Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features
To address the challenges of insufficient accuracy in detecting tomato disease object detection caused by dense target distributions, large-scale variations, and poor feature information of small objects in complex backgrounds, this study proposes the tomato disease object detection method that inte...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1255119/full |
| _version_ | 1797663327214632960 |
|---|---|
| author | Jun Liu Xuewei Wang |
| author_facet | Jun Liu Xuewei Wang |
| author_sort | Jun Liu |
| collection | DOAJ |
| description | To address the challenges of insufficient accuracy in detecting tomato disease object detection caused by dense target distributions, large-scale variations, and poor feature information of small objects in complex backgrounds, this study proposes the tomato disease object detection method that integrates prior knowledge attention mechanism and multi-scale features (PKAMMF). Firstly, the visual features of tomato disease images are fused with prior knowledge through the prior knowledge attention mechanism to obtain enhanced visual features corresponding to tomato diseases. Secondly, a new feature fusion layer is constructed in the Neck section to reduce feature loss. Furthermore, a specialized prediction layer specifically designed to improve the model’s ability to detect small targets is incorporated. Finally, a new loss function known as A-SIOU (Adaptive Structured IoU) is employed to optimize the performance of the model in terms of bounding box regression. The experimental results on the self-built tomato disease dataset demonstrate the effectiveness of the proposed approach, and it achieves a mean average precision (mAP) of 91.96%, which is a 3.86% improvement compared to baseline methods. The results show significant improvements in the detection performance of multi-scale tomato disease objects. |
| first_indexed | 2024-03-11T19:12:54Z |
| format | Article |
| id | doaj.art-37a786ccab8f4a389938521d04255a2d |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-11T19:12:54Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-37a786ccab8f4a389938521d04255a2d2023-10-09T10:16:25ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-10-011410.3389/fpls.2023.12551191255119Tomato disease object detection method combining prior knowledge attention mechanism and multiscale featuresJun LiuXuewei WangTo address the challenges of insufficient accuracy in detecting tomato disease object detection caused by dense target distributions, large-scale variations, and poor feature information of small objects in complex backgrounds, this study proposes the tomato disease object detection method that integrates prior knowledge attention mechanism and multi-scale features (PKAMMF). Firstly, the visual features of tomato disease images are fused with prior knowledge through the prior knowledge attention mechanism to obtain enhanced visual features corresponding to tomato diseases. Secondly, a new feature fusion layer is constructed in the Neck section to reduce feature loss. Furthermore, a specialized prediction layer specifically designed to improve the model’s ability to detect small targets is incorporated. Finally, a new loss function known as A-SIOU (Adaptive Structured IoU) is employed to optimize the performance of the model in terms of bounding box regression. The experimental results on the self-built tomato disease dataset demonstrate the effectiveness of the proposed approach, and it achieves a mean average precision (mAP) of 91.96%, which is a 3.86% improvement compared to baseline methods. The results show significant improvements in the detection performance of multi-scale tomato disease objects.https://www.frontiersin.org/articles/10.3389/fpls.2023.1255119/fullcomplex backgroundtomato diseasesprior knowledgeattention mechanismmulti-scale featuresobject detection |
| spellingShingle | Jun Liu Xuewei Wang Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features Frontiers in Plant Science complex background tomato diseases prior knowledge attention mechanism multi-scale features object detection |
| title | Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| title_full | Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| title_fullStr | Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| title_full_unstemmed | Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| title_short | Tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| title_sort | tomato disease object detection method combining prior knowledge attention mechanism and multiscale features |
| topic | complex background tomato diseases prior knowledge attention mechanism multi-scale features object detection |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1255119/full |
| work_keys_str_mv | AT junliu tomatodiseaseobjectdetectionmethodcombiningpriorknowledgeattentionmechanismandmultiscalefeatures AT xueweiwang tomatodiseaseobjectdetectionmethodcombiningpriorknowledgeattentionmechanismandmultiscalefeatures |