Rapid and accurate detection of peanut pod appearance quality based on lightweight and improved YOLOv5_SSE model
The results underscore the superiority of the SSE-YOLOv5s model, which achieves a maximum mAP of 99.3% with a minimal model size of 1. 1MB and a peak FPS of 192.3. This optimized network model excels in rapidly, efficiently, and accurately detecting the appearance quality of mixed multi-target peanut pods, making it suitable for deployment on embedded devices. This study provides an essential reference for multi-target appearance quality inspection of peanut pods.
Authors
- Fei He (ORCID: https://orcid.org/0000-0002-6003-6764)
- Dexu Yang
- X. Zhong (ORCID: https://orcid.org/0009-0005-4860-5441)
- Chunyu Wang (ORCID: https://orcid.org/0000-0003-1629-0885)
- Guozhen Wu (ORCID: https://orcid.org/0000-0002-9067-3713)
- Zhixia Liu (ORCID: https://orcid.org/0009-0009-3852-8234)
- Jing Wang (ORCID: https://orcid.org/0009-0003-3994-9512)
Institutions
- Shenyang Agricultural University (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-02-20
- DOI
- https://doi.org/10.3389/fpls.2025.1494688
- Citations
- 2
- Primary Topic
- Industrial Vision Systems and Defect Detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48