, then labeling a large number of ship images, and training the corrosion image automatic identification model through a part of images with labels; inputting a plurality of to-be-detected ship images into the trained model, reserving the images marked with corrosion labels, and marking a corrosion area bounding box, wherein the marked images form a corrosion area positioning data set; establishing a corrosion area target detection model, and training the model by using part of the images in the corrosion area positioning data set; and finally, inputting a to-be-positioned rusted ship image into the trained corrosion area target detection model, outputting bounding box parameters of a corrosion area, and marking the position of the corrosion area by using a bounding box. According to the method, an integrated process from ship image acquisition to corrosion area automatic positioning is realized, a deep learning image recognition algorithm and a target detection algorithm are fused, and the method is very intelligent.

Description

technical field [0001] The invention relates to the field of ship corrosion area detection, in particular to an in-depth inspection method for automatic identification of ship corrosion areas. Background technique [0002] The traditional corrosion detection of warships is mostly on-site manual inspection, which often consumes a lot of time and energy, and even has potential safety hazards in high-risk areas of ships, which poses a potential threat to the personal safety of inspection workers. In order to reduce the time and labor cost of ship corrosion detection and promote the safe and efficient development of the work, it is necessary to focus on the current technological frontiers to improve the inspection process and reduce human intervention in the corrosion detection process as much as possible. [0003] At present, due to its low-cost and high-efficiency on-site performance, robot inspection has been initially applied in many scenarios such as construction sites and ...

AI Technical Summary

Problems solved by technology

[0004] In view of the fact that rust does not have a specific regular shape and color, image recognition is performed only based on the shape and color, and the rust detection error is relatively large

In addition, for a specific ship, the number of images collected by the UAV is limited, and relying solely on the collected images to train a complex deep neural network will also lead to large image recognition errors

Images