Container surface damage detection method based on two-stage convolutional neural network

Abstract

The invention discloses a container surface damage detection method based on a two-stage convolutional neural network. The method comprises the following steps: S1, making a container surface damage detection training data set and a test data set; S2, constructing a container surface damage detection model based on a two-stage convolutional neural network, wherein the two-stage convolutional neural network comprises a segmentation network and a classification network, the segmentation network processes the container surface damage image sample to obtain a damage segmentation feature map, and the classification network performs damage type judgment on the container surface damage image; S3, training the container surface damage detection model through the training data set and the test data set; and S4, discriminating the surface damage of the container by using the trained model, and outputting a detection result. Container surface damage detection is carried out by establishing the two-stage convolutional neural network model, the recognition error rate can be effectively reduced, the detection accuracy is improved, and accurate judgment of the type of the container surface damage is achieved.

Description

technical field [0001] The invention relates to the field of container damage detection, in particular to a container surface damage detection method based on a two-stage convolutional neural network. Background technique [0002] In recent years, my country's social economy has grown rapidly, and the large-scale container ships and port automation have shown a high-speed development trend. Therefore, the business volume and throughput of container ports are also increasing. Because containers are prone to deformation and rupture due to frequent collisions during hoisting and stacking, and are often exposed to the sun and rain outdoors, resulting in corrosion holes, therefore, in the various operations of container ports, the inspection and evaluation of container surface damage is the key to container inspection. The necessary procedures of the port can effectively avoid accidents during container transportation and loading and unloading, and at the same time prevent disput...

AI Technical Summary

Problems solved by technology

At present, the detection technology with deep learning as the core has been more maturely applied to container number identification and ship detection in ports, but it is rarely used in container surface damage detection.

Images