TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms
Currently, intelligent pest monitoring systems transmit entire monitoring images to cloud servers for analysis. This approach not only consumes significant bandwidth and increases monitoring costs, but also struggles with accurately recognizing small-target and overlapping pests. To overcome these c...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/6/4/268 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846106381549043712 |
|---|---|
| author | Junlin Mu Linlin Sun Bo Ma Ruofei Liu Shuangxi Liu Xianliang Hu Hongjian Zhang Jinxing Wang |
| author_facet | Junlin Mu Linlin Sun Bo Ma Ruofei Liu Shuangxi Liu Xianliang Hu Hongjian Zhang Jinxing Wang |
| author_sort | Junlin Mu |
| collection | DOAJ |
| description | Currently, intelligent pest monitoring systems transmit entire monitoring images to cloud servers for analysis. This approach not only consumes significant bandwidth and increases monitoring costs, but also struggles with accurately recognizing small-target and overlapping pests. To overcome these challenges, this paper introduces a two-stage multi-feature fusion small-target pest detection algorithm based on edge computing devices, termed TFEMRNet. The algorithm initially conducts semantic segmentation on an edge processor, followed by uploading the segmented images to a cloud server for target identification. Specifically, the semantic segmentation model TFENet incorporates a Multi-Attention Channel Aggregation (MACA) module, which integrates semantic features from EfficientNet-Pest and Swin Transformer, thereby enhancing the model’s ability to extract features of small-target pests. Experimental results demonstrate that TFEMRNet surpasses models such as YOLOv11, Fast R-CNN, and Mask R-CNN on small-target pest datasets, achieving precision of 96.75%, recall of 96.45%, and an F1 score of 95.60%. Notably, the TFENet model within TFEMRNet attains an IoU of 91.63% in semantic segmentation accuracy, outperforming other segmentation models such as U-Net and PSPNet. These findings affirm TFEMRNet’s superior efficacy in small-target pest detection, offering an effective solution for agricultural pest monitoring. |
| format | Article |
| id | doaj-art-e8a0575c15a54dc0ae61a4440fc24fd7 |
| institution | Kabale University |
| issn | 2624-7402 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj-art-e8a0575c15a54dc0ae61a4440fc24fd72024-12-27T14:03:44ZengMDPI AGAgriEngineering2624-74022024-12-01644688470310.3390/agriengineering6040268TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge PlatformsJunlin Mu0Linlin Sun1Bo Ma2Ruofei Liu3Shuangxi Liu4Xianliang Hu5Hongjian Zhang6Jinxing Wang7College of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaShandong Xiangchen Technology Group Co., Ltd., Jinan 250000, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCurrently, intelligent pest monitoring systems transmit entire monitoring images to cloud servers for analysis. This approach not only consumes significant bandwidth and increases monitoring costs, but also struggles with accurately recognizing small-target and overlapping pests. To overcome these challenges, this paper introduces a two-stage multi-feature fusion small-target pest detection algorithm based on edge computing devices, termed TFEMRNet. The algorithm initially conducts semantic segmentation on an edge processor, followed by uploading the segmented images to a cloud server for target identification. Specifically, the semantic segmentation model TFENet incorporates a Multi-Attention Channel Aggregation (MACA) module, which integrates semantic features from EfficientNet-Pest and Swin Transformer, thereby enhancing the model’s ability to extract features of small-target pests. Experimental results demonstrate that TFEMRNet surpasses models such as YOLOv11, Fast R-CNN, and Mask R-CNN on small-target pest datasets, achieving precision of 96.75%, recall of 96.45%, and an F1 score of 95.60%. Notably, the TFENet model within TFEMRNet attains an IoU of 91.63% in semantic segmentation accuracy, outperforming other segmentation models such as U-Net and PSPNet. These findings affirm TFEMRNet’s superior efficacy in small-target pest detection, offering an effective solution for agricultural pest monitoring.https://www.mdpi.com/2624-7402/6/4/268pest identificationtiny object recognitionmulti-stage detection approachedge-based processingfeature integration |
| spellingShingle | Junlin Mu Linlin Sun Bo Ma Ruofei Liu Shuangxi Liu Xianliang Hu Hongjian Zhang Jinxing Wang TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms AgriEngineering pest identification tiny object recognition multi-stage detection approach edge-based processing feature integration |
| title | TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms |
| title_full | TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms |
| title_fullStr | TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms |
| title_full_unstemmed | TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms |
| title_short | TFEMRNet: A Two-Stage Multi-Feature Fusion Model for Efficient Small Pest Detection on Edge Platforms |
| title_sort | tfemrnet a two stage multi feature fusion model for efficient small pest detection on edge platforms |
| topic | pest identification tiny object recognition multi-stage detection approach edge-based processing feature integration |
| url | https://www.mdpi.com/2624-7402/6/4/268 |
| work_keys_str_mv | AT junlinmu tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT linlinsun tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT boma tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT ruofeiliu tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT shuangxiliu tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT xianlianghu tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT hongjianzhang tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms AT jinxingwang tfemrnetatwostagemultifeaturefusionmodelforefficientsmallpestdetectiononedgeplatforms |