跳到主要导航 跳到搜索 跳到主要内容

A Lightweight Model Solution for Aluminum Material Defect Detection at the Edge

  • Zhengzhou Chen
  • , Jinhao Liang
  • , Yueling Zhang*
  • , Jiangtao Wang*
  • , Qing Zhang
  • , Gang Xu
  • *此作品的通讯作者
  • East China Normal University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Defect detection models have been widely applied in industrial edge platform. However, in the field of aluminum material defect detection still have some challenges: (i) limited availability of aluminum material defect datasets and (ii) the high computational cost associated with large-scale models. To address these challenges, we propose a novel lightweight model for aluminum material defect detection. For the first challenge, we propose Positive Sample Augmentation(PSA) to effectively increase the number of samples. Additionally, we employ model pruning, knowledge distillation and model quantization to reduce inference latency and model size. We have successfully deployed this solution on real-world industrial platforms, double the running speed and reduce approximately 75% hardware costs, thereby validating the feasibility of our approach.

源语言英语
主期刊名2024 IEEE 14th International Symposium on Industrial Embedded Systems, SIES 2024
出版商Institute of Electrical and Electronics Engineers Inc.
页164-171
页数8
ISBN(电子版)9798350388633
DOI
出版状态已出版 - 2024
活动14th IEEE International Symposium on Industrial Embedded Systems, SIES 2024 - Chengdu, 中国
期限: 23 10月 2024 → 25 10月 2024

丛书

姓名2024 IEEE 14th International Symposium on Industrial Embedded Systems, SIES 2024

会议

会议14th IEEE International Symposium on Industrial Embedded Systems, SIES 2024
国家/地区中国
市Chengdu
时期23/10/24 → 25/10/24

学术指纹

探究 'A Lightweight Model Solution for Aluminum Material Defect Detection at the Edge' 的科研主题。它们共同构成独一无二的学术指纹。

引用此