报告详情
CDC-YOLO for Gear Defect Detection: Make YOLOv8 Faster and Lighter on RK3588
编号：36
访问权限：仅限参会人
更新：2024-10-23 10:51:13
浏览：191次
口头报告
报告开始：2024年11月01日 16:40（Asia/Shanghai）
报告时间：20min
所在会场：[P4] Parallel Session 4 [P4-1] Parallel Session 4（November 1 PM）
暂无文件
摘要
Defect detection on the gear surface is crucial for preventing faults in mechanical systems. However, most detection models are not extremely effective on embedded platforms. To address this issue, we present a lightweight detection model called CDC-YOLO, which is based on YOLOv8 and specifically designed for embedded platforms. It utilizes our proposed CDC module as a residual structure for extracting multi-scale features, allowing for better adaptation to different platforms. Additionally, we achieve model lightweighting by using a dual convolutional architecture. Experimental results on both computers and embedded platforms demonstrate that our proposed method outperforms the baseline YOLOv8.
关键词
defect detection, YOLO, dual convolution, embedded platform.
报告人
YaoJiachen
Mr. Nanjing University of Science and Technology；School of Mechanical Engineering稿件作者
全部评论
重要日期
-
会议日期
10月31日
2024
至11月03日
2024
-
09月30日 2024
初稿截稿日期
-
11月12日 2024
注册截止日期
主办单位
Anhui University
Xi’an Jiaotong University
Harbin Institute of Technology
IEEE Instrumentation & Measurement Society
Xi’an Jiaotong University
Harbin Institute of Technology
IEEE Instrumentation & Measurement Society
联系方式
- Mrs. icsmd
- ic******@163.com
发表评论