In order to avoid the uneven phenomenon of sugarcane planting,such as seed missing and reseeding,the computervision technology was applied to the intelligent identification of sugarcane varieties with single-bud segme...In order to avoid the uneven phenomenon of sugarcane planting,such as seed missing and reseeding,the computervision technology was applied to the intelligent identification of sugarcane varieties with single-bud segment,and the designidea of rapid detection of sugarcane planting distribution was proposed in this study.With sugarcane species with single-budsegment as the research object,the sugarcane species distribution image was acquired,and LabelImg was used for imageannotation and format conversion to build the YOLOv5s target detection model.On the basis of depth-separable convolution,SE module is spliced to obtain the weights of extracted features and extract key features of input feature map.By addingregularization to constrain the BN layer coefficient,sparse regularization is carried out on the BN layer to reduce the networkinput size and improve the model training speed.On this basis,600 rounds of iterative training were carried out to complete thetarget recognition of sugarcane species characteristics in single-bud segment.The results showed that the recognition accuracy,mAP value,and Recall value of YOLOv5s single-bud segment target detection model are 98.95%,98.89%,and 98.69%,andthe loss value converges in advance between 0-0.02.The results showed that YOLOv5s could effectively detect and identifysugarcane seeds with single-bud segment during field planting,which lays a foundation for promoting precise and intelligentsugarcane planting.展开更多
Sugarcane mechanized planting technology consists of seed preparation and field planting.This study aims at the issues of easy damage to the seeds during the operation of the automatic cutting machine for single-bud s...Sugarcane mechanized planting technology consists of seed preparation and field planting.This study aims at the issues of easy damage to the seeds during the operation of the automatic cutting machine for single-bud segment sugarcane,lack of intelligent seed selection and calibration technology,low recognition accuracy,and the need for manual feeding of the planting machine’s seed meter which leads to seed leakage.This study,based on machine vision and deep learning,optimizes the seed calibration method and proposes an improved YoloV5-STD target detection algorithm to improve the recognition accuracy of seed characteristics and optimize the overall engineering structure.For the planting machine,a new type of hopper for the seed meter is designed using natural rubber as the base material mixed with polystyrene,and the flexible automatic seed metering mechanism is analyzed to achieve automatic feeding and seed metering.Test assessment indicators were formulated based on the enterprise standards of the Institute of Agricultural Machinery Research,Chinese Academy of Tropical Agricultural Sciences.Experimental results show that the recognition accuracy of the 2DZ-2 type single-bud segment intelligent cutting machine is≥95%,the bud injury rate is<1.8%,the qualified rate of cutting is 95.8%,and the single-channel cutting efficiency is 64 buds/min.The 2CZD-2C type single-bud segment planter has a planting qualification rate of 96.6%,a planting efficiency of 208 buds/min,and a seed leakage rate of<2.1%.展开更多
Mechanized sugarcane seeding is one of the effective technical measures for improving seeding uniformity and operation efficiency.However,the imperfection of supporting equipment limits the promotion and application o...Mechanized sugarcane seeding is one of the effective technical measures for improving seeding uniformity and operation efficiency.However,the imperfection of supporting equipment limits the promotion and application of this technology.As there are some problems in domestic sugarcane planting machines currently,such as large auxiliary labor,high labor intensity,low seeding uniformity,and large amount of seeds,a disc-type single-bud sugarcane seed metering device was innovatively designed on the basis of the analysis of physical properties of single-bud sugarcane seeds and the combination with agronomic requirements for field planting in this paper.Solidworks was used to simulate and analyze the mechanism,check the theoretical parameters,and process the test prototype.Through single-factor experiments,the effective factors affecting seeding uniformity were determined.A multi-factor orthogonal rotation test was designed,data were collected and then SPSS was used to get the optimal parameters for the seeding uniformity:the advancement speed of machine is 0.22 m/s,the number of disc seeding grooves is 10,the rotating disc speed is 0.18 r/s,and the seeding uniformity is 86.2%;the seeding uniformity was verified by field trial,and the results showed that the average seeding uniformity of the field verification was 83%,with the error 3.2% relative to the optimization result.The relative error is within 10%,indicating that the optimization result is reliable and meets the requirements of seeding uniformity,thus providing theoretical basis for the research and development of the disc-type single-bud seeding device.展开更多
基金financially supported by the Research Funds for the South Asian Tropical Crop Research Institute of the Chinese Academy of Tropical Agricultural Sciences(Grant No.1630062025008)the Project of Guangxi Zhuang Autonomous Region Key Technologies R&D Program(Grant No.GK AB23026069 and GN AB241484034)+3 种基金Natural ScienceFoundation of Guangdong Province(2025A1515012901)Hot Zone Hilly Mountain Small Machinery Technology Innovation Team(Grant No.CATASCXTD202409)Hainan Provincial Natural Science Foundation(Grant No.524QN332)Fundamental Research Funds for Central Public Welfare Research Institutes(Grant No.1630062024009).
文摘In order to avoid the uneven phenomenon of sugarcane planting,such as seed missing and reseeding,the computervision technology was applied to the intelligent identification of sugarcane varieties with single-bud segment,and the designidea of rapid detection of sugarcane planting distribution was proposed in this study.With sugarcane species with single-budsegment as the research object,the sugarcane species distribution image was acquired,and LabelImg was used for imageannotation and format conversion to build the YOLOv5s target detection model.On the basis of depth-separable convolution,SE module is spliced to obtain the weights of extracted features and extract key features of input feature map.By addingregularization to constrain the BN layer coefficient,sparse regularization is carried out on the BN layer to reduce the networkinput size and improve the model training speed.On this basis,600 rounds of iterative training were carried out to complete thetarget recognition of sugarcane species characteristics in single-bud segment.The results showed that the recognition accuracy,mAP value,and Recall value of YOLOv5s single-bud segment target detection model are 98.95%,98.89%,and 98.69%,andthe loss value converges in advance between 0-0.02.The results showed that YOLOv5s could effectively detect and identifysugarcane seeds with single-bud segment during field planting,which lays a foundation for promoting precise and intelligentsugarcane planting.
基金supported by the Project of Guangxi Zhuang Autonomous Region Key Technologies R&D Program(Grant No.GK AB23026069 and GN AB241484034)the Basic Scientific Research Expenses of Central Public Welfare Scientific Research Institutes(Grant No.1630132022001)+1 种基金the Basic Scientific Research Expenses of Chinese Academy of Tropical Agricultural Sciences(Grant No.1630132024004)the Zhanjiang Science and Technology Project(Grant No.2023A01009).
文摘Sugarcane mechanized planting technology consists of seed preparation and field planting.This study aims at the issues of easy damage to the seeds during the operation of the automatic cutting machine for single-bud segment sugarcane,lack of intelligent seed selection and calibration technology,low recognition accuracy,and the need for manual feeding of the planting machine’s seed meter which leads to seed leakage.This study,based on machine vision and deep learning,optimizes the seed calibration method and proposes an improved YoloV5-STD target detection algorithm to improve the recognition accuracy of seed characteristics and optimize the overall engineering structure.For the planting machine,a new type of hopper for the seed meter is designed using natural rubber as the base material mixed with polystyrene,and the flexible automatic seed metering mechanism is analyzed to achieve automatic feeding and seed metering.Test assessment indicators were formulated based on the enterprise standards of the Institute of Agricultural Machinery Research,Chinese Academy of Tropical Agricultural Sciences.Experimental results show that the recognition accuracy of the 2DZ-2 type single-bud segment intelligent cutting machine is≥95%,the bud injury rate is<1.8%,the qualified rate of cutting is 95.8%,and the single-channel cutting efficiency is 64 buds/min.The 2CZD-2C type single-bud segment planter has a planting qualification rate of 96.6%,a planting efficiency of 208 buds/min,and a seed leakage rate of<2.1%.
基金financially supported by National Key Research and Development Project(Grant No.2017YFD0700805)Special Fund for Basic Scientific Research Business Expenses of Chinese Academy of Tropical Agricultural Sciences(Grant No.1630132022001)+2 种基金Hainan Natural Science Foundation Project(Grant No.520QN331)Zhanjiang Science and Technology Plan Project(Grant No.2021A05011 and 2021A05189)Special Topic on the Construction of Key Laboratory of Zhanjiang Science and Technology Planning Project(Grant No.2020A05004).
文摘Mechanized sugarcane seeding is one of the effective technical measures for improving seeding uniformity and operation efficiency.However,the imperfection of supporting equipment limits the promotion and application of this technology.As there are some problems in domestic sugarcane planting machines currently,such as large auxiliary labor,high labor intensity,low seeding uniformity,and large amount of seeds,a disc-type single-bud sugarcane seed metering device was innovatively designed on the basis of the analysis of physical properties of single-bud sugarcane seeds and the combination with agronomic requirements for field planting in this paper.Solidworks was used to simulate and analyze the mechanism,check the theoretical parameters,and process the test prototype.Through single-factor experiments,the effective factors affecting seeding uniformity were determined.A multi-factor orthogonal rotation test was designed,data were collected and then SPSS was used to get the optimal parameters for the seeding uniformity:the advancement speed of machine is 0.22 m/s,the number of disc seeding grooves is 10,the rotating disc speed is 0.18 r/s,and the seeding uniformity is 86.2%;the seeding uniformity was verified by field trial,and the results showed that the average seeding uniformity of the field verification was 83%,with the error 3.2% relative to the optimization result.The relative error is within 10%,indicating that the optimization result is reliable and meets the requirements of seeding uniformity,thus providing theoretical basis for the research and development of the disc-type single-bud seeding device.
