LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection
Summary: Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of c...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004224027858 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545926872662016 |
|---|---|
| author | Changshun Wang Junying Han Chengzhong Liu Jianping Zhang Yanni Qi |
| author_facet | Changshun Wang Junying Han Chengzhong Liu Jianping Zhang Yanni Qi |
| author_sort | Changshun Wang |
| collection | DOAJ |
| description | Summary: Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of computer vision and deep learning techniques offers a new way to solve this problem. In this study, based on RT-DETR, we introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR. Experimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model. Compared to the base model, LEHP-DETR reduces the number of parameters by 67.3%, the model size by 66.3%, and the FLOPs by 37.6%. the average detection accuracy mAP50 and mAP50:95 increased by 2.6% and 3.5%, respectively. |
| format | Article |
| id | doaj-art-a513111969c74c429832bde38a1b9b21 |
| institution | Kabale University |
| issn | 2589-0042 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj-art-a513111969c74c429832bde38a1b9b212025-01-11T06:41:48ZengElsevieriScience2589-00422025-01-01281111558LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detectionChangshun Wang0Junying Han1Chengzhong Liu2Jianping Zhang3Yanni Qi4College of Information Science and Technology, Gansu Agricultural University, Lanzhou 730000, ChinaCollege of Information Science and Technology, Gansu Agricultural University, Lanzhou 730000, China; Corresponding authorCollege of Information Science and Technology, Gansu Agricultural University, Lanzhou 730000, ChinaCrop Research Institute, Gansu Academy of Agricultural Sciences, Lanzhou 730000, ChinaCrop Research Institute, Gansu Academy of Agricultural Sciences, Lanzhou 730000, ChinaSummary: Flax, as a functional crop with rich essential fatty acids and nutrients, is important in nutrition and industrial applications. However, the current process of flax seed detection relies mainly on manual operation, which is not only inefficient but also prone to error. The development of computer vision and deep learning techniques offers a new way to solve this problem. In this study, based on RT-DETR, we introduced the RepNCSPELAN4 module, ADown module, Context Aggregation module, and TFE module, and designed the HWD-ADown module, HiLo-AIFI module, and DSSFF module, and proposed an improved model, called LEHP-DETR. Experimental results show that LEHP-DETR achieves significant performance improvement on the flax dataset and comprehensively outperforms the comparison model. Compared to the base model, LEHP-DETR reduces the number of parameters by 67.3%, the model size by 66.3%, and the FLOPs by 37.6%. the average detection accuracy mAP50 and mAP50:95 increased by 2.6% and 3.5%, respectively.http://www.sciencedirect.com/science/article/pii/S2589004224027858BioinformaticsPlant biologyAgricultural science |
| spellingShingle | Changshun Wang Junying Han Chengzhong Liu Jianping Zhang Yanni Qi LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection iScience Bioinformatics Plant biology Agricultural science |
| title | LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection |
| title_full | LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection |
| title_fullStr | LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection |
| title_full_unstemmed | LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection |
| title_short | LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection |
| title_sort | lehp detr a model with backbone improved and hybrid encoding innovated for flax capsule detection |
| topic | Bioinformatics Plant biology Agricultural science |
| url | http://www.sciencedirect.com/science/article/pii/S2589004224027858 |
| work_keys_str_mv | AT changshunwang lehpdetramodelwithbackboneimprovedandhybridencodinginnovatedforflaxcapsuledetection AT junyinghan lehpdetramodelwithbackboneimprovedandhybridencodinginnovatedforflaxcapsuledetection AT chengzhongliu lehpdetramodelwithbackboneimprovedandhybridencodinginnovatedforflaxcapsuledetection AT jianpingzhang lehpdetramodelwithbackboneimprovedandhybridencodinginnovatedforflaxcapsuledetection AT yanniqi lehpdetramodelwithbackboneimprovedandhybridencodinginnovatedforflaxcapsuledetection |