Surface defect detection of hot rolled steel based on attention mechanism and dilated convolution for industrial robots

Yuanfan Yu, Sixian Chan, Tinglong Tang, Xiaolong Zhou, Yuan Yao, Hongkai Zhang

Research output: Journal PublicationArticlepeer-review

3 Citations (Scopus)

Abstract

In the manufacturing process of industrial robots, the defect detection of raw materials includes two types of tasks, which makes the defect detection guarantee its accuracy. It also makes the defect detection task challenging in practical work. In analyzing the disadvantages of the existing defect detection task methods, such as low precision and low generalization ability, a detection method on the basis of attention mechanism and dilated convolution module is proposed. In order to effectively extract features, a two-stage detection framework is chosen by applying Resnet50 as the pre-training network of our model. With this foundation, the attention mechanism and dilated convolution are utilized. With the attention mechanism, the network can focus on the features of effective regions and suppress the invalid regions during detection. With dilated convolution, the receptive field of the model can be increased without increasing the calculation amount of the model. As a result, it can achieve a larger receptive field, which will obtain more dense data and improve the detection effect of small target defects. Finally, great experiments are conducted on the NEU-DET dataset. Compared with the baseline network, the proposed method in this paper achieves 81.79% mAP, which are better results.
Original languageEnglish
Article number1856
Number of pages13
JournalElectronics
Volume12
Issue number8
DOIs
Publication statusPublished - 14 Apr 2023

Keywords

  • deep learning
  • defect detection;
  • attention mechanism
  • dilated convolution

Fingerprint

Dive into the research topics of 'Surface defect detection of hot rolled steel based on attention mechanism and dilated convolution for industrial robots'. Together they form a unique fingerprint.

Cite this