In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at pic...In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at picking automation,existing studies focus on visual detection of 1L1B,but algorithm validation is limited to a specific variety of tea sprouting in a certain harvest season at a certain location,which limits the engineering application of developed tea picking robots working in various natural tea fields.To address this gap,a deep learning model DMT(detecting multispecies of tea)based on YOLOX-S was proposed in this paper.The DMT network takes YOLOX-S as a baseline and adds ECA-Net to the CSP Darknet and FPN of YOLOX-S.The average precision(AP),precision,and recall of DMT are 94.23%,93.39%,and 88.02%,respectively,for detecting 1L1B sprouting in spring;93.92%,93.56%,and 87.88%,respectively,for detecting 1L1Bsprouting in autumn.These experimental results are better than those of the five current object detection models.After fine-tuning the DMT network with another dataset composed of multiple tea varieties,the DMT network can detect 1L1B for different varieties of tea in multiple picking seasons.The results can promote the engineering application of picking automation of fresh tea leaves.展开更多
利用遥感技术快速准确地提取耕地信息是耕地保护的关键环节。以山东省商河县为例,提出了一种基于多季相分形特征的Landsat 8 OLI影像耕地信息提取方法。首先采用毯子覆盖法计算多季相遥感影像每个像元的上分形信号和下分形信号,对比分...利用遥感技术快速准确地提取耕地信息是耕地保护的关键环节。以山东省商河县为例,提出了一种基于多季相分形特征的Landsat 8 OLI影像耕地信息提取方法。首先采用毯子覆盖法计算多季相遥感影像每个像元的上分形信号和下分形信号,对比分析耕地和其他土地利用类型的分形特征,选取上分形信号的第3尺度作为特征尺度,提取商河县耕地空间分布特征;其次采用同时期的土地利用矢量数据、Esri land cover数据和统计数据进行耕地信息提取精度评价;最后分别设置多季相分形提取与单季相分形提取、现有土地利用数据产品的对比实验,并基于点位匹配度和面积匹配度进行评价。结果表明:多季相数据更能反映农作物生长的复杂性,有助于提高耕地信息的提取精度;不同土地利用类型在不同分形尺度的信号值各不相同,分形特征可以在不同尺度上清晰地刻画出不同土地利用类型的分异性;基于矢量数据和Esri land cover数据评价的多季相分形特征耕地提取点位匹配度为87.13%和89.83%,面积匹配度为99.73%和97.91%,均比单季相分形提取结果精度高;综合考虑点位匹配度、面积匹配度和空间分布特征,研发方法能有效区分耕地和其他土地利用类型,提取结果更优,且与统计数据有更高的一致性。该方法可准确提取耕地信息,为耕地的动态监测和损害评估提供技术支撑。展开更多
Bituminous materials are heat-sensitive, and their mechanical properties vary with temperature. This variation in properties is not without consequences on the performance of flexible road structures under the repeate...Bituminous materials are heat-sensitive, and their mechanical properties vary with temperature. This variation in properties is not without consequences on the performance of flexible road structures under the repeated passage of multi-axles. This study determines the influence of seasonal variations on the rate of permanent deformation, the rut depth of flexible pavements and the effect of alternating loading of heavy goods vehicles following the temperature variations on the durability of roads. Thus, an ambient and pavement surface temperature measurement was carried out in 2022. The temperature profile at different layers of the modelled pavement, the evaluation of deformation rates and rutting depth were determined using several models. The results show that the permanent deformation and rutting rates are higher at the level of the bituminous concrete layer than at the level of the asphalt gravel layer because the stresses decrease from the surface to the depth of the pavement. On the other hand, the variations in these rates, permanent deformations and ruts between the hot and so-called cold periods are more pronounced in the bitumen gravel than in bituminous concrete, showing that gravel bitumen is more sensitive to temperature variations than bituminous concrete despite its higher rigidity. Of these results, we suggested a periodic and alternating loading of the different types of heavy goods vehicles. These loads consist of fully applying the WAEMU standards with a tolerance of 15% during periods of high and low temperatures. This regulation has increased 2 to 3 times in the durability of roadways depending on the type of heavy goods vehicle.展开更多
基金the National Natural Science Foundation of China(Grants No.U23A20175No.52305289)+1 种基金“Pioneer”and“Leading Goose”R&D Program of Zhejiang(Grant No.2022C02052)China Agriculture Research System of MOF and MARA and Basic.
文摘In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at picking automation,existing studies focus on visual detection of 1L1B,but algorithm validation is limited to a specific variety of tea sprouting in a certain harvest season at a certain location,which limits the engineering application of developed tea picking robots working in various natural tea fields.To address this gap,a deep learning model DMT(detecting multispecies of tea)based on YOLOX-S was proposed in this paper.The DMT network takes YOLOX-S as a baseline and adds ECA-Net to the CSP Darknet and FPN of YOLOX-S.The average precision(AP),precision,and recall of DMT are 94.23%,93.39%,and 88.02%,respectively,for detecting 1L1B sprouting in spring;93.92%,93.56%,and 87.88%,respectively,for detecting 1L1Bsprouting in autumn.These experimental results are better than those of the five current object detection models.After fine-tuning the DMT network with another dataset composed of multiple tea varieties,the DMT network can detect 1L1B for different varieties of tea in multiple picking seasons.The results can promote the engineering application of picking automation of fresh tea leaves.
文摘利用遥感技术快速准确地提取耕地信息是耕地保护的关键环节。以山东省商河县为例,提出了一种基于多季相分形特征的Landsat 8 OLI影像耕地信息提取方法。首先采用毯子覆盖法计算多季相遥感影像每个像元的上分形信号和下分形信号,对比分析耕地和其他土地利用类型的分形特征,选取上分形信号的第3尺度作为特征尺度,提取商河县耕地空间分布特征;其次采用同时期的土地利用矢量数据、Esri land cover数据和统计数据进行耕地信息提取精度评价;最后分别设置多季相分形提取与单季相分形提取、现有土地利用数据产品的对比实验,并基于点位匹配度和面积匹配度进行评价。结果表明:多季相数据更能反映农作物生长的复杂性,有助于提高耕地信息的提取精度;不同土地利用类型在不同分形尺度的信号值各不相同,分形特征可以在不同尺度上清晰地刻画出不同土地利用类型的分异性;基于矢量数据和Esri land cover数据评价的多季相分形特征耕地提取点位匹配度为87.13%和89.83%,面积匹配度为99.73%和97.91%,均比单季相分形提取结果精度高;综合考虑点位匹配度、面积匹配度和空间分布特征,研发方法能有效区分耕地和其他土地利用类型,提取结果更优,且与统计数据有更高的一致性。该方法可准确提取耕地信息,为耕地的动态监测和损害评估提供技术支撑。
文摘Bituminous materials are heat-sensitive, and their mechanical properties vary with temperature. This variation in properties is not without consequences on the performance of flexible road structures under the repeated passage of multi-axles. This study determines the influence of seasonal variations on the rate of permanent deformation, the rut depth of flexible pavements and the effect of alternating loading of heavy goods vehicles following the temperature variations on the durability of roads. Thus, an ambient and pavement surface temperature measurement was carried out in 2022. The temperature profile at different layers of the modelled pavement, the evaluation of deformation rates and rutting depth were determined using several models. The results show that the permanent deformation and rutting rates are higher at the level of the bituminous concrete layer than at the level of the asphalt gravel layer because the stresses decrease from the surface to the depth of the pavement. On the other hand, the variations in these rates, permanent deformations and ruts between the hot and so-called cold periods are more pronounced in the bitumen gravel than in bituminous concrete, showing that gravel bitumen is more sensitive to temperature variations than bituminous concrete despite its higher rigidity. Of these results, we suggested a periodic and alternating loading of the different types of heavy goods vehicles. These loads consist of fully applying the WAEMU standards with a tolerance of 15% during periods of high and low temperatures. This regulation has increased 2 to 3 times in the durability of roadways depending on the type of heavy goods vehicle.
