Mikania micrantha Kunth is an invasive alien weed and known as a plant killer around the world.Accurately and rapidly identifying M.micrantha in the wild is important for monitoring its growth status,as this helps man...Mikania micrantha Kunth is an invasive alien weed and known as a plant killer around the world.Accurately and rapidly identifying M.micrantha in the wild is important for monitoring its growth status,as this helps management officials to take the necessary steps to devise a comprehensive strategy to control the invasive weed in the identified area.However,this approach still mainly depends on satellite remote sensing and manual inspection.The cost is high and the accuracy rate and efficiency are low.We acquired color images of the monitoring area in the wild environment using an Unmanned Aerial Vehicle(UAV)and proposed a novel network-MmNet-based on a deep Convolutional Neural Network(CNN)to identify M.micrantha in the images.The network consists of AlexNet Local Response Normalization(LRN),along with the GoogLeNet and continuous convolution of VGG inception models.After training and testing,the identification of 400 testing samples by MmNet is very good,with accuracy of 94.50%and time cost of 10.369 s.Moreover,in quantitative comparative analysis,the proposed MmNet not only has high accuracy and efficiency but also simple construction and outstanding repeatability.Compared with recently popular CNNs,MmNet is more suitable for the identification of M.micrantha in the wild.However,to meet the challenge of wild environments,more M.micrantha images need to be acquired for MmNet training.In addition,the classification labels need to be sorted in more detail.Altogether,this research provides some theoretical and scientific basis for the development of intelligent monitoring and early warning systems for M.micrantha and other invasive species.展开更多
To study the regional distribution features of aroma characteristics, the regional distribution maps of aroma characteristics of 225 tobacco leaf samples from Henan Province were drawn by Kriging interpolation method ...To study the regional distribution features of aroma characteristics, the regional distribution maps of aroma characteristics of 225 tobacco leaf samples from Henan Province were drawn by Kriging interpolation method in ArcGIS. The results showed that:(1) the aroma quality of flue-cured tobacco from Henan Province tobacco-growing areas ranged from better to slightly better and aroma quantity ranged from just a little to much. The ability of diffusiveness expressed slight to a little strong and the raw green odour, immature odour and ligneous odour were tiny;(2) there were significant differences between the aroma quality and scorched odour and no statistical differences among the aroma quantity, diffusiveness, raw green odour, ligneous odour and immature odour from different counties;(3) there were trends that scale of aroma quality increased from southwest to both north and east, aroma quantity showed a patchy distribution in space, diffusiveness decreased from east to west, scorched odour increased from west to both north and south, ligneous odour increased from north to south and green odour increased from south to north.展开更多
基金supported by the National Natural Science Foundation of China(3180111238)the Fund Project of the Key Laboratory of Integrated Pest Management on Crops in South China,Ministry of Agriculture and Rural Affairs,China(SCIPM2018-05)+2 种基金the Key Research and Development Program of Nanning,China(20192065)the Guangdong Science and Technology Planning Project,China(2017A020216022)the Industrial Development Fund Support Project of Dapeng District,Shenzhen,China(KY20180117)。
文摘Mikania micrantha Kunth is an invasive alien weed and known as a plant killer around the world.Accurately and rapidly identifying M.micrantha in the wild is important for monitoring its growth status,as this helps management officials to take the necessary steps to devise a comprehensive strategy to control the invasive weed in the identified area.However,this approach still mainly depends on satellite remote sensing and manual inspection.The cost is high and the accuracy rate and efficiency are low.We acquired color images of the monitoring area in the wild environment using an Unmanned Aerial Vehicle(UAV)and proposed a novel network-MmNet-based on a deep Convolutional Neural Network(CNN)to identify M.micrantha in the images.The network consists of AlexNet Local Response Normalization(LRN),along with the GoogLeNet and continuous convolution of VGG inception models.After training and testing,the identification of 400 testing samples by MmNet is very good,with accuracy of 94.50%and time cost of 10.369 s.Moreover,in quantitative comparative analysis,the proposed MmNet not only has high accuracy and efficiency but also simple construction and outstanding repeatability.Compared with recently popular CNNs,MmNet is more suitable for the identification of M.micrantha in the wild.However,to meet the challenge of wild environments,more M.micrantha images need to be acquired for MmNet training.In addition,the classification labels need to be sorted in more detail.Altogether,this research provides some theoretical and scientific basis for the development of intelligent monitoring and early warning systems for M.micrantha and other invasive species.
基金Supported by Major Special Projects of Development of Strong Flavor Characteristic and High Quality Tobacco Leaf by China National Tobacco Corporation(110201101001 TS-01)Pingdingshan Tobacco Company Technology Projects(PDSKJ2017018)Tianchang International Tobacco Company Technology Projects(TCKJ201701)
文摘To study the regional distribution features of aroma characteristics, the regional distribution maps of aroma characteristics of 225 tobacco leaf samples from Henan Province were drawn by Kriging interpolation method in ArcGIS. The results showed that:(1) the aroma quality of flue-cured tobacco from Henan Province tobacco-growing areas ranged from better to slightly better and aroma quantity ranged from just a little to much. The ability of diffusiveness expressed slight to a little strong and the raw green odour, immature odour and ligneous odour were tiny;(2) there were significant differences between the aroma quality and scorched odour and no statistical differences among the aroma quantity, diffusiveness, raw green odour, ligneous odour and immature odour from different counties;(3) there were trends that scale of aroma quality increased from southwest to both north and east, aroma quantity showed a patchy distribution in space, diffusiveness decreased from east to west, scorched odour increased from west to both north and south, ligneous odour increased from north to south and green odour increased from south to north.
