CDC-YOLO for Gear Defect Detection: Make YOLOv8 Faster and Lighter on RK3588
ID：36
Submission ID：46 View Protection：ATTENDEE
Updated Time：2024-10-23 10:51:13
Hits：47
Oral Presentation
Start Time：2024-11-01 16:40 （Asia/Shanghai）
Duration：20min
Session：[P4] Parallel Session 4 » [P4-1] Parallel Session 4（November 1 PM）
No files
Abstract
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.
Keywords
defect detection, YOLO, dual convolution, embedded platform.
Speaker
YaoJiachen
Mr. Nanjing University of Science and Technology；School of Mechanical EngineeringSubmission Author
All comments
15th August 2024 31st August 2024- Manuscript Submission
15th September 2024 - Acceptance Notification
1st October 2024 - Camera Ready Submission
1st October 2024 – Early Bird Registration
Contact Us
Website:
https://icsmd2024.aconf.org/
Comment submit