文献类型： 外文期刊
作者： Ding, Zezhong 1 ; Chen, Zhiwei 2 ; Gui, Zhiyong 2 ; Guo, Mengqi 2 ; Zhu, Xuesong 3 ; Hu, Bin 1 ; Dong, Chunwang 1 ;
作者机构： 1.Shihezi Univ, Coll Mech & Elect Engn, Shihezi 832000, Peoples R China
2.Shandong Acad Agr Sci, Tea Res Inst, Jinan 250100, Peoples R China
3.Feilanda Intelligent Technol Co Ltd, Hangzhou 311121, Peoples R China
关键词： rose tea grading; YOLOv8; attention mechanism; lightweight; SIoU
期刊名称：FOODS （ 影响因子：5.2； 五年影响因子：5.5 ）
ISSN：
年卷期： 2024 年 13 卷 8 期
页码：
收录情况： SCI
摘要： Rose tea is a type of flower tea in China's reprocessed tea category, which is divided into seven grades, including super flower, primary flower, flower bud, flower heart, yellow flower, scattered flower, and waste flower. Grading rose tea into distinct quality levels is a practice that is essential to boosting their competitive advantage. Manual grading is inefficient. We provide a lightweight model to advance rose tea grading automation. Firstly, four kinds of attention mechanisms were introduced into the backbone and compared. According to the experimental results, the Convolutional Block Attention Module (CBAM) was chosen in the end due to its ultimate capacity to enhance the overall detection performance of the model. Second, the lightweight module C2fGhost was utilized to change the original C2f module in the neck to lighten the network while maintaining detection performance. Finally, we used the SIoU loss in place of the CIoU loss to improve the boundary regression performance of the model. The results showed that the mAP, precision (P), recall (R), FPS, GFLOPs, and Params values of the proposed model were 86.16%, 89.77%, 83.01%, 166.58, 7.978, and 2.746 M, respectively. Compared with the original model, the mAP, P, and R values increased by 0.67%, 0.73%, and 0.64%, the GFLOPs and Params decreased by 0.88 and 0.411 M, respectively, and the speed was comparable. The model proposed in this study also performed better than other advanced detection models. It provides theoretical research and technical support for the intelligent grading of roses.
- 相关文献
作者其他论文 更多>>
-
Long-range infrared absorption spectroscopy and fast mass spectrometry for rapid online measurements of volatile organic compounds from black tea fermentation
作者：Yang, Chongshan;Li, Guanglin;Zhao, Chunjiang;Fu, Xinglan;Yang, Chongshan;Jiao, Leizi;Wen, Xuelin;Lin, Peng;Duan, Dandan;Zhao, Chunjiang;Dong, Daming;Yang, Chongshan;Jiao, Leizi;Wen, Xuelin;Lin, Peng;Duan, Dandan;Dong, Daming;Dong, Chunwang
关键词：Black tea fermentation; Volatile organic compounds; Proton transfer reaction mass spectrometry; Fourier transform infrared spectroscopy; Principal component analysis; Extreme learning machine
-
Predictive models for sensory score and physicochemical composition of Yuezhou Longjing tea using near-infrared spectroscopy and data fusion
作者：Chen, Yong;Guo, Mengqi;Guo, Mengqi;Ding, Zezhong;Zhang, Haowen;Lu, Min;Qi, Dandan;Dong, Chunwang;Chen, Kai;Jiang, Xinfeng
关键词：NIR; Data fusion; Physicochemical analysis; Sensory score; Model building
-
Insights into major pigment accumulation and (non)enzymatic degradations and conjugations to characterized flavors during intelligent black tea processing
作者：Zhang, Yongcheng;Mu, Dan;Wu, Yan;Yan, Kangni;Zhang, Yongcheng;Peng, Qunhua;Fu, Jianyu;Lv, Haipeng;Lin, Zhi;Shi, Jiang;Yan, Kangni;Feng, Shan;Zhao, Zhangfeng;Chen, Long;Ye, Lin;Dong, Chunwang
关键词：Intelligently processed black tea; Pigments; Carotenoids; Maillard products; Flavor
-
Small target tea bud detection based on improved YOLOv5 in complex background
作者：Wang, Mengjie;Meng, Hewei;Li, Yaping;Wang, Mengjie;Li, Yang;Chen, Zhiwei;Gui, Zhiyong;Dong, Chunwang
关键词：object detection; deep information extraction; lightweight; MPDIoU; YOLOv5; attention mechanism
-
NIR Spectral Inversion of Soil Physicochemical Properties in Tea Plantations under Different Particle Size States
作者：He, Qinghai;Li, Xiaoli;He, Qinghai;Zhang, Haowen;Zhang, Haowen;Zhang, Xiaojia;Dong, Chunwang;Zhang, Haowen;Li, Tianhua
关键词：NIR spectroscopy; soil; dimensionality reduction; support vector regression; tea garden
-
Research on the Detection Method of Organic Matter in Tea Garden Soil Based on Image Information and Hyperspectral Data Fusion
作者：Zhang, Haowen;Yang, Chongshan;Lu, Min;Liu, Zhongyuan;Zhang, Xiaojia;Dong, Chunwang;He, Qinghai;He, Qinghai;Li, Xiaoli;Dong, Chunwang
关键词：hyperspectral; machine visualization properties; data fusion; tea plantation soils; organic matter
-
Real-Time Discrimination and Quality Evaluation of Black Tea Fermentation Quality Using a Homemade Simple Machine Vision System
作者：Yang, Chongshan;An, Ting;Qi, Dandan;Yuan, Changbo;Dong, Chunwang;Yang, Chongshan;An, Ting
关键词：black tea; fermentation; machine vision; discrimination; quality evaluation
