LEHP-DETR: A model with backbone improved and hybrid encoding innovated for flax capsule detection
文献类型： 外文期刊
作者： Wang, Changshun 1 ; Han, Junying 1 ; Liu, Chengzhong 1 ; Zhang, Jianping 2 ; Qi, Yanni 2 ;
作者机构： 1.Gansu Agr Univ, Coll Informat Sci & Technol, Lanzhou 730000, Peoples R China
2.Gansu Acad Agr Sci, Crop Res Inst, Lanzhou 730000, Peoples R China
期刊名称：ISCIENCE （ 影响因子：4.1； 五年影响因子：4.7 ）
ISSN：
年卷期： 2025 年 28 卷 1 期
页码：
收录情况： SCI
摘要： 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 data- set 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.
- 相关文献
作者其他论文 更多>>
-
Vis-NIR and NIR hyperspectral imaging combined with convolutional neural network with attention module for flaxseed varieties identification
作者：Zhu, Dongyu;Han, Junying;Liu, Chengzhong;Zhang, Jianping;Qi, Yanni
关键词：Hyperspectral imaging; Flaxseed; Identification; Convolutional neural network; Channel attention and transformer modules
-
Real-Time Corn Variety Recognition Using an Efficient DenXt Architecture with Lightweight Optimizations
作者：Zhao, Jin;Liu, Chengzhong;Han, Junying;Zhang, Linzhe;Zhou, Yuqian;Li, Yongsheng
关键词：at nodulation; corn plant; image classification; deep learning; DenseNet 121
-
Genome-Wide Identification and Expression Profiling of Dehydration-Responsive Element-Binding Family Genes in Flax (Linum usitatissimum L.)
作者：Wang, Yan;Niu, Yamin;Lu, Nan;Hu, Zuyu;Liu, Zigang;Zhang, Jianping;Wang, Yan;Qi, Yanni;Wang, Limin;Xu, Chenmeng;Li, Wenjuan;Dang, Zhao;Zhao, Wei;Wang, Ping;Xie, Yaping;Niu, Yamin;Lu, Nan;Hu, Zuyu;Zhang, Jianping;Liu, Zigang
关键词：flax;
DREB ; transcription factors; abiotic stress; expression analysis -
Genetic analysis and identification of major locus and candidate genes linked to thousand-seed weight in flax (Linum usitatissimum)
作者：Qi, Yanni;Wang, Limin;Li, Wenjuan;Dang, Zhao;Zhao, Wei;Wang, Ping;Xie, Yaping;Xu, Chenmeng;Wang, Yan;Zhang, Jianping;Wang, Wei
关键词：Flax; TSW; BSA-seq; Fine mapping; qRT-PCR
-
Potato Plant Variety Identification Study Based on Improved Swin Transformer
作者：Xing, Xue;Liu, Chengzhong;Han, Junying;Ma, Baixiong;Feng, Quan;Qi, Enfang;Qu, Yaying
关键词：deep learning; potato; Swin Transformer; convolutional neural network; variety identification
-
Flaxseed protein content prediction based on hyperspectral wavelength selection with fractional order ant colony optimization
作者：Wang, Bo;Han, Junying;Liu, Chengzhong;Zhang, Jianping;Qi, Yanni
关键词：hyperspectral imaging; wavelength selection; visible-near infrared; protein content; fractional order ant colony optimization
-
Combining Vis-NIR and NIR hyperspectral imaging techniques with a data fusion strategy for rapid and nondestructive determination of multiple nutritional qualities in flaxseed
作者：Zhu, Dongyu;Han, Junying;Liu, Chengzhong;Zhang, Jianping;Qi, Yanni
关键词：Hyperspectral imaging; Flaxseed; Data fusion; Multiple nutritional qualities; Visualization
