Container dangerous goods identification detection method based on machine vision and deep learning

Abstract

The invention discloses a container dangerous goods identification detection method based on machine vision and deep learning, and the method comprises the following steps: 1, employing a camera installed on a wharf crane as an image collector, and collecting the identification data of container dangerous goods; 2, making a data set by using the collected dangerous goods identification data, and performing enhancement processing on the data set; and step 3, detecting and identifying the classification identifier of the dangerous goods and outputting an identification result. Compared with the prior art, the method has the positive effects that the method can effectively utilize a deep learning algorithm to extract picture feature information, and performs feature detection and classification on the dangerous goods identification by depending on a large amount of data, so that not only is the position of the dangerous goods identification output, but also the dangerous goods type is output; the wharf production operation efficiency is improved.

Description

technical field [0001] The technical field of the present invention is artificial intelligence, machine vision, and deep learning. Target detection and classification based on machine vision and deep learning are used to perform target detection on container dangerous goods signs in image data and identify types based on features. Background technique [0002] The "International Maritime Dangerous Goods Code", referred to as "International Dangerous Goods Code" (IMDG Code), is an expert working group appointed by the Maritime Safety Committee (MSC) of the International Maritime Organization to form an expert working group from countries that are very experienced in maritime dangerous goods. The provisions of Chapter VII were prepared in close cooperation with the United Nations Committee of Experts on the Transport of Dangerous Goods. Dangerous goods labels are affixed to the container surface to indicate the physical and chemical properties of dangerous goods, as well as si...

AI Technical Summary

Problems solved by technology

The work of identifying dangerous goods marks in the prior art is basically the same. Using identification methods such as radio frequency technology or sensor technology not only has low efficiency and high false detection rate, but also requires harsh equipment for the environment. The detection of dangerous goods marks only stays in the detection range. on the basis of nothing

[0003] Most traditional container terminals use manual intervention to operate. Low operating efficiency, low safety guarantee for tally staff, and high error rate are all problems of traditional container terminals.

Errors caused by manual recording methods increase the burden of repeated processing on the system, leading to a decline in the service level of the terminal, which not only affects the living environment of the terminal itself, but also causes large economic losses for import and export enterprises in the area covered by the terminal

Images