A Detection Method for Crop Diseases and Pests Based on Improved YOLOv7
With the rapid advancement of science and technology, artificial intelligence (AI) and machine learning (ML) have been widely applied in agriculture. To tackle challenges in crop disease and pest identification-such as diverse species, subtle inter-class feature differences, and significant intra-cl...
Saved in:
| Published in: | IAENG international journal of computer science Vol. 52; no. 9; p. 3327 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Hong Kong
International Association of Engineers
01.09.2025
|
| Subjects: | |
| ISSN: | 1819-656X, 1819-9224 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With the rapid advancement of science and technology, artificial intelligence (AI) and machine learning (ML) have been widely applied in agriculture. To tackle challenges in crop disease and pest identification-such as diverse species, subtle inter-class feature differences, and significant intra-class variations across crop growth stages-an improved YOLOv7 (IP-YOLOv7) object detection algorithm integrated with a hybrid attention mechanism is proposed. By incorporating the hybrid attention module into the backbone network of YOLOv7, the algorithm enhances its capability to learn pathological features and focuses more effectively on small-scale effective feature regions of crop leaves, thereby improving the identification accuracy of YOLOv7 for various crop diseases and pests. Experimental results demonstrate that YOLOv7 achieves a mean average precision (mAP) of 95.17%, while IP-YOLOv7 reaches 97.35% in crop disease and pest detection, indicating high accuracy and robustness of IP-YOLOv7 in this task. |
|---|---|
| Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ISSN: | 1819-656X 1819-9224 |