WO2019000563A1 - 种植参数调控方法和种植参数调控装置 - Google Patents
种植参数调控方法和种植参数调控装置 Download PDFInfo
- Publication number
- WO2019000563A1 WO2019000563A1 PCT/CN2017/096258 CN2017096258W WO2019000563A1 WO 2019000563 A1 WO2019000563 A1 WO 2019000563A1 CN 2017096258 W CN2017096258 W CN 2017096258W WO 2019000563 A1 WO2019000563 A1 WO 2019000563A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- reference image
- growth
- pest
- crop
- preset
- Prior art date
Links
Images
Classifications
-
- 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
- A01G7/00—Botany in general
Definitions
- the invention relates to the technical field of intelligent control systems, in particular to a planting parameter regulating method and a planting parameter regulating device.
- the present invention aims to solve at least one of the technical problems existing in the prior art or related art.
- Another object of the present invention is to provide a planting parameter regulating device.
- the technical solution of the first aspect of the present invention provides a method for regulating planting parameters, comprising: determining the fertility of a crop corresponding to an abnormal growth parameter when abnormal growth parameters are detected in the growth image information of the crop; And determining at least one corresponding pest and disease reference image according to the growth period, and determining whether the growth image information matches any of the preset pest and disease reference images; and when determining that the growth image information matches any of the preset pest and disease reference images, The sprinkling parameters for performing the de-worming operation on the crop are determined according to the attribute information of the matched preset pest reference image.
- the attribute information determines the sprinkling parameters for the de-worming operation of the crops, that is, according to the matched reference image of the preset pests and diseases, the sprinkling parameters for the de-worming operation of the crops are determined in time, that is, the problem of crop pests and diseases is solved in time, and the problem is reduced.
- the labor cost of removing worms improves the survival rate and yield of crops.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- abnormal growth parameters are detected in the growth image information of the crop, specifically: identifying a feature growth parameter of the growth image information of the crop; and determining whether the feature growth parameter matches the preset feature growth parameter; When it is determined that the feature growth parameter does not match the preset feature growth parameter, the feature growth parameter is determined as an abnormal growth parameter, wherein the feature growth parameter includes a stem size, a stem color, a leaf color, and a difference in adjacent leaf size of the crop. at least one.
- the parameter is determined as an abnormal growth parameter, wherein the characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop, and timely and accurately determines whether the crop belongs to abnormal growth.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, and the leaves are large and thin and green. If the stem length of the crop is less than two meters in the vine stage, the crop is judged to be abnormal growth, or the leaf color is yellow or spotted, and the crop is judged to be abnormal growth.
- the growth period is one of a germination period, a seedling period, a pumping period, and a result period of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, guarded melon reference map
- the reference image of the pest and disease corresponding to the reference image of the leaf larvae includes the downy mildew reference image, the disease reference image, the anthrax reference image, the blight reference image, the powdery mildew reference image, the target spot disease reference image, Bacterial angular plaque reference image, locust reference image, hummer reference image, whitefly reference image and squash reference image
- the corresponding pest and disease reference image in the result period includes downy mildew reference image, disease reference image, target spot disease Reference image, bacterial ang
- the method includes: calculating a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; and determining that the growth image information matches the preset pest and disease reference image when the matching degree is greater than or equal to the preset matching degree; Reading the attribute information of the matched reference pest reference image; determining the sprinkling parameters of the pest removal operation according to the attribute information, wherein the sprinkling parameters include the pesticide type, the pesticide liquid amount and the deworming mode, and the deworming method includes spraying the pesticide De-worming methods and / or irrigation pesticides.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- sprinkler irrigation parameters include pesticide type, pesticide liquid amount and de-worming method.
- De-worming methods include spray pesticide de-worming methods and/or irrigation pesticide de-worming methods.
- the pesticides used for different pests and diseases are shown in Table 4 below:
- a planting parameter regulating device comprising: a determining unit, configured to determine an abnormal growth parameter corresponding to an abnormal growth parameter when detecting an abnormal growth parameter in the growth image information of the crop The growth period of the crop; also used to determine at least one corresponding pest and disease reference image according to the growth period, and determine whether the growth image information matches any of the preset pest reference images; and is also used to determine the growth image information and any pre-determination When the pest and disease reference image is matched, the sprinkling parameters for performing the de-worming operation on the crop are determined according to the attribute information of the matched preset pest reference image.
- the setting determining unit is configured to determine a growth period of the crop corresponding to the abnormal growth parameter when the abnormal growth parameter exists in the growth image information of the detected crop, and to determine at least the corresponding at least according to the growth period a preset pest and disease reference image and judge Whether the growing image information matches any of the preset pest reference images, and is further configured to determine that the crop is dewormed according to the attribute information of the matched preset pest reference image when determining that the growing image information matches any of the preset pest reference images
- the sprinkling parameters of the operation that is, according to the matched reference image of the preset pests and diseases, timely determine the sprinkling parameters for the de-worming operation of the crops, that is, solve the problem of pests and diseases of the crops in time, and reduce the labor cost of removing the insects and removing diseases, Increased crop survival and yield.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- the planting parameter regulating device further includes: an identifying unit, configured to identify feature growth parameters of the growth image information of the crop; and a determining unit, configured to determine whether the feature growth parameter is grown with the preset feature Parameter matching; the determining unit is further configured to: determine the feature growth parameter as an abnormal growth parameter when determining that the feature growth parameter does not match the preset feature growth parameter, wherein the feature growth parameter includes a stem size, a stem color, and a leaf color of the crop At least one of the degrees of difference in adjacent blade sizes.
- the feature growth parameter for identifying the growth image information of the crop is set by the setting unit, and the setting judgment unit is configured to determine whether the feature growth parameter matches the preset feature growth parameter, and is further used by the setting determining unit.
- the feature growth parameter is determined as an abnormal growth parameter, and the crop is abnormally grown in a timely and accurate manner.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, and the leaves are large and thin and green. If the stem length of the crop is less than two meters in the vine stage, the crop is judged to be abnormal growth, or the leaf color is yellow or spotted, and the crop is judged to be abnormal growth.
- the growth period is a germination period and a seedling of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, squash reference image and leafmind reference image, reference to the corresponding pests and diseases in the vine period
- Images include downy mildew reference images, disease reference images, anthrax reference images, blight reference images, powdery mildew reference images, target spot disease reference images, bacterial angular spot reference images, locust reference images, thrips reference images
- the reference image of the whitefly and the reference image of the melon, the corresponding pest and disease reference image in the result period includes the downy mildew reference image, the disease reference image, the target spot disease reference image, the bacterial angular spot
- the planting parameter regulating device further comprises: a calculating unit, configured to calculate a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; After determining that the matching degree is greater than or equal to the preset matching degree, determining that the growth image information matches the preset pest and disease reference image; the planting parameter control device further comprises: a reading unit, configured to read the matched preset pest and disease reference image The attribute information; the determining unit is further configured to: determine, according to the attribute information, a sprinkling parameter for performing a de-worming operation on the crop, wherein the sprinkling parameter includes a pesticide type, a pesticide liquid amount, and a de-worming method, and the de-worming method includes a spray pesticide de-worming method and / or irritable pesticides.
- a calculating unit configured to calculate a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; After determining that the matching degree is greater than or
- the setting unit is configured to calculate a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period, and the determining unit is further configured to determine that the matching degree is greater than or equal to the preset matching. Determining, the growth image information is matched with the preset pest reference image, and the reading unit is configured to read the attribute information of the matched preset pest reference image, and the setting determining unit is further configured to determine the crop according to the attribute information. Insect removal The sprinkling parameters made by the calculation more intuitively reflect the causes of abnormal growth of crops, simplifying the steps of manual image information comparison, saving time and human resources, and improving the accuracy and efficiency of dealing with crop growth abnormalities.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- FIG. 1 shows a schematic flow chart of a method for regulating planting parameters according to an embodiment of the present invention
- Figure 2 shows a schematic block diagram of a planting parameter control device in accordance with one embodiment of the present invention
- Figure 3 shows a schematic block diagram of a pesticide sprinkler terminal in accordance with one embodiment of the present invention.
- FIG. 1 shows a schematic flow chart of a method of regulating planting parameters in accordance with one embodiment of the present invention.
- FIG. 1 illustrates a planting parameter regulation method according to an embodiment of the present invention, including: steps S102, when detecting abnormal growth parameters in the growth image information of the crop, determining a growth period of the crop corresponding to the abnormal growth parameter; and step S104, determining a corresponding reference image of the at least one preset pest and pest according to the growth period, and determining the growth image Whether the information matches any of the preset pest reference images; and in step S106, when determining that the growth image information matches any of the preset pest reference images, determining the pest removal operation of the crop according to the attribute information of the matched preset pest reference image Sprinkler parameters.
- the attribute information determines the sprinkling parameters for the de-worming operation of the crops, that is, according to the matched reference image of the preset pests and diseases, the sprinkling parameters for the de-worming operation of the crops are determined in time, that is, the problem of crop pests and diseases is solved in time, and the problem is reduced.
- the labor cost of removing worms improves the survival rate and yield of crops.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- abnormal growth parameters are detected in the growth image information of the crop, specifically: identifying a feature growth parameter of the growth image information of the crop; and determining whether the feature growth parameter matches the preset feature growth parameter; When it is determined that the feature growth parameter does not match the preset feature growth parameter, the feature growth parameter is determined as an abnormal growth parameter, wherein the feature growth parameter includes a stem size, a stem color, a leaf color, and a difference in adjacent leaf size of the crop. at least one.
- the parameter is determined as an abnormal growth parameter, wherein the characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop, and timely and accurately determines whether the crop belongs to abnormal growth.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, and the leaves are large and thin and green. If the stem length of the crop is less than two meters in the vine stage, the crop is judged to be abnormal growth, or the leaf color is yellow or spotted, and the crop is judged to be abnormal growth.
- the growth period is one of a germination period, a seedling period, a pumping period, and a result period of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, squash reference image and leafmind reference image, reference to the corresponding pests and diseases in the vine period
- Images include downy mildew reference images, disease reference images, anthrax reference images, blight reference images, powdery mildew reference images, target spot disease reference images, bacterial angular spot reference images, locust reference images, thrips reference images
- the reference image of the whitefly and the reference image of the melon, the corresponding pest and disease reference image in the result period includes the downy mildew reference image, the disease reference image, the target spot disease reference image, the bacterial angular spot
- the method includes: calculating a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; and determining that the growth image information matches the preset pest and disease reference image when the matching degree is greater than or equal to the preset matching degree; Reading the attribute information of the matched preset pest and disease reference image; determining the sprinkling parameters of the pest removal operation according to the attribute information, wherein the sprinkling parameters include the pesticide type, the pesticide liquid amount and the deworming mode,
- the de-worming method includes spray pesticide de-worming methods and/or irrigation pesticide de-worming methods.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- Figure 2 shows a schematic block diagram of a planting parameter control device in accordance with one embodiment of the present invention.
- FIG. 2 shows a planting parameter regulating device 200 according to an embodiment of the present invention, comprising: a determining unit 202, for determining a crop corresponding to an abnormal growing parameter when abnormal growth parameters are present in the growth image information of the detected crop
- the growth period is also used to determine at least one corresponding pest and disease reference image according to the growth period, and determine whether the growth image information matches any of the preset pest reference images; and is also used to determine the growth image information and any preset
- the sprinkling parameters for performing the de-worming operation on the crop are determined according to the attribute information of the matched preset pest reference image.
- the setting determining unit 202 is configured to determine the growth period of the crop corresponding to the abnormal growth parameter when the abnormal growth parameter exists in the growth image information of the detected crop, and is further used to determine the corresponding period according to the growth period.
- the attribute information of the image determines the sprinkling parameters for the de-worming operation of the crop, that is, according to the matched reference image of the preset pests and diseases, the sprinkling parameters for the de-worming operation of the crops are determined in time, that is, the problem of crop pests and diseases is solved in time, The labor cost of removing insects and diseases is reduced, and the survival rate and yield of crops are improved.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- the planting parameter regulating device 200 further includes: an identifying unit 204, configured to identify a feature growing parameter of the growing image information of the crop; and a determining unit 206, configured to determine whether the feature growing parameter is The characteristic growth parameter matching is performed; the determining unit 202 is further configured to: when determining that the feature growth parameter does not match the preset feature growth parameter, determine the feature growth parameter as an abnormal growth parameter, wherein the feature growth parameter includes a stem size and a stem of the crop At least one of a difference in color, blade color, and adjacent blade size.
- the setting determination unit 206 is configured to determine whether the feature growth parameter matches the preset feature growth parameter, and the setting determining unit The 202 is further configured to determine the feature growth parameter as an abnormal growth parameter when determining that the feature growth parameter does not match the preset feature growth parameter, and timely and accurately determine whether the crop belongs to abnormal growth.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, and the leaves are large and thin and green. If the stem length of the crop is less than two meters in the vine stage, the crop is judged to be abnormal growth, or the leaf color is yellow or spotted, and the crop is judged to be abnormal growth.
- the growth period is one of a germination period, a seedling period, a pumping period, and a result period of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, squash reference image and leafmind reference image
- Image includes downy mildew reference Image, disease reference image, anthrax reference image, blight reference image, powdery mildew reference image, target spot disease reference image, bacterial angular spot reference image, locust reference image, hummer reference image, whitefly reference image and defensive
- the melon reference image, the corresponding pest and disease reference image corresponding to the result period includes the downy mildew reference image, the disease reference image, the target spot disease reference image, the bacterial angular spot reference image,
- the planting parameter regulating device 200 further includes: a calculating unit 208, configured to calculate a matching degree between the growth image information and any preset pest reference image corresponding to the growth period;
- the 202 is further configured to: determine that the growth image information is matched with the preset pest reference image when the matching degree is greater than or equal to the preset matching degree;
- the planting parameter control apparatus 200 further includes: a reading unit 210, configured to read the matching pre The attribute information of the pest and disease reference image is set;
- the determining unit 202 is further configured to: determine, according to the attribute information, a sprinkling parameter for performing a de-worming operation on the crop, wherein the sprinkling parameter includes a pesticide type, a pesticide liquid amount, and a de-worming method, and the de-worming method includes spraying Pesticide de-worming methods and / or irrigation pesticides.
- the setting calculation unit 208 is configured to calculate a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period, and the determining unit 202 is further configured to determine that the matching degree is greater than or equal to the pre-determination.
- the matching degree is set, the determined growth image information is matched with the preset pest reference image, and the reading unit 210 is configured to read the attribute information of the matched preset pest reference image, and the setting determining unit 202 is further configured to use the attribute information according to the attribute information.
- Determining the sprinkler parameters for the de-worming operation of crops which more intuitively reflects the causes of abnormal growth of crops, simplifies the steps of manual image information comparison, saves time and human resources, and improves the accuracy of crop growth abnormalities. Sex and efficiency.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- the determining unit 202 and the calculating unit 208 may be a processor, a single chip microcomputer and a microcontroller of the planting parameter regulating device 200, and the identifying unit 204 may be an image recognition component of the planting parameter regulating device 200, specifically including a camera.
- the filter unit and the Laplace transformer, etc., the judging unit 206 may be a comparator of the planting parameter regulating device 200, and the reading unit 210 may be a memory of the planting parameter regulating device 200 or a communication component having a storage capability, and the communication component may It is an antenna.
- Figure 3 shows a schematic block diagram of a pesticide sprinkler terminal in accordance with one embodiment of the present invention.
- the computer program storage step stored in the memory 302 includes: determining the growth period of the crop corresponding to the abnormal growth parameter when detecting the abnormal growth parameter in the growth image information of the crop; determining the corresponding at least one preset pest based on the growth period Referencing the image, and determining whether the growth image information matches any of the preset pest reference images; and determining that the growth image information matches any of the preset pest reference images, determining the crop according to the attribute information of the matched preset pest reference image Sprinkler parameters for de-worming operations.
- the attribute information determines the sprinkling parameters for the de-worming operation of the crops, that is, according to the matched reference image of the preset pests and diseases, the sprinkling parameters for the de-worming operation of the crops are determined in time, that is, the problem of crop pests and diseases is solved in time, and the problem is reduced.
- the labor cost of removing worms improves the survival rate and yield of crops.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- abnormal growth parameters are detected in the growth image information of the crop, specifically: identifying a feature growth parameter of the growth image information of the crop; and determining whether the feature growth parameter matches the preset feature growth parameter; When it is determined that the feature growth parameter does not match the preset feature growth parameter, the feature growth parameter is determined as an abnormal growth parameter, wherein the feature growth parameter includes a stem size, a stem color, a leaf color, and a difference in adjacent leaf size of the crop. at least one.
- the parameter is determined as an abnormal growth parameter, wherein the characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop, and timely and accurately determines whether the crop belongs to abnormal growth.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, and the leaves are large and thin and green. If the stem length of the crop is less than two meters in the vine stage, the crop is judged to be abnormal growth, or the leaf color is yellow or spotted, and the crop is judged to be abnormal growth.
- the growth period is one of a germination period, a seedling period, a pumping period, and a result period of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, squash reference image and leafmind reference image, reference to the corresponding pests and diseases in the vine period
- Images include downy mildew reference images, disease reference images, anthrax reference images, blight reference images, powdery mildew reference images, target spot disease reference images, bacterial angular spot reference images, locust reference images, thrips reference images
- the reference image of the whitefly and the reference image of the melon, the corresponding pest and disease reference image in the result period includes the downy mildew reference image, the disease reference image, the target spot disease reference image, the bacterial angular spot
- the method includes: calculating a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; and determining that the growth image information matches the preset pest and disease reference image when the matching degree is greater than or equal to the preset matching degree; Reading the attribute information of the matched reference pest reference image; determining the sprinkling parameters of the pest removal operation according to the attribute information, wherein the sprinkling parameters include the pesticide type, the pesticide liquid amount and the deworming mode, and the deworming method includes spraying the pesticide De-worming methods and / or irrigation pesticides.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- a computer readable storage medium having stored thereon a computer program, wherein when the computer program is executed by the processor, the implementing step comprises: determining that an abnormal growth parameter exists in the growth image information of the crop, The growth period of the crop corresponding to the abnormal growth parameter; determining at least one corresponding pest and disease reference image according to the growth period, and determining whether the growth image information matches any of the preset pest and disease reference images; determining the growth image information and any pre-determination When the pest and disease reference image is matched, according to the genus of the matched reference pest reference image The sexual information determines the sprinkling parameters for the de-worming operation of the crop.
- the attribute information determines the sprinkling parameters for the de-worming operation of the crops, that is, according to the matched reference image of the preset pests and diseases, the sprinkling parameters for the de-worming operation of the crops are determined in time, that is, the problem of crop pests and diseases is solved in time, and the problem is reduced.
- the labor cost of removing worms improves the survival rate and yield of crops.
- the characteristic growth parameter of the acquired growth image information of the crop (such as the growth state and the stem height defined by the time parameter shown in Table 1), wherein the growth image information has the geographic region attribute, and the feature is Growth parameter analysis is used to determine the abnormal growth of crops.
- the growth image information is compared with the preset pest and disease reference image, which not only can quickly determine the type of pests and diseases, but also can determine the degree of pests and diseases in time, and adopts electronically controlled sprinkler terminals. Sprinkle irrigation of crops in geographical areas where pests and diseases occur.
- abnormal growth parameters are detected in the growth image information of the crop, specifically: identifying a feature growth parameter of the growth image information of the crop; and determining whether the feature growth parameter matches the preset feature growth parameter; When it is determined that the feature growth parameter does not match the preset feature growth parameter, the feature growth parameter is determined as an abnormal growth parameter, wherein the feature growth parameter includes a stem size, a stem color, a leaf color, and a difference in adjacent leaf size of the crop. at least one.
- the parameter is determined as an abnormal growth parameter, wherein the characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop, and timely and accurately determines whether the crop belongs to abnormal growth.
- the preset growth parameter characteristic growth parameter includes at least one of a stem size, a stem color, a leaf color, and a difference degree of an adjacent leaf size of the crop.
- the length of the vine in the vine period is up to three meters or more.
- the leaves are palm-shaped, the leaves are large and thin and green, such as crops
- the stem length is less than two meters in the vine period, it is judged that the crop belongs to abnormal growth, or the leaf color is yellow or spots appear, and the crop is judged to be abnormal growth.
- the growth period is one of a germination period, a seedling period, a pumping period, and a result period of the crop.
- the reference image of the preset pest and disease corresponding to the germination period includes the squatting disease reference image and the reference image of the underground pest
- the reference image of the preset pest and disease corresponding to the seedling stage includes the wilting Disease reference image, root rot reference image, anthrax reference image, downy mildew reference image, disease reference image, melon reference image, squash reference image and leafmind reference image, reference to the corresponding pests and diseases in the vine period
- Images include downy mildew reference images, disease reference images, anthrax reference images, blight reference images, powdery mildew reference images, target spot disease reference images, bacterial angular spot reference images, locust reference images, thrips reference images
- the reference image of the whitefly and the reference image of the melon, the corresponding pest and disease reference image in the result period includes the downy mildew reference image, the disease reference image, the target spot disease reference image, the bacterial angular spot
- the method includes: calculating a matching degree between the growth image information and any preset pest and disease reference image corresponding to the growth period; and determining that the growth image information matches the preset pest and disease reference image when the matching degree is greater than or equal to the preset matching degree; Reading the attribute information of the matched reference pest reference image; determining the sprinkling parameters of the pest removal operation according to the attribute information, wherein the sprinkling parameters include the pesticide type, the pesticide liquid amount and the deworming mode, and the deworming method includes spraying the pesticide De-worming methods and / or irrigation pesticides.
- the technical solution by calculating the matching degree between the growth image information and any preset pest reference image corresponding to the growth period, by determining that the matching degree is greater than or equal to the preset matching degree,
- the growth image information is determined to match the preset pest and disease reference image, and the attribute information of the matched pest and pest reference image is read, and the sprinkling parameters of the de-worming operation of the crop are determined according to the attribute information, and the reason for the abnormal growth of the crop is more intuitively reflected through calculation. It simplifies the steps of manual image information comparison, saves time and human resources, and improves the accuracy and efficiency of dealing with crop growth abnormalities.
- the degree of matching between the growth image information and the preset pest reference image reaches a set matching degree (eg, the preset matching degree is greater than or equal to 80%), it is determined that the crop in the crop image has the same pest or disease as the matching image or Abnormal growth.
- the present invention provides a planting parameter regulating method and a planting parameter regulating device, which further determines the presence of abnormal growth parameters in the growth image information of the crop.
- the sprinkling parameters for performing the de-worming operation on the crop are determined according to the attribute information of the matched preset pest reference image, that is, according to the matched preset pest reference image, timely determination
- the sprinkling parameters of the de-worming operation of crops solved the problem of crop pests and diseases in a timely manner, reduced the labor cost of removing insects and diseases, and improved the survival rate and yield of crops.
- the units in the apparatus of the present invention can be combined, divided, and deleted according to actual needs.
- ROM Read-Only Memory
- RAM Random Access Memory
- PROM Programmable Read-Only Memory
- EPROM Erasable Programmable Read Only Memory
- OTPROM One-Time Programmable Read-Only Memory
- EEPROM Electronically-Erasable Programmable Read-Only Memory
- CD-ROM Compact Disc Read-Only Memory
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Botany (AREA)
- Ecology (AREA)
- Forests & Forestry (AREA)
- Environmental Sciences (AREA)
- Catching Or Destruction (AREA)
Abstract
一种种植参数调控方法和种植参数调控装置，其中，种植参数调控方法包括：在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期（S102）；根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配（S104）；在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数（S106）。根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
Description
本申请要求于2017年06月30日提交中国专利局、申请号为201710525615.X、发明名称为“种植参数调控方法和种植参数调控装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及智能控制系统技术领域，具体而言，涉及一种种植参数调控方法和一种种植参数调控装置。
相关技术中，通常采用人工方式对农作物的生长状况进行监测，存在以下技术缺陷：
(1)种植面积过大时，存在人工监测主动效率较低和及时性差等问题，导致农作物的病虫害问题不能得到良好的监测和控制；
(2)农作物的病虫害类型过多，需要人工识别农作物的病虫害类型，并且需要针对性指定农药的喷灌策略，因此，导致了种植过程的人工成本升高。
发明内容
本发明旨在至少解决现有技术或相关技术中存在的技术问题之一。
为此，本发明的一个目的在于提供一种种植参数调控方法。
本发明的另一个目的在于提供一种种植参数调控装置。
为了实现上述目的，本发明的第一方面的技术方案提供了一种种植参数调控方法，包括：在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；在判定生长图像信息与任一预设病虫害参考图像匹配时，
根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过在检测到农作物的生长图像信息中存在异常生长参数时，进一步地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
其中，以黄瓜为种植的农作物的一个例子，则黄瓜的生育期如下表1所示。
表1
另外，不同生育期出现的病虫害类型如表2和表3所示。
表2
表3
在上述技术方案中，优选地，检测到农作物的生长图像信息中存在异常生长参数，具体包括：识别农作物的生长图像信息的特征生长参数；判断特征生长参数是否与预设特征生长参数匹配；在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过识别农作物的生长图像信息的特征生长参数，判断特征生长参数是否与预设特征生长参数匹配，通过在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图
像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、上述白粉病参考图像、蔓枯病参考图像、灰霉病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，具体包括：计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；读取匹配的预设病虫害参考图像的属性信息；根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配，通过读取匹配的预设病虫害参考图像的属性信息，根据属性信息确定对农作物进行除虫操作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
另外，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式，例如针对不同病虫害所用农药如下表表4所示：
表4
根据本发明的第二方面的实施例，还提出了一种种植参数调控装置，包括：确定单元，用于在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；还用于根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；还用于在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过设置确定单元，用于在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期，还用于根据生育期确定对应的至少一个预设病虫害参考图像，并判断
生长图像信息是否与任一预设病虫害参考图像匹配，还用于在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
在上述任一项技术方案中，优选地，种植参数调控装置还包括：识别单元，用于识别农作物的生长图像信息的特征生长参数；判断单元，用于判断特征生长参数是否与预设特征生长参数匹配；确定单元还用于：在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过设置识别单元，用于识别农作物的生长图像信息的特征生长参数，通过设置判断单元，用于判断特征生长参数是否与预设特征生长参数匹配，通过设置确定单元还用于在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗
期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、白粉病参考图像、蔓枯病参考图像、灰霉病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，种植参数调控装置还包括：计算单元，用于计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；确定单元还用于：在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；种植参数调控装置还包括：读取单元，用于读取匹配的预设病虫害参考图像的属性信息；确定单元还用于：根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过设置计算单元用于计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过确定单元还用于在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配，通过设置读取单元，用于读取匹配的预设病虫害参考图像的属性信息，通过设置确定单元还用于根据属性信息确定对农作物进行除虫操
作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
本发明的附加方面和优点将在下面的描述部分中给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
本发明的上述和/或附加的方面和优点从结合下面附图对实施例的描述中将变得明显和容易理解，其中：
图1示出了根据本发明的一个实施例的种植参数调控方法的示意流程图；
图2示出了根据本发明的一个实施例的种植参数调控装置的示意框图；
图3示出了根据本发明的一个实施例的农药喷灌终端的示意框图。
为了能够更清楚地理解本发明的上述目的、特征和优点，下面结合附图和具体实施方式对本发明进行进一步的详细描述。需要说明的是，在不冲突的情况下，本申请的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本发明，但是，本发明还可以采用其他不同于在此描述的其他方式来实施，因此，本发明的保护范围并不受下面公开的具体实施例的限制。
实施例1：
图1示出了根据本发明的一个实施例的种植参数调控方法的示意流程图。
如图1示出了根据本发明的实施例的种植参数调控方法，包括：步骤
S102，在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；步骤S104，根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；步骤S106，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过在检测到农作物的生长图像信息中存在异常生长参数时，进一步地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
在上述技术方案中，优选地，检测到农作物的生长图像信息中存在异常生长参数，具体包括：识别农作物的生长图像信息的特征生长参数；判断特征生长参数是否与预设特征生长参数匹配；在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过识别农作物的生长图像信息的特征生长参数，判断特征生长参数是否与预设特征生长参数匹配，通过在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、上述白粉病参考图像、蔓枯病参考图像、灰霉病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，具体包括：计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；读取匹配的预设病虫害参考图像的属性信息；根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，
除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配，通过读取匹配的预设病虫害参考图像的属性信息，根据属性信息确定对农作物进行除虫操作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
图2示出了根据本发明的一个实施例的种植参数调控装置的示意框图。
如图2示出了根据本发明的实施例的种植参数调控装置200，包括：确定单元202，用于在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；还用于根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；还用于在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过设置确定单元202，用于在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期，还用于根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配，还用于在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
在上述任一项技术方案中，优选地，种植参数调控装置200还包括：识别单元204，用于识别农作物的生长图像信息的特征生长参数；判断单元206，用于判断特征生长参数是否与预设特征生长参数匹配；确定单元202还用于：在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过设置识别单元204，用于识别农作物的生长图像信息的特征生长参数，通过设置判断单元206，用于判断特征生长参数是否与预设特征生长参数匹配，通过设置确定单元202还用于在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考
图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、白粉病参考图像、蔓枯病参考图像、灰霉病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，种植参数调控装置200还包括：计算单元208，用于计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；确定单元202还用于：在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；种植参数调控装置200还包括：读取单元210，用于读取匹配的预设病虫害参考图像的属性信息；确定单元202还用于：根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过设置计算单元208用于计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过确定单元202还用于在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配，通过设置读取单元210，用于读取匹配的预设病虫害参考图像的属性信息，通过设置确定单元202还用于根据属性信息确定对农作物进行除虫操作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
其中，值得特别指出的是，确定单元202和计算单元208可以是种植参数调控装置200的处理器、单片机和微控制器，识别单元204可以为种植参数调控装置200的图像识别组件，具体包括摄像头、滤波器和拉普拉斯变换器等，判断单元206可以为种植参数调控装置200的比较器，读取单元210可以为种植参数调控装置200的存储器或具有存储能力的通信组件，通信组件可以是天线。
图3示出了根据本发明的一个实施例的农药喷灌终端的示意框图。
如图3示出了根据本发明的一个实施例的农药喷灌终端300，包括存储器302、处理器304及存储在存储器302上并可在处理器304上运行的计算机程序，处理器304用于执行存储器302中存储的计算机程序时实现步骤包括：在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过在检测到农作物的生长图像信息中存在异常生长参数时，进一步地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
其中，以黄瓜为种植的农作物的一个例子，则黄瓜的生育期如下表1
所示。
在上述技术方案中，优选地，检测到农作物的生长图像信息中存在异常生长参数，具体包括：识别农作物的生长图像信息的特征生长参数；判断特征生长参数是否与预设特征生长参数匹配；在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过识别农作物的生长图像信息的特征生长参数，判断特征生长参数是否与预设特征生长参数匹配，通过在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、上述白粉病参考图像、蔓枯病参考图像、灰霉
病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，具体包括：计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；读取匹配的预设病虫害参考图像的属性信息；根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配，通过读取匹配的预设病虫害参考图像的属性信息，根据属性信息确定对农作物进行除虫操作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
根据本发明的实施例提出了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现步骤包括：在检测到农作物的生长图像信息中存在异常生长参数时，确定与异常生长参数对应的农作物的生育期；根据生育期确定对应的至少一个预设病虫害参考图像，并判断生长图像信息是否与任一预设病虫害参考图像匹配；在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属
性信息确定对农作物进行除虫操作的喷灌参数。
在该技术方案中，通过在检测到农作物的生长图像信息中存在异常生长参数时，进一步地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
具体地，首先，获取的农作物的生长图像信息的特征生长参数(如表1所示的以时间参数界定的生长状态和茎高等尺寸)，其中，生长图像信息具备地理区域属性的，通过对特征生长参数分析来确定农作物属于异常生长，其次，将生长图像信息与预设病虫害参考图像比对，不仅可以快速确定病虫害类型，也可以及时确定病虫害程度，并且，采用电控的喷灌终端，针对性地对出现病虫害的地理区域的农作物进行喷灌。
其中，以黄瓜为种植的农作物的一个例子，则黄瓜的生育期如下表1所示。
在上述技术方案中，优选地，检测到农作物的生长图像信息中存在异常生长参数，具体包括：识别农作物的生长图像信息的特征生长参数；判断特征生长参数是否与预设特征生长参数匹配；在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
在该技术方案中，通过识别农作物的生长图像信息的特征生长参数，判断特征生长参数是否与预设特征生长参数匹配，通过在判定特征生长参数与预设特征生长参数不匹配时，将特征生长参数确定为异常生长参数，其中，特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，及时且准确地判断农作物是否属于异常生长。
具体地，预设生长参数特征生长参数包括农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个，例如，黄瓜在结蔓期的藤蔓长度可达三米以上，叶片呈现掌状，叶片大而薄且呈绿色，如农作物
在结蔓期茎长不足两米，则判断农作物属于异常生长，或叶片颜色为偏黄色或出现斑点，也判断农作物属于异常生长。
在上述任一项技术方案中，优选地，生育期为农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
在上述任一项技术方案中，优选地，农作物为黄瓜时，发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，抽蔓期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和守瓜参考图像，结果期对应的预设病虫害参考图像包括霜霉病参考图像、疫病参考图像、靶斑病参考图像、细菌性角斑病参考图像、枯萎病参考图像、上述白粉病参考图像、蔓枯病参考图像、灰霉病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像、斑潜蝇参考图像和瓜绢螟参考图像。
在该技术方案中，通过不同生育期对应的多种预设病虫害参考图像，直观清楚地确定了农作物因病虫害出现症状，全面地考虑了引起农作物生长异常的原因，进而提高处理农作物因病虫害出现生长异常问题的效率。
在上述任一项技术方案中，优选地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，具体包括：计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度；在判定匹配度大于或等于预设匹配度时，确定生长图像信息与预设病虫害参考图像匹配；读取匹配的预设病虫害参考图像的属性信息；根据属性信息确定对农作物进行除虫操作的喷灌参数，其中，喷灌参数包括农药类型、农药液量和除虫方式，除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
在该技术方案中，通过计算生长图像信息与生育期对应的任一预设病虫害参考图像之间的匹配度，通过在判定匹配度大于或等于预设匹配度时，
确定生长图像信息与预设病虫害参考图像匹配，通过读取匹配的预设病虫害参考图像的属性信息，根据属性信息确定对农作物进行除虫操作的喷灌参数，通过计算更加直观反映农作物出现生长异常原因，简化了人工进行图像信息比对的步骤，节省了时间和人力资源，提高了处理农作物出现生长异常问题的准确性和效率。
其中，若生长图像信息与预设病虫害参考图像之间的匹配程度达到设定匹配度(如预设匹配度大于或等于80％)，则判断作物图像中的作物具有与匹配图像相同的病虫害或生长异常。
以上结合附图详细说明了本发明的技术方案，本发明提出了一种种植参数调控方法和种植参数调控装置，通过在检测到农作物的生长图像信息中存在异常生长参数时，进一步地，在判定生长图像信息与任一预设病虫害参考图像匹配时，根据匹配的预设病虫害参考图像的属性信息确定对农作物进行除虫操作的喷灌参数，也即根据匹配的预设病虫害参考图像，及时地确定对农作物进行除虫操作的喷灌参数，也即及时地解决了农作物的病虫害问题，降低了除虫除病的人工成本，提高了农作物的存活率和产量。
本发明方法中的步骤可根据实际需要进行顺序调整、合并和删减。
本发明装置中的单元可根据实际需要进行合并、划分和删减。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质包括只读存储器(Read-Only Memory，ROM)、随机存储器(Random Access Memory，RAM)、可编程只读存储器(Programmable Read-only Memory，PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory，EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory，OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory，EEPROM)、只读光盘(Compact Disc Read-Only Memory，CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于
本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。
Claims (10)
- 一种种植参数调控方法，其特征在于，包括：在检测到农作物的生长图像信息中存在异常生长参数时，确定与所述异常生长参数对应的所述农作物的生育期；根据所述生育期确定对应的至少一个预设病虫害参考图像，并判断所述生长图像信息是否与任一所述预设病虫害参考图像匹配；在判定所述生长图像信息与任一所述预设病虫害参考图像匹配时，根据匹配的所述预设病虫害参考图像的属性信息确定对所述农作物进行除虫操作的喷灌参数。
- 根据权利要求1所述的种植参数调控方法，其特征在于，所述检测到农作物的生长图像信息中存在异常生长参数，具体包括：识别所述农作物的生长图像信息的特征生长参数；判断所述特征生长参数是否与预设特征生长参数匹配；在判定所述特征生长参数与所述预设特征生长参数不匹配时，将所述特征生长参数确定为所述异常生长参数，其中，所述特征生长参数包括所述农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
- 根据权利要求1所述的种植参数调控方法，其特征在于，所述生育期为所述农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
- 根据权利要求3所述的种植参数调控方法，其特征在于，所述农作物为黄瓜时，所述发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，所述幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，所述抽蔓期对应的预设病虫害参考图像包括所述霜霉病参考图像、所述疫病参考图像、所述炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、 粉虱参考图像和所述守瓜参考图像，所述结果期对应的预设病虫害参考图像包括所述霜霉病参考图像、所述疫病参考图像、所述靶斑病参考图像、所述细菌性角斑病参考图像、所述枯萎病参考图像、上述白粉病参考图像、所述蔓枯病参考图像、所述灰霉病参考图像、所述蚜虫参考图像、所述蓟马参考图像、所述粉虱参考图像、所述斑潜蝇参考图像和瓜绢螟参考图像。
- 根据权利要求1至4中任一项所述的种植参数调控方法，其特征在于，所述在判定所述生长图像信息与任一所述预设病虫害参考图像匹配时，根据匹配的所述预设病虫害参考图像的属性信息确定对所述农作物进行除虫操作的喷灌参数，具体包括：计算所述生长图像信息与所述生育期对应的任一所述预设病虫害参考图像之间的匹配度；在判定所述匹配度大于或等于预设匹配度时，确定所述生长图像信息与所述预设病虫害参考图像匹配；读取匹配的所述预设病虫害参考图像的属性信息；根据所述属性信息确定对所述农作物进行除虫操作的喷灌参数，其中，所述喷灌参数包括农药类型、农药液量和除虫方式，所述除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
- 一种种植参数调控装置，其特征在于，包括：确定单元，用于在检测到农作物的生长图像信息中存在异常生长参数时，确定与所述异常生长参数对应的所述农作物的生育期；所述确定单元还用于：根据所述生育期确定对应的至少一个预设病虫害参考图像，并判断所述生长图像信息是否与任一所述预设病虫害参考图像匹配；所述确定单元还用于：在判定所述生长图像信息与任一所述预设病虫害参考图像匹配时，根据匹配的所述预设病虫害参考图像的属性信息确定对所述农作物进行除虫操作的喷灌参数。
- 根据权利要求6所述的种植参数调控装置，其特征在于，还包括：识别单元，用于识别所述农作物的生长图像信息的特征生长参数；判断单元，用于判断所述特征生长参数是否与预设特征生长参数匹配；所述确定单元还用于：在判定所述特征生长参数与所述预设特征生长参数不匹配时，将所述特征生长参数确定为所述异常生长参数，其中，所述特征生长参数包括所述农作物的茎尺寸、茎颜色、叶片颜色、相邻叶片尺寸的差异度中的至少一个。
- 根据权利要求6所述的种植参数调控装置，其特征在于，所述生育期为所述农作物的发芽期、幼苗期、抽蔓期和结果期中的一个时间段。
- 根据权利要求8所述的种植参数调控装置，其特征在于，所述农作物为黄瓜时，所述发芽期对应的预设病虫害参考图像包括猝倒病参考图像和地下害虫参考图像，所述幼苗期对应的预设病虫害参考图像包括立枯病参考图像、根腐病参考图像、炭疽病参考图像、霜霉病参考图像、疫病参考图像、瓜蚜参考图像、守瓜参考图像和斑潜蝇参考图像，所述抽蔓期对应的预设病虫害参考图像包括所述霜霉病参考图像、所述疫病参考图像、所述炭疽病参考图像、枯萎病参考图像、白粉病参考图像、靶斑病参考图像、细菌性角斑病参考图像、蚜虫参考图像、蓟马参考图像、粉虱参考图像和所述守瓜参考图像，所述结果期对应的预设病虫害参考图像包括所述霜霉病参考图像、所述疫病参考图像、所述靶斑病参考图像、所述细菌性角斑病参考图像、所述枯萎病参考图像、上述白粉病参考图像、所述蔓枯病参考图像、所述灰霉病参考图像、所述蚜虫参考图像、所述蓟马参考图像、所述粉虱参考图像、所述斑潜蝇参考图像和瓜绢螟参考图像。
- 根据权利要求6至9中任一项所述的种植参数调控装置，其特征在于，还包括：计算单元，用于计算所述生长图像信息与所述生育期对应的任一所述预设病虫害参考图像之间的匹配度；所述确定单元还用于：在判定所述匹配度大于或等于预设匹配度时，确定所述生长图像信息与所述预设病虫害参考图像匹配；所述种植参数调控装置还包括：读取单元，用于读取匹配的所述预设病虫害参考图像的属性信息；所述确定单元还用于：根据所述属性信息确定对所述农作物进行除虫 操作的喷灌参数，其中，所述喷灌参数包括农药类型、农药液量和除虫方式，所述除虫方式包括喷淋农药除虫方式和/或灌溉农药除虫方式。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710525615.X | 2017-06-30 | ||
| CN201710525615.XA CN107211706A (zh) | 2017-06-30 | 2017-06-30 | 种植参数调控方法和种植参数调控装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019000563A1 true WO2019000563A1 (zh) | 2019-01-03 |
Family
ID=59951707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2017/096258 WO2019000563A1 (zh) | 2017-06-30 | 2017-08-07 | 种植参数调控方法和种植参数调控装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107211706A (zh) |
| WO (1) | WO2019000563A1 (zh) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107211706A (zh) * | 2017-06-30 | 2017-09-29 | 深圳前海弘稼科技有限公司 | 种植参数调控方法和种植参数调控装置 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102334422A (zh) * | 2010-07-27 | 2012-02-01 | 中国农业科学院蔬菜花卉研究所 | 基于机器视觉的蔬菜叶部病害实时诊断方法与系统 |
| CN104766152A (zh) * | 2015-01-30 | 2015-07-08 | 安徽大学 | 一种作物病害识别与病情评估装置 |
| CN105407318A (zh) * | 2015-10-29 | 2016-03-16 | 桂林市腾瑞电子科技有限公司 | 一种智能喷药系统 |
| CN107211706A (zh) * | 2017-06-30 | 2017-09-29 | 深圳前海弘稼科技有限公司 | 种植参数调控方法和种植参数调控装置 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021939A (zh) * | 2007-03-29 | 2007-08-22 | 沈阳理工大学 | 基于计算机图像处理的农作物病害诊断系统 |
| CN205249868U (zh) * | 2015-12-03 | 2016-05-25 | 韩山师范学院 | 物联网智能农场种植系统 |
| CN106097119A (zh) * | 2016-06-14 | 2016-11-09 | 广州大气候农业科技有限公司 | 采集装置、服务器、及信息采集、推送、获取及发送方法 |
-
2017
- 2017-06-30 CN CN201710525615.XA patent/CN107211706A/zh active Pending
- 2017-08-07 WO PCT/CN2017/096258 patent/WO2019000563A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102334422A (zh) * | 2010-07-27 | 2012-02-01 | 中国农业科学院蔬菜花卉研究所 | 基于机器视觉的蔬菜叶部病害实时诊断方法与系统 |
| CN104766152A (zh) * | 2015-01-30 | 2015-07-08 | 安徽大学 | 一种作物病害识别与病情评估装置 |
| CN105407318A (zh) * | 2015-10-29 | 2016-03-16 | 桂林市腾瑞电子科技有限公司 | 一种智能喷药系统 |
| CN107211706A (zh) * | 2017-06-30 | 2017-09-29 | 深圳前海弘稼科技有限公司 | 种植参数调控方法和种植参数调控装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107211706A (zh) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Neethling et al. | Assessing local climate vulnerability and winegrowers’ adaptive processes in the context of climate change | |
| TWI574607B (zh) | 用於作物的施藥系統及其施藥方法 | |
| CN102954816B (zh) | 作物长势的监测方法 | |
| US11676261B2 (en) | Image data for improving and diagnosing sprinkler controller performance | |
| US20150309496A1 (en) | Control system and method for landscape maintenance | |
| CN107392785B (zh) | 种植参数调控方法和种植参数调控装置 | |
| CN104764533A (zh) | 基于无人机图像采集和红外热像仪的智能农业系统 | |
| Bramley et al. | Spatio‐temporal variability in vine vigour and yield in a Marlborough Sauvignon Blanc vineyard | |
| CN110598532B (zh) | 一种树木病虫害监控系统及方法 | |
| EP3804518A1 (en) | Method and system for selective, to flower set adapted, spraying of orchards | |
| AU2019263121A1 (en) | Systems and methods for applying an agricultural practice to a target agricultural field | |
| WO2019000563A1 (zh) | 种植参数调控方法和种植参数调控装置 | |
| CN109906833A (zh) | 一种基于大数据的温室智能管理系统 | |
| CN112699729A (zh) | 一种无人机察打一体除草方法 | |
| WO2021087685A1 (zh) | 结合多光谱和地表语义的作业规划方法、装置及设备 | |
| KR102652306B1 (ko) | 식물 성장 관리 장치 | |
| Sozzi et al. | On-the-go variable rate fertilizer application on vineyard using a proximal spectral sensor | |
| KR20150066145A (ko) | 밭관개 자동운영관리 시스템 및 방법 | |
| CN108958201A (zh) | 园林养护装置及园林养护方法 | |
| CN109769606A (zh) | 一种基于互联网的小麦病虫害防治方法 | |
| CN115082706A (zh) | 一种病虫害识别方法、装置、设备及可读存储介质 | |
| CN115511158A (zh) | 一种基于大数据的农作物智能选育分析方法及系统 | |
| KR102399956B1 (ko) | 인공지능 분석 기반 스마트 잔디 매니지먼트 시스템 | |
| Smith et al. | Spatial aspects of vineyard management and wine grape production | |
| WO2020084414A1 (en) | Yield and market analytics |
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: 17916234 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 05.06.2020) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 17916234 Country of ref document: EP Kind code of ref document: A1 |