Furnace mouth image preprocessing method

Abstract

The invention provides a furnace mouth image preprocessing method. The method includes acquiring the furnace mouth flame image and removing the invalid regions on the periphery of the furnace mouth flame image to obtain an initial ROI; detecting the initial ROI and judging whether the invalid region with the longitudinal penetration exists or not; if the invalid region with the longitudinal penetration exists, segmenting the initial ROI into a plurality of sub-graphs; and removing the invalid sub-graphs in the sub-graphs to accurately extract the ROI. For the problem of image noise caused by the shielding of a furnace mouth area by a fireproofing door and a smoke cover under the complex light condition of a converter working site, the various irrelevant content and interferent objects canbe removed, and an effective ROI can be obtained, the recognition accuracy of the state of the converter can be obviously improved, the method has the advantages of being easy to realize and small incalculation amount, the requirements of real-time performance processing can be met, and the effectiveness of input images in the depth learning model can be guaranteed.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a furnace mouth image preprocessing method. Background technique [0002] The converter is prone to splashing during the blowing process, which is mainly manifested as slag jumping inside the furnace mouth, and slag and metal overflow or ejection outside the furnace mouth. In the actual production process, the lance operator will make a comprehensive judgment based on the converter splash state observed in the furnace mouth area and various blowing parameters, so as to choose to increase or decrease the oxygen lance position or add various auxiliary materials. [0003] As the key parameter of the oxygen lance control, the splash state of the converter plays a pivotal role in the automatic steelmaking process. The current rise of deep learning also provides a powerful tool for the recognition of the splash state of the converter. However, due to the harsh space environment and com...

AI Technical Summary

Problems solved by technology

The current rise of deep learning also provides a powerful tool for the recognition of the splash state of the converter. However, due to the harsh space environment and complex light conditions in the iron and steel industry site, there is a lot of noise in the acquired image. At the same time, the fire doors and smoke hoods outside the converter are also It will seriously block the furnace mouth area, so how to eliminate irrelevant information in the image, enhance the detectability of relevant information and simplify the data to the greatest extent is the basis of image classification

[0004] However, there is currently no effective method for image processing of the converter mouth, so a new technical means is urgently needed to remove all kinds of irrelevant content and interference, so as to obtain an effective ROI (region of interest, sensory image). region of interest) to ensure the validity of the input image in the deep learning model

Images