WO2022007114A1 - 利用蝗虫密度分析的危害检测平台 - Google Patents
利用蝗虫密度分析的危害检测平台 Download PDFInfo
- Publication number
- WO2022007114A1 WO2022007114A1 PCT/CN2020/109739 CN2020109739W WO2022007114A1 WO 2022007114 A1 WO2022007114 A1 WO 2022007114A1 CN 2020109739 W CN2020109739 W CN 2020109739W WO 2022007114 A1 WO2022007114 A1 WO 2022007114A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- locust
- density
- type
- locusts
- detection platform
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G13/00—Protecting plants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Definitions
- the invention relates to the field of insect disaster analysis, in particular to a hazard detection platform utilizing locust density analysis.
- Locusts commonly known as "grasshoppers", belong to the order Orthoptera, including Tetrigoidea, Eumastacoidea and Locustoidea species. There are more than 10,000 species in the world, and more than 1,000 species in my country. Distributed in tropical, temperate grassland and desert regions around the world. Locusts mainly include migratory locusts and soil locusts. There are three species of migratory locusts in my country: Locusta migratoria manilensis (Meyen), Asian locust (Locusta migratoria migratoria (Linnaeus)) and Vietnamese migratory locust (Locusta migratoria tibitensis Chen). Among them, the East Asian locust has the largest distribution range in my country. It is the most important species of migratory locusts causing locust plagues in my country, and it mainly harms grasses and is an agricultural pest.
- Locusts have a wide range of food, can eat wheat, rice, millet, corn, beans, tobacco, reeds, vegetables, fruit trees, forest trees and weed leaves, tender stems, flower buds and tender fruits, etc., bite the leaves into nicks or holes , In the event of a large outbreak, the crops can be eaten into bare rods or eaten completely, causing serious economic losses.
- the present invention provides a hazard detection platform utilizing locust density analysis, which can objectively evaluate the distribution density of locusts in the current farmland, and based on the different minimum distribution densities of different types of locusts causing harm , to objectively analyze the current pest disaster scene in farmland, so as to facilitate the subsequent formulation of targeted pest control measures.
- a hazard detection platform utilizing locust density analysis comprising:
- the density analysis device is respectively connected with the data storage chip and the type detection mechanism, and is used for calculating the locust density of the corresponding type based on the number of the corresponding locust objects in the instant enhanced image of the locust type harmful to the type of the currently planted crops;
- a data transmission interface connected with the density analysis device, is used to pack the corresponding type of locust density with the corresponding type wirelessly when the received locust density of the corresponding type exceeds the minimum distribution density of the corresponding type of locust formation damage. Send to the remote agricultural management service center;
- Monitoring and video recording equipment arranged on a vertical pole near the farmland, its field of vision covers the entire farmland to perform video recording operations on the entire farmland, and obtain the corresponding current video frame;
- a data storage chip located in the control box below the vertical pole, is used to pre-save the type of crops currently planted in the farmland;
- the data storage chip is also used to store the respective standard locust patterns corresponding to various locusts, and the standard locust patterns corresponding to each locust are the images that only include the single locust that the single locust of the corresponding species is photographed;
- a signal enhancement mechanism connected with the monitoring video recording device, is used to perform exponential transformation-based image signal enhancement processing on the received current video frame, so as to obtain and output a corresponding instant enhanced image;
- the type detection mechanism is respectively connected with the data storage chip and the signal enhancement mechanism, and is used to identify the locust object corresponding to each locust in the instant enhanced image based on the respective standard locust patterns corresponding to various locusts. Determine the number of locust objects corresponding to various locusts in the instant enhanced image;
- calculating the locust density of the corresponding type based on the number of corresponding locust objects in the instant enhanced image of the locust type that is harmful to the type of currently planted crops includes: The number of corresponding locust objects and the area of the entire farmland are used to calculate the locust density of the corresponding type.
- the method comprises using a kind of hazard detection platform utilizing locust density analysis as above, for forming hazard based on different kinds of locusts Different minimum distribution densities are used to objectively assess the pest infestation in the current farmland.
- the hazard detection platform utilizing locust density analysis of the present invention has reliable monitoring and effective evaluation. Because it can objectively evaluate the distribution density of locusts in the current farmland, and based on the different minimum distribution densities of the damage caused by different types of locusts, it is possible to objectively analyze the insect disaster scene in the current farmland.
- FIG. 1 is a schematic diagram showing the composition of a locust swarm monitored by a hazard detection platform utilizing locust density analysis according to an embodiment of the present invention.
- Locusts are generally facultative diapause insects, and most of them overwinter as eggs in oocysts in the soil. Only a few species, such as Japanese yellow-spine locusts and short-legged locusts, overwinter as adults. The number of generations in a year depends on the biological characteristics of the species and the annual effective accumulated temperature, food, light and the growth and development of each insect stage in different regions.
- the feeding habits of adults and locust flies are the same, both are herbivorous, and the supplementary nutrition is strong in the adult stage, accounting for more than 75% of the total food intake in life. They bite the leaves and flower buds of plants with chewing mouthparts to form nicks and holes, and in severe cases, eat up the leaves and flower buds of a large area of plants, causing heavy economic losses in agriculture, forestry and animal husbandry.
- Some species are oligophagous pests, such as the East Asian locust, which only feed on grasses and sedges; some species are polyphagous, such as the locust.
- the present invention builds a hazard detection platform utilizing locust density analysis, which can effectively solve the corresponding technical problems.
- Fig. 1 is the compositional schematic diagram of the locust swarm monitored by the hazard detection platform utilizing locust density analysis shown according to an embodiment of the present invention, and the system includes:
- the density analysis device is respectively connected with the data storage chip and the type detection mechanism, and is used for calculating the locust density of the corresponding type based on the number of the corresponding locust objects in the instant enhanced image of the locust type harmful to the type of the currently planted crops;
- a data transmission interface connected with the density analysis device, is used to pack the corresponding type of locust density with the corresponding type wirelessly when the received locust density of the corresponding type exceeds the minimum distribution density of the corresponding type of locust formation damage. Send to the remote agricultural management service center;
- Monitoring and video recording equipment arranged on a vertical pole near the farmland, its field of vision covers the entire farmland to perform video recording operations on the entire farmland, and obtain the corresponding current video frame;
- a data storage chip located in the control box below the vertical pole, is used to pre-save the type of crops currently planted in the farmland;
- the data storage chip is also used to store the respective standard locust patterns corresponding to various locusts, and the standard locust patterns corresponding to each locust are the images that only include the single locust that the single locust of the corresponding species is photographed;
- a signal enhancement mechanism connected with the monitoring video recording device, is used to perform exponential transformation-based image signal enhancement processing on the received current video frame, so as to obtain and output a corresponding instant enhanced image;
- the type detection mechanism is respectively connected with the data storage chip and the signal enhancement mechanism, and is used to identify the locust object corresponding to each locust in the instant enhanced image based on the respective standard locust patterns corresponding to various locusts. Determine the number of locust objects corresponding to various locusts in the instant enhanced image;
- calculating the locust density of the corresponding type based on the number of corresponding locust objects in the instant enhanced image of the locust type that is harmful to the type of currently planted crops includes: The number of corresponding locust objects and the area of the entire farmland are used to calculate the locust density of the corresponding type.
- Calculating the locust density of the corresponding type based on the number of the corresponding locust objects in the instant enhanced image and the area of the entire farmland based on the locust type that is harmful to the type of currently planted crops includes: the number is positively correlated with the density , the area is inversely related to the density.
- the data sending interface is also used to not report the information on the locust density of the corresponding type when the received locust density of the corresponding type does not exceed the minimum distribution density of the corresponding type of locust formation damage.
- the type detection mechanism is also connected to the parallel data bus, and is used for receiving data from the parallel data bus and sending the data to the parallel data bus;
- the data storage chip shares the same user control interface with the signal enhancement mechanism and the type detection mechanism, and the user control interface is realized by the SOC chip.
- the signal enhancement mechanism, the type detection mechanism and the data storage chip are connected to the same quartz oscillating device, and are used for acquiring the time series data provided by the quartz oscillating device.
- the content storage chip is one of FLASH flash memory, SDRAM storage chip and DDR storage chip.
- the data storage chip is connected to the IIC control bus for receiving various control commands sent by the IIC control bus;
- control commands are used to respectively configure various working parameters of the data storage chip.
- the type detection mechanism is connected to the IIC control bus, and is used for receiving various control instructions sent through the IIC control bus.
- the hazard detection platform utilizing locust density analysis can also include:
- the MCU controller is configured to refuse to undertake part of the tasks of the signal enhancement mechanism when entering the sleep mode, and to undertake part of the tasks of the signal enhancement mechanism when entering the working mode.
- the present invention also set up a kind of hazard detection method utilizing locust density analysis, described method comprises using a kind of hazard detection platform utilizing locust density analysis as above, for forming hazard based on different kinds of locusts
- the different minimum distribution densities of the current farmland can objectively assess the pest infestation.
- MCU can be divided into Harvard (Harvard) structure and Von Neumann (Von Neumann) structure according to its memory structure.
- Harvard Hard
- Von Neumann Vol Neumann
- the vast majority of today's microcontrollers are based on the von Neumann architecture, which clearly defines four basic parts necessary for an embedded system: a central processing unit core, program memory (read-only memory or flash memory) , data memory (random access memory), one or more timers/timers, and input/output ports for communication with peripherals and extended resources, all integrated on a single integrated circuit chip.
- first and second are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with “first”, “second” may expressly or implicitly include at least one of that feature.
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Toxicology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Catching Or Destruction (AREA)
Abstract
一种利用蝗虫密度分析的危害检测平台，包括：密度分析设备，分别与数据存储芯片和类型检测机构连接，用于基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度；数据发送接口，与所述密度分析设备连接，用于在接收到的相应类型的蝗虫密度超过相应类型蝗虫形成危害的最低分布密度时，将相应类型的蝗虫密度与相应类型打包无线发送给远端的农业管理服务中心。本检测平台监控可靠、评估有效。由于能够客观评估当前农田内的蝗虫分布密度，并基于不同类型蝗虫造成危害的不同的最低分布密度，从而能够对当前农田的虫灾场景进行客观分析。
Description
本发明涉及虫灾分析领域，尤其涉及一种利用蝗虫密度分析的危害检测平台。
蝗虫，俗称“蚂蚱”，属直翅目，包括蚱总科(Tetrigoidea)、蜢总科(Eumastacoidea)、蝗总科(Locustoidea)的种类，全世界有超过10000种，我国有1000余种，分布于全世界的热带、温带的草地和沙漠地区。蝗虫主要包括飞蝗和土蝗。在我国飞蝗有东亚飞蝗(Locusta migratoria manilensis(Meyen))、亚洲飞蝗(Locusta migratoria migratoria(Linnaeus))和西藏飞蝗(Locusta migratoria tibitensis Chen)3种，其中东亚飞蝗在我国分布范围最广，危害最严重，是造成我国蝗灾的最主要飞蝗种类，主要危害禾本科植物，是农业害虫。
蝗虫食物范围广，可取食小麦、水稻、谷子、玉米、豆类、烟草、芦苇、蔬菜、果树、林木及杂草的叶子、嫩茎、花蕾和嫩果等，将叶片咬成缺刻或孔洞，大发生时可将作物食成光杆或全部吃净，造成严重经济损失。
发明内容
为了解决现有技术中的相关技术问题，本发明提供了一种利用蝗虫密度分析的危害检测平台，能够客观评估当前农田内的蝗虫分布密度，并基于不同类型蝗虫造成危害的不同的最低分布密度，对当前农田的虫灾场景进行客观分析，从而便于后续制定针对性的灭虫措施。
为此，本发明需要具备以下几处关键的发明点：
(1)根据当前农田内不同种类的蝗虫数量和农田面积对不同种类的 蝗虫的分布密度进行判断；
(2)利用不同类型蝗虫其形成危害的最低分布密度不同的特性，对当前农田内的蝗虫的危害性进行判断，从而避免引起过度的灭蝗措施。
根据本发明的一方面，提供了一种利用蝗虫密度分析的危害检测平台，所述系统包括：
密度分析设备，分别与数据存储芯片和类型检测机构连接，用于基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度；
数据发送接口，与所述密度分析设备连接，用于在接收到的相应类型的蝗虫密度超过相应类型蝗虫形成危害的最低分布密度时，将所述相应类型的蝗虫密度与所述相应类型打包无线发送给远端的农业管理服务中心；
监控录像设备，设置在农田附近的竖杆上，其视野覆盖整块农田以对所述整块农田执行录像操作，并获得相应的当前录像帧；
数据存储芯片，位于所述竖杆下方的控制箱内，用于预先保存所述农田的当前种植作物的类型；
所述数据存储芯片还用于存储各种蝗虫分别对应的各个标准蝗虫图案，每一种蝗虫对应的标准蝗虫图案为对相应种类的单只蝗虫进行拍摄的只包括所述单只蝗虫的图像；
信号增强机构，与所述监控录像设备连接，用于对接收到的当前录像帧执行基于指数变换的图像信号增强处理，以获得并输出对应的即时增强图像；
类型检测机构，分别与所述数据存储芯片和所述信号增强机构连接，用于基于各种蝗虫分别对应的各个标准蝗虫图案在所述即时增强图像中识别出每一种蝗虫对应的蝗虫对象以确定所述即时增强图像中各种蝗虫对应的蝗虫对象的数量；
其中，基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度包括：基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量以及所述整块农田的面积计算相应类型的蝗虫密度。
根据本发明的另一方面，还提供了一种利用蝗虫密度分析的危害检测方法，所述方法包括使用一种如上述的利用蝗虫密度分析的危害检测平台，用于基于不同种类蝗虫形成危害的不同最低分布密度对当前农田的虫灾进行客观评估。
本发明的利用蝗虫密度分析的危害检测平台监控可靠、评估有效。由于能够客观评估当前农田内的蝗虫分布密度，并基于不同类型蝗虫造成危害的不同的最低分布密度，从而能够对当前农田的虫灾场景进行客观分析。
以下将结合附图对本发明的实施方案进行描述，其中：
图1为根据本发明实施方案示出的利用蝗虫密度分析的危害检测平台所监控蝗群的构成示意图。
下面将参照附图对本发明的利用蝗虫密度分析的危害检测平台的实施方案进行详细说明。
蝗虫一般属于兼性滞育昆虫，多以卵在土壤中的卵囊内越冬，仅诸如日本黄脊蝗、短脚斑腿蝗等少数种类以成虫越冬。在1年中发生的世代数，取决于该物种的生物学特性与不同地区的年有效积温、食物、光照及其各虫期生长发育情况。
成虫与蝗蝻的食性相同，均为植食性，而且成虫期补充营养强烈，约占一生总食量的75％以上。它们以咀嚼式口器咬食植物叶片和花蕾成缺刻 和孔洞，严重时将大面积植物的叶片和花蕾食光，造成农林牧业重大经济损失。有些种类为寡食性害虫，如东亚飞蝗，仅取食禾本科和莎草科植物；有些种类为多食性，如大垫尖翅蝗等。当季节干旱时，它们更贪食，取食的大量食物未经充分消化即排泄出体外，以便从中获得大量水分，供给生理代谢需要，从而增加了对作物的危害程度。
当前，无法客观评估当前农田内的蝗虫分布密度，并基于不同类型蝗虫造成危害的不同的最低分布密度，对当前农田的虫灾场景进行客观分析，导致无法方便后续制定针对性的灭虫措施。
为了克服上述不足，本发明搭建了一种利用蝗虫密度分析的危害检测平台，能够有效解决相应的技术问题。
图1为根据本发明实施方案示出的利用蝗虫密度分析的危害检测平台所监控蝗群的构成示意图，所述系统包括：
密度分析设备，分别与数据存储芯片和类型检测机构连接，用于基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度；
数据发送接口，与所述密度分析设备连接，用于在接收到的相应类型的蝗虫密度超过相应类型蝗虫形成危害的最低分布密度时，将所述相应类型的蝗虫密度与所述相应类型打包无线发送给远端的农业管理服务中心；
监控录像设备，设置在农田附近的竖杆上，其视野覆盖整块农田以对所述整块农田执行录像操作，并获得相应的当前录像帧；
数据存储芯片，位于所述竖杆下方的控制箱内，用于预先保存所述农田的当前种植作物的类型；
所述数据存储芯片还用于存储各种蝗虫分别对应的各个标准蝗虫图案，每一种蝗虫对应的标准蝗虫图案为对相应种类的单只蝗虫进行拍摄的只包括所述单只蝗虫的图像；
信号增强机构，与所述监控录像设备连接，用于对接收到的当前录像帧执行基于指数变换的图像信号增强处理，以获得并输出对应的即时增强图像；
类型检测机构，分别与所述数据存储芯片和所述信号增强机构连接，用于基于各种蝗虫分别对应的各个标准蝗虫图案在所述即时增强图像中识别出每一种蝗虫对应的蝗虫对象以确定所述即时增强图像中各种蝗虫对应的蝗虫对象的数量；
其中，基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度包括：基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量以及所述整块农田的面积计算相应类型的蝗虫密度。
接着，继续对本发明的利用蝗虫密度分析的危害检测平台的具体结构进行进一步的说明。
所述利用蝗虫密度分析的危害检测平台中：
基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量以及所述整块农田的面积计算相应类型的蝗虫密度包括：所述数量与所述密度成正相关的关系，所述面积与所述密度成反相关的关系。
所述利用蝗虫密度分析的危害检测平台中：
所述数据发送接口还用于在接收到的相应类型的蝗虫密度未超过相应类型蝗虫形成危害的最低分布密度时，不对所述相应类型的蝗虫密度进行信息上报。
所述利用蝗虫密度分析的危害检测平台中：
所述类型检测机构还与并行数据总线连接，用于从所述并行数据总线处接收数据，并将数据发送给所述并行数据总线；
其中，所述数据存储芯片与所述信号增强机构、所述类型检测机构共用同一用户控制接口，所述用户控制接口由SOC芯片来实现。
所述利用蝗虫密度分析的危害检测平台中：
所述信号增强机构、所述类型检测机构和所述数据存储芯片与同一石英振荡设备连接，用于获取所述石英振荡设备提供的时序数据。
所述利用蝗虫密度分析的危害检测平台中：
所述内容存储芯片为FLASH闪存、SDRAM存储芯片以及DDR存储芯片中的一种。
所述利用蝗虫密度分析的危害检测平台中：
所述数据存储芯片与IIC控制总线连接，用于接收所述IIC控制总线发送的各种控制命令；
其中，所述各种控制命令用于分别配置所述数据存储芯片的各个工作参数。
所述利用蝗虫密度分析的危害检测平台中：
所述类型检测机构与IIC控制总线连接，用于接收通过所述IIC控制总线发送的各项控制指令。
所述利用蝗虫密度分析的危害检测平台中还可以包括：
MCU控制器，用于在进入休眠模式时，拒绝承担所述信号增强机构的部分任务，以及在进入工作模式时，承担所述信号增强机构的部分任务。
同时，为了克服上述不足，本发明还搭建了一种利用蝗虫密度分析的危害检测方法，所述方法包括使用一种如上述的利用蝗虫密度分析的危害检测平台，用于基于不同种类蝗虫形成危害的不同最低分布密度对当前农田的虫灾进行客观评估。
另外，MCU根据其存储器结构可分为哈佛(Harvard)结构和冯·诺依曼(Von Neumann)结构。现在的单片机绝大多数都是基于冯·诺伊曼结构的，这种结构清楚地定义了嵌入式系统所必需的四个基本部分：一个中央处理器核心，程序存储器(只读存储器或者闪存)、数据存储器(随机存储器)、一个或者更多的定时/计时器，还有用来与外围设备以及扩展资源进行通信的输入/输出端口，所有这些都被集成在单个集成电路芯片上。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。
虽然本发明已以实施例揭示如上，但其并非用以限定本发明，任何所属技术领域的普通技术人员，在不脱离本发明的精神和范围内，应当可以做出适当的改动和同等替换。因此本发明的保护范围应当以本申请权利要求所界定的范围为准。
Claims (10)
- 一种利用蝗虫密度分析的危害检测平台，所述系统包括：密度分析设备，分别与数据存储芯片和类型检测机构连接，用于基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度；数据发送接口，与所述密度分析设备连接，用于在接收到的相应类型的蝗虫密度超过相应类型蝗虫形成危害的最低分布密度时，将所述相应类型的蝗虫密度与所述相应类型打包无线发送给远端的农业管理服务中心；监控录像设备，设置在农田附近的竖杆上，其视野覆盖整块农田以对所述整块农田执行录像操作，并获得相应的当前录像帧；数据存储芯片，位于所述竖杆下方的控制箱内，用于预先保存所述农田的当前种植作物的类型；所述数据存储芯片还用于存储各种蝗虫分别对应的各个标准蝗虫图案，每一种蝗虫对应的标准蝗虫图案为对相应种类的单只蝗虫进行拍摄的只包括所述单只蝗虫的图像；信号增强机构，与所述监控录像设备连接，用于对接收到的当前录像帧执行基于指数变换的图像信号增强处理，以获得并输出对应的即时增强图像；类型检测机构，分别与所述数据存储芯片和所述信号增强机构连接，用于基于各种蝗虫分别对应的各个标准蝗虫图案在所述即时增强图像中识别出每一种蝗虫对应的蝗虫对象以确定所述即时增强图像中各种蝗虫对应的蝗虫对象的数量；其中，基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量计算相应类型的蝗虫密度包括：基于对当前种植 作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量以及所述整块农田的面积计算相应类型的蝗虫密度。
- 如权利要求1所述的利用蝗虫密度分析的危害检测平台，其特征在于：基于对当前种植作物的类型有害的蝗虫类型在即时增强图像中的对应的蝗虫对象的数量以及所述整块农田的面积计算相应类型的蝗虫密度包括：所述数量与所述密度成正相关的关系，所述面积与所述密度成反相关的关系。
- 如权利要求2所述的利用蝗虫密度分析的危害检测平台，其特征在于：所述数据发送接口还用于在接收到的相应类型的蝗虫密度未超过相应类型蝗虫形成危害的最低分布密度时，不对所述相应类型的蝗虫密度进行信息上报。
- 如权利要求3所述的利用蝗虫密度分析的危害检测平台，其特征在于：所述类型检测机构还与并行数据总线连接，用于从所述并行数据总线处接收数据，并将数据发送给所述并行数据总线；其中，所述数据存储芯片与所述信号增强机构、所述类型检测机构共用同一用户控制接口，所述用户控制接口由SOC芯片来实现。
- 如权利要求4所述的利用蝗虫密度分析的危害检测平台，其特征在 于：所述信号增强机构、所述类型检测机构和所述数据存储芯片与同一石英振荡设备连接，用于获取所述石英振荡设备提供的时序数据。
- 如权利要求5所述的利用蝗虫密度分析的危害检测平台，其特征在于：所述内容存储芯片为FLASH闪存、SDRAM存储芯片以及DDR存储芯片中的一种。
- 如权利要求6所述的利用蝗虫密度分析的危害检测平台，其特征在于：所述数据存储芯片与IIC控制总线连接，用于接收所述IIC控制总线发送的各种控制命令；其中，所述各种控制命令用于分别配置所述数据存储芯片的各个工作参数。
- 如权利要求7所述的利用蝗虫密度分析的危害检测平台，其特征在于：所述类型检测机构与IIC控制总线连接，用于接收通过所述IIC控制总线发送的各项控制指令。
- 如权利要求8所述的利用蝗虫密度分析的危害检测平台，其特征在于，所述平台还包括：MCU控制器，用于在进入休眠模式时，拒绝承担所述信号增强机构的部分任务，以及在进入工作模式时，承担所述信号增强机构的部分任务。
- 一种利用蝗虫密度分析的危害检测方法，所述方法包括提供一种如权利要求1-9任一所述的利用蝗虫密度分析的危害检测平台，用于基于不同种类蝗虫形成危害的不同最低分布密度对当前农田的虫灾进行客观评估。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010641834.6 | 2020-07-06 | ||
| CN202010641834.6A CN111862011A (zh) | 2020-07-06 | 2020-07-06 | 利用蝗虫密度分析的危害检测平台 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022007114A1 true WO2022007114A1 (zh) | 2022-01-13 |
Family
ID=73153678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/109739 WO2022007114A1 (zh) | 2020-07-06 | 2020-08-18 | 利用蝗虫密度分析的危害检测平台 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111862011A (zh) |
| WO (1) | WO2022007114A1 (zh) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102062870A (zh) * | 2010-10-26 | 2011-05-18 | 东北师范大学 | 蝗虫密度等级自动监测系统 |
| CN102096808A (zh) * | 2011-01-19 | 2011-06-15 | 南京农业大学 | 稻飞虱虫情自动测报方法 |
| CN103034872A (zh) * | 2012-12-26 | 2013-04-10 | 四川农业大学 | 基于颜色和模糊聚类算法的农田害虫识别方法 |
| CN103210896A (zh) * | 2013-04-19 | 2013-07-24 | 北京理工大学 | 一种温室番茄害虫智能监测与诱捕系统 |
| US20140279600A1 (en) * | 2013-03-15 | 2014-09-18 | Mitchell Barry Chait | Automated monitoring of pest traps in a distributed work environment |
| CN105137840A (zh) * | 2015-08-19 | 2015-12-09 | 方中元 | 设施温室内作物病虫害自动监测与智能施药防控系统 |
-
2020
- 2020-07-06 CN CN202010641834.6A patent/CN111862011A/zh not_active Withdrawn
- 2020-08-18 WO PCT/CN2020/109739 patent/WO2022007114A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102062870A (zh) * | 2010-10-26 | 2011-05-18 | 东北师范大学 | 蝗虫密度等级自动监测系统 |
| CN102096808A (zh) * | 2011-01-19 | 2011-06-15 | 南京农业大学 | 稻飞虱虫情自动测报方法 |
| CN103034872A (zh) * | 2012-12-26 | 2013-04-10 | 四川农业大学 | 基于颜色和模糊聚类算法的农田害虫识别方法 |
| US20140279600A1 (en) * | 2013-03-15 | 2014-09-18 | Mitchell Barry Chait | Automated monitoring of pest traps in a distributed work environment |
| CN103210896A (zh) * | 2013-04-19 | 2013-07-24 | 北京理工大学 | 一种温室番茄害虫智能监测与诱捕系统 |
| CN105137840A (zh) * | 2015-08-19 | 2015-12-09 | 方中元 | 设施温室内作物病虫害自动监测与智能施药防控系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111862011A (zh) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guichard et al. | Advances and perspectives in selecting resistance traits against the parasitic mite Varroa destructor in honey bees | |
| Tefera et al. | Methods of screening maize for resistance to stem borers and post-harvest insect pests | |
| Haschek et al. | Carabid beetle condition, reproduction and density in winter oilseed rape affected by field and landscape parameters | |
| Green et al. | Reproductive parameters of the fisher (Pekania pennanti) in the southern Sierra Nevada, California | |
| Jachuła et al. | Validation of floral food resources for pollinators in agricultural landscape in SE Poland | |
| Clapperton et al. | Diet, population structure and breeding of Rattus rattus L. in South Island beech forest | |
| CN111252246A (zh) | 一种基于无人机、固定摄像模块联用的大区域病虫害防治方法 | |
| Labbé et al. | Songbird use of native and invasive fruit in the northeastern USA | |
| Norman et al. | Reproduction of eastern wild turkeys in Virginia and West Virginia | |
| Scherer-Neto et al. | Long-term monitoring of a hyacinth macaw Anodorhynchus hyacinthinus (Psittacidae) roost in the Pantanal, Brazil | |
| Lima et al. | Factors determining yield and nutritive value of maize for silage under tropical conditions | |
| WO2022007114A1 (zh) | 利用蝗虫密度分析的危害检测平台 | |
| Pitta et al. | Dual-purpose wheat grain and animal production under different grazing periods | |
| Weckerly | Selective feeding by black-tailed deer: forage quality or abundance? | |
| Matsui et al. | Predation risk of eggs and nestlings relative to nest‐site characteristics of the Bull‐headed Shrike Lanius bucephalus | |
| Tyler et al. | Effects of weather on the survival and growth of Corncrake Crex crex chicks | |
| Tarr | Effects of non-native shrubs on caterpillars and shrubland-dependent passerines within three transmission line rights-of-way in southeastern New Hampshire | |
| Hancock et al. | The effect of harvest method on cereal stubble use by seed-eating birds in a High Nature Value farming system | |
| Schroeder | Individual fitness correlates in the Black-tailed Godwit | |
| Takahashi et al. | Nest types and microhabitat characteristics of the Japanese Marsh Warbler Locustella pryeri | |
| Wuensche | An assessment of plant resistance to the sorghum midge, Contarinia sorghicola, in selected lines of Sorghum bicolor | |
| Stringer | Evaluating hemp (Cannabis sativa) as a forage based on yield, nutritive analysis, and morphological composition | |
| Castelán-Ortega et al. | Grazing behaviour of dairy cows and body condition score associated with sward characteristics of four pasture types | |
| Williams et al. | Recurrent Selection for Resistance in Corn to Tunneling by the Second‐Brood Southwestern Corn Borer 1 | |
| Cheng et al. | Key factors involved in reduction of damage to sunflower by the European sunflower moth in China through late planting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20943954 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20943954 Country of ref document: EP Kind code of ref document: A1 |