Detecting Algorithm based on the Improved YOLOv8s for a Weak Feature Defect of Aviation Clamps Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.62051/ijmee.v4n3.03
There are some weak defects on the surface of aviation clamps. Because they are very weak, it is difficult to identify them efficiently and accurately by the existing visual detecting algorithms, and the existing methods have high arithmetic power requirements for vision detecting systems. So, this work proposes a detecting algorithm for a weak feature defect detection of aviation clamps (YOLO-OGS). Firstly, in order to improve the ability of convolutional operations of extract features and decrease the model's GFLOPs, the Multidimensional dynamic convolutional ODConv is added to the backbone network of YOLOv8. Then, in order to reduce the complexity of the model while increasing the effectiveness of feature fusion at various levels by keeping more of the hidden connections in the channels, the GhostSlimFPN paradigm network structure, which contains GSConv convolution and slim-neck structure, is introduced in the neck network. Finally, the Shuffle Attention module is used to widen the image's sensory field and enhance the details of weak flaws. Based on the aviation clamp defect data set, the comparative analysis results of YOLO-OGS and YOLOv8s algorithms show that YOLO-OGS decreases the GFLOPs by 14.4% and increases precision, recall, [email protected], and GFLOPs by 4%, 6.4%, and 3.4%, respectively. And compared with the other existing mainstream networks YOLOv6, YOLOv8s, YOLOv8n, YOLOv5n, YOLOv5s, YOLOv7, YOLOv3-tiny. 8.3%, 3.4%, 4.4%, 15.4%, 8%, 13.4%, and 12% improvement in [email protected].
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.62051/ijmee.v4n3.03
- https://wepub.org/index.php/IJMEE/article/download/5046/5586
- OA Status
- diamond
- References
- 33
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4410728864