CN111723736A - Fruit tree flowering phase monitoring method and device, computer equipment and storage medium - Google Patents
Fruit tree flowering phase monitoring method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111723736A CN111723736A CN202010564544.6A CN202010564544A CN111723736A CN 111723736 A CN111723736 A CN 111723736A CN 202010564544 A CN202010564544 A CN 202010564544A CN 111723736 A CN111723736 A CN 111723736A
- Authority
- CN
- China
- Prior art keywords
- fruit tree
- flower
- tree flower
- global
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 259
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000013145 classification model Methods 0.000 claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000001629 suppression Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 241000220225 Malus Species 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 101100518501 Mus musculus Spp1 gene Proteins 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000132456 Haplocarpha Species 0.000 description 1
- 235000021016 apples Nutrition 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for monitoring the flowering phase of a fruit tree, computer equipment and a storage medium, relates to the technical field of visual recognition, and is used for improving the accuracy of monitoring the flowering phase of the fruit tree. The main technical scheme of the invention is as follows: acquiring a global image of a target fruit tree, and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image; intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers; inputting each fruit tree flower subgraph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label; and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
Description
Technical Field
The invention relates to the technical field of visual identification, in particular to a method and a device for monitoring flowering phase of fruit trees, computer equipment and a storage medium.
Background
Before and after the fruit trees bloom, the temperature rises quickly, diseases and pests start to move in succession, and the fruit trees are harmed. The flowering period is an important period for preventing and controlling various diseases and pests, and if the management is not good, the yield and the quality are seriously influenced, even the harvest is stopped, and the major loss is brought, so that the monitoring of the flowering period of the fruit trees becomes more important. The existing monitoring method also adopts empirical values or simple mathematical regression, and has low accuracy.
Disclosure of Invention
The invention provides a method and a device for monitoring the flowering phase of a fruit tree, computer equipment and a storage medium, which are used for improving the accuracy of monitoring the flowering phase of the fruit tree.
The embodiment of the invention provides a method for monitoring the flowering phase of a fruit tree, which comprises the following steps:
acquiring a global image of a target fruit tree, and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
inputting each fruit tree flower subgraph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
The embodiment of the invention provides a fruit tree florescence monitoring device, which comprises:
the first acquisition module is used for acquiring a global image of a target fruit tree and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
the intercepting module is used for intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
the second acquisition module is used for inputting each fruit tree flower subgraph into the classification model to obtain the fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and the determining module is used for determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
A computer device comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the fruit tree florescence monitoring method.
A computer-readable storage medium, which stores a computer program, which when executed by a processor, implements the above-mentioned method for monitoring flowering of fruit trees.
The invention provides a method, a device, computer equipment and a storage medium for monitoring the flowering phase of a fruit tree, which are characterized in that firstly, a global image of a target fruit tree is obtained, and the global image is input into a detection model to obtain the position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image; intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers; inputting each fruit tree flower subgraph into a classification model to obtain the fruit tree flower state corresponding to each fruit tree flower subgraph; and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs. Compared with the current method for monitoring the flowering phase of the fruit tree by adopting empirical values or simple mathematical regression, the method extracts the fruit tree flower subgraphs respectively corresponding to each fruit tree flower from the shot global image, inputs the fruit tree flower subgraphs into the classification model to obtain the fruit tree flower states respectively corresponding to each fruit tree flower subgraph, and can accurately determine the states of each fruit tree flower through the classification model because the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label, so that the flowering phase of the target fruit tree can be determined according to the determined fruit tree flower states, and the accuracy of monitoring the flowering phase of the fruit tree can be improved through the method.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a method for monitoring flowering phase of fruit trees according to an embodiment of the present invention;
FIG. 2 is a schematic view of a method for monitoring flowering phase of fruit trees according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a detection box in a global image according to an embodiment of the present invention;
FIG. 4 is a diagram of a classification model architecture in accordance with an embodiment of the present invention;
FIG. 5 is an exemplary diagram of images of apple flowers in different states according to one embodiment of the present invention;
FIG. 6 is a flow chart of determining the flowering status of a target fruit tree according to an embodiment of the present invention
FIG. 7 is a schematic block diagram of a fruit tree flowering phase monitoring apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method for monitoring the flowering phase of the fruit tree provided by the invention is used for comprehensively predicting the flowering phases of the fruit tree in the initial flowering phase and the full flowering phase by calculating the proportion of the number of the fruit tree flowers in a bud state, a semi-open state and a full-open state to the number of all the fruit tree flowers. The core of the method is that a detection model and a classification model are trained by utilizing a deep convolutional neural network, so that the accurate prediction of the position of the fruit tree flower in a global image and the correct judgment of the state of the fruit tree flower are realized. In the following, apple flowers are taken as an example, and a specific embodiment is provided for the steps of the method for monitoring the flowering phase of fruit trees.
As shown in fig. 1, an embodiment of the present invention provides a method for monitoring flowering phase of a fruit tree, which specifically includes the following steps:
s10, obtaining a global image of the target fruit tree, and inputting the global image into a detection model to obtain the position coordinates of all types of fruit tree flowers in the global image.
In the embodiment of the invention, the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image. The types of the fruit tree flowers may include a flower bud, a semi-open state, a fully-open state, and the like, and the embodiment of the present invention is not particularly limited. Specifically, the detection model is obtained by training in the following way: acquiring the global sample image, wherein the global sample image comprises fruit tree flower types and position coordinates corresponding to the flowers respectively; and training the global image sample through a target detection algorithm to obtain the detection model.
In this embodiment of the present invention, the training the global image sample through the target detection algorithm to obtain the detection model includes: scaling the global image sample to a preset size, and then inputting the scaled global image sample into an SSD model to obtain feature maps with different sizes through convolution operation; generating prediction frames aiming at feature maps with different sizes, and obtaining the coordinate and classification result of each prediction frame through convolution operation; calculating the coordinates and classification results of the prediction frame through a non-maximum suppression algorithm to obtain a final detection result; and calculating position error loss and classification loss according to the detection result, and performing back propagation to update parameters of the detection model.
Specifically, the global image is scaled to 300 × 300 pixels and input into the SSD model, feature maps of 38 × 38, 19 × 19, 10 × 10, 5 × 5, 3 × 3, and 1 × 1 are sequentially generated by convolution operations, and the targets are detected using the feature maps of different sizes, the large feature map is used to detect small targets, and the small feature map is used to detect large targets. It should be noted that, because the feature map obtained by the model after convolution operation is smaller and smaller, and the receptive field of each point in the smaller feature map is larger, the smaller feature map is used for detecting a large target; the field of view of each point in the larger feature map is smaller, so the larger feature map is used to detect small targets. Wherein, the characteristic diagram mainly refers to color and shape characteristics.
Then, generating prediction frames according to the feature maps with different sizes, and obtaining the coordinates and classification results of each prediction frame through convolution operation. Specifically, for a feature map with a size of m × n, mn units are total, if the number of prediction frames set for each unit is k, each unit needs (c +4) × k prediction values, and all units need (c +4) × kmn prediction values in total, then (c +4) × k convolution kernels need to be used to complete the detection process of the feature map.
And finally, obtaining a final detection result through a non-maximum suppression (NMS) algorithm. And calculating the position error loss and the classification loss according to the detection result, and performing back propagation to update the model parameters. The detection is not limited to the SSD algorithm, and other object detection methods based on deep learning can be applied. For each prediction box, firstly, the category (the one with the maximum confidence) and the confidence value of the prediction box are determined according to the category confidence, and the prediction boxes belonging to the background are filtered. Then, the prediction boxes with lower thresholds are filtered according to confidence threshold values (such as 0.5), and then the prediction boxes are arranged in descending order according to the confidence values, and only top-k prediction boxes are reserved. And finally, carrying out NMS algorithm to filter the prediction boxes with larger overlapping degree. The last remaining prediction box is the detection result.
In the embodiment of the invention, because the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinate in the global sample image, the position coordinates of all types of fruit tree flowers in the global image can be accurately obtained by inputting the global image into the detection model (as shown in fig. 3), so that the fruit tree flower subgraph can be accurately intercepted in the subsequent steps according to the position coordinates of the type fruit tree flowers.
And S20, intercepting the fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers.
It should be noted that each of the position coordinates of the fruit tree flowers corresponds to one fruit tree flower, and the image of the corresponding flower can be captured from the global image through the position coordinates of the fruit tree flowers. Thereby identifying the state of the flower from the intercepted image in a subsequent step.
And S30, inputting each fruit tree flower sub-graph into a classification model to obtain the fruit tree flower state corresponding to each fruit tree flower sub-graph.
And the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label. Specifically, the classification model is obtained by training in the following way: obtaining the fruit tree flower sample sub-graph, wherein the fruit tree flower sample sub-graph is an image comprising one flower, and the fruit tree flower state labels in the fruit tree flower sample sub-graph comprise a flower bud state label, a semi-open state label and a fully-open state label; and training the fruit tree flower sample subgraph through a deep convolutional neural network structure to obtain the classification model.
In an embodiment provided by the present invention, as shown in fig. 4, the training of the fruit tree flower sample subgraph through the deep convolutional neural network structure to obtain the classification model includes: and sequentially carrying out 5 × 5 convolution, 3 × 3 convolution, 2 × 2 maximum pooling, 2 × 2 convolution and full connection operation on the fruit tree flower sample subgraph input into the deep convolution neural network structure, and finally obtaining the category of the input fruit tree flower sample subgraph through a softmax layer.
S40, determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
Wherein, the flower state of the fruit tree comprises a bud state, a semi-open state and a full-open state (as shown in fig. 5). As shown in fig. 6, step S40 determines the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all fruit tree flower subgraphs, including:
s401, calculating the ratio of the number of the flowers in the bud state, the semi-open state and the full-open state to the number of all the flowers respectively.
For the embodiment of the invention, after the flowering phase state of the target fruit tree is determined according to the fruit tree flower state corresponding to all the fruit tree flower subgraphs, the number N of apple flowers in all the global images and the numbers N1, N2 and N3 of the apple flowers in a flower bud state, a semi-open state and a fully-open state are counted, and the flowering rate is calculated:
η1＝n1/N*100％
η2＝n2/N*100％
η3＝n3/N*100％
and comprehensively considering the values of eta 1, eta 2 and eta 3 to monitor the flowering period of the apples.
S402, determining the flowering phase state of the target fruit tree according to the percentage value of the bud state, the semi-open state and the full-open state.
Specifically, the flowering phase of the target fruit tree is monitored according to the specific numerical values of eta 1, eta 2 and eta 3. If the initial flowering period is set as follows: full-open 10%, half-open 20%, bud 70%; the full-bloom period is set as follows: full-open 80%, half-open 15%, flower bud 5%. It should be noted that the percentage values of the various bud states, the half-open state and the full-open state in the initial flowering period and the full flowering period may be set according to actual requirements, and the percentage values of the various states are not specifically limited in the embodiment of the present invention.
The invention provides a fruit tree florescence monitoring method, which comprises the steps of firstly obtaining a global image of a target fruit tree, inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image; intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers; inputting each fruit tree flower subgraph into a classification model to obtain the fruit tree flower state corresponding to each fruit tree flower subgraph; and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs. Compared with the current method for monitoring the flowering phase of the fruit tree by adopting empirical values or simple mathematical regression, the method extracts the fruit tree flower subgraphs respectively corresponding to each fruit tree flower from the shot global image, inputs the fruit tree flower subgraphs into the classification model to obtain the fruit tree flower states respectively corresponding to each fruit tree flower subgraph, and can accurately determine the states of each fruit tree flower through the classification model because the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label, so that the flowering phase of the target fruit tree can be determined according to the determined fruit tree flower states, and the accuracy of monitoring the flowering phase of the fruit tree can be improved through the method.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, a device for monitoring the flowering phase of a fruit tree is provided, and the device for monitoring the flowering phase of the fruit tree corresponds to the method for monitoring the flowering phase of the fruit tree in the above embodiments one to one. As shown in fig. 7, the fruit tree flowering phase monitoring device comprises: the device comprises a first acquisition module 10, an interception module 20, a second acquisition module 30 and a determination module 40. The functional modules are explained in detail as follows:
the first acquisition module 10 is configured to acquire a global image of a target fruit tree, and input the global image into a detection model to obtain position coordinates of all types of fruit trees and flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
an intercepting module 20, configured to intercept a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
the second obtaining module 30 is configured to input each fruit tree flower sub-graph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower sub-graph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and the determining module 40 is configured to determine the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
Specifically, the determining module 40 includes:
a calculating unit 41, configured to calculate ratio values of the number of flowers in the bud state, the half-open state, and the full-open state to the number of all flowers respectively;
and the determining unit 42 is configured to determine the flowering phase state of the target fruit tree according to the percentage value of the bud state, the semi-open state and the full-open state.
In one embodiment provided by the present invention, the detection model is obtained by training in the following way:
acquiring the global sample image, wherein the global sample image comprises fruit tree flower types and position coordinates corresponding to the flowers respectively;
and training the global image sample through a target detection algorithm to obtain the detection model.
Specifically, the training the global image sample through the target detection algorithm to obtain the detection model includes:
scaling the global image sample to a preset size, and then inputting the scaled global image sample into an SSD model to obtain feature maps with different sizes through convolution operation;
generating prediction frames aiming at feature maps with different sizes, and obtaining the coordinate and classification result of each prediction frame through convolution operation;
calculating the coordinates and classification results of the prediction frame through a non-maximum suppression algorithm to obtain a final detection result;
and calculating position error loss and classification loss according to the detection result, and performing back propagation to update parameters of the detection model.
In an embodiment provided by the present invention, the classification model is obtained by training in the following way:
obtaining the fruit tree flower sample sub-graph, wherein the fruit tree flower sample sub-graph is an image comprising one flower, and the fruit tree flower state labels in the fruit tree flower sample sub-graph comprise a flower bud state label, a semi-open state label and a fully-open state label;
and training the fruit tree flower sample subgraph through a deep convolutional neural network structure to obtain the classification model.
Specifically, the training of the fruit tree flower sample subgraph through the deep convolutional neural network structure to obtain the classification model includes:
and sequentially carrying out 5 × 5 convolution, 3 × 3 convolution, 2 × 2 maximum pooling, 2 × 2 convolution and full connection operation on the fruit tree flower sample subgraph input into the deep convolution neural network structure, and finally obtaining the category of the input fruit tree flower sample subgraph through a softmax layer.
For specific limitations of the fruit tree flowering monitoring device, reference may be made to the above limitations of the fruit tree flowering monitoring method, and details are not repeated here. All or part of the modules in the fruit tree flowering phase monitoring device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a fruit tree flowering phase monitoring method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a global image of a target fruit tree, and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
inputting each fruit tree flower subgraph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a global image of a target fruit tree, and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
inputting each fruit tree flower subgraph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method for monitoring the flowering phase of a fruit tree is characterized by comprising the following steps:
acquiring a global image of a target fruit tree, and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
inputting each fruit tree flower subgraph into a classification model to obtain a fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
2. The method for monitoring flowering phase of fruit trees as claimed in claim 1, wherein the fruit tree flower state comprises a bud state, a semi-open state and a fully open state, and the determining the flowering phase of the target fruit tree according to the fruit tree flower states corresponding to all fruit tree flower subgraphs comprises:
calculating the ratio of the number of the flowers in the bud state, the semi-open state and the full-open state to the number of all the flowers respectively;
and determining the flowering phase state of the target fruit tree according to the percentage value of the bud state, the semi-open state and the full-open state.
3. The fruit tree flowering monitoring method according to claim 1, wherein the detection model is trained by:
acquiring the global sample image, wherein the global sample image comprises fruit tree flower types and position coordinates corresponding to the flowers respectively;
and training the global image sample through a target detection algorithm to obtain the detection model.
4. The fruit tree flowering monitoring method according to claim 3, wherein the training of the global image samples through a target detection algorithm to obtain the detection model comprises:
scaling the global image sample to a preset size, and then inputting the scaled global image sample into an SSD model to obtain feature maps with different sizes through convolution operation;
generating prediction frames aiming at feature maps with different sizes, and obtaining the coordinates and classification results of each prediction frame through convolution operation;
calculating the coordinates and classification results of the prediction frame through a non-maximum suppression algorithm to obtain a final detection result;
and calculating position error loss and classification loss according to the detection result, and performing back propagation to update parameters of the detection model.
5. The fruit tree flowering monitoring method according to claim 1, wherein the classification model is trained by:
obtaining the fruit tree flower sample sub-graph, wherein the fruit tree flower sample sub-graph is an image comprising one flower, and the fruit tree flower state labels in the fruit tree flower sample sub-graph comprise a flower bud state label, a semi-open state label and a fully-open state label;
and training the fruit tree flower sample subgraph through a deep convolutional neural network structure to obtain the classification model.
6. The fruit tree flowering monitoring method of claim 5, wherein the training of the fruit tree flower sample subgraph through a deep convolutional neural network structure to obtain the classification model comprises:
and sequentially carrying out 5 × 5 convolution, 3 × 3 convolution, 2 × 2 maximum pooling, 2 × 2 convolution and full connection operation on the fruit tree flower sample subgraph input into the deep convolution neural network structure, and finally obtaining the category of the input fruit tree flower sample subgraph through a softmax layer.
7. The fruit tree florescence monitoring device is characterized by comprising:
the first acquisition module is used for acquiring a global image of a target fruit tree and inputting the global image into a detection model to obtain position coordinates of all types of fruit tree flowers in the global image; the detection model is obtained by training according to the global sample image and the corresponding fruit tree flower type and position coordinates in the global sample image;
the intercepting module is used for intercepting a fruit tree flower subgraph in the global image according to the position coordinates of all types of fruit tree flowers;
the second acquisition module is used for inputting each fruit tree flower subgraph into the classification model to obtain the fruit tree flower state corresponding to each fruit tree flower subgraph; the classification model is obtained by training according to the fruit tree flower sample subgraph and the corresponding fruit tree flower state label;
and the determining module is used for determining the flowering phase state of the target fruit tree according to the fruit tree flower states corresponding to all the fruit tree flower subgraphs.
8. The fruit tree flowering monitoring device of claim 7, wherein the determining module comprises:
the calculating unit is used for calculating the ratio of the number of the flowers in the bud state, the semi-open state and the full-open state to the number of all the flowers;
and the determining unit is used for determining the flowering phase state of the target fruit tree according to the percentage value of the bud state, the semi-open state and the full-open state.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of flowering monitoring of fruit trees as claimed in any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for monitoring flowering of fruit trees according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564544.6A CN111723736A (en) | 2020-06-19 | 2020-06-19 | Fruit tree flowering phase monitoring method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564544.6A CN111723736A (en) | 2020-06-19 | 2020-06-19 | Fruit tree flowering phase monitoring method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111723736A true CN111723736A (en) | 2020-09-29 |
Family
ID=72567626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010564544.6A Pending CN111723736A (en) | 2020-06-19 | 2020-06-19 | Fruit tree flowering phase monitoring method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723736A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332849A (en) * | 2022-03-16 | 2022-04-12 | 科大天工智能装备技术（天津）有限公司 | Crop growth state combined monitoring method and device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846826A (en) * | 2018-04-24 | 2018-11-20 | 深圳大学 | Object detecting method, device, image processing equipment and storage medium |
| CN109492665A (en) * | 2018-09-28 | 2019-03-19 | 江苏省无线电科学研究所有限公司 | Detection method, device and the electronic equipment of growth period duration of rice |
| CN109815846A (en) * | 2018-12-29 | 2019-05-28 | 腾讯科技（深圳）有限公司 | Image processing method, device, storage medium and electronic device |
| CN109886155A (en) * | 2019-01-30 | 2019-06-14 | 华南理工大学 | Man power single stem rice detection localization method, system, equipment and medium based on deep learning |
| CN110070101A (en) * | 2019-03-12 | 2019-07-30 | 平安科技（深圳）有限公司 | Floristic recognition methods and device, storage medium, computer equipment |
| CN110544251A (en) * | 2019-09-08 | 2019-12-06 | 刘凡 | Dam crack detection method based on multi-migration learning model fusion |
| CN111160079A (en) * | 2019-06-28 | 2020-05-15 | 广西慧云信息技术有限公司 | Method for rapidly identifying flowering phase of citrus |
-
2020
- 2020-06-19 CN CN202010564544.6A patent/CN111723736A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846826A (en) * | 2018-04-24 | 2018-11-20 | 深圳大学 | Object detecting method, device, image processing equipment and storage medium |
| CN109492665A (en) * | 2018-09-28 | 2019-03-19 | 江苏省无线电科学研究所有限公司 | Detection method, device and the electronic equipment of growth period duration of rice |
| CN109815846A (en) * | 2018-12-29 | 2019-05-28 | 腾讯科技（深圳）有限公司 | Image processing method, device, storage medium and electronic device |
| CN109886155A (en) * | 2019-01-30 | 2019-06-14 | 华南理工大学 | Man power single stem rice detection localization method, system, equipment and medium based on deep learning |
| CN110070101A (en) * | 2019-03-12 | 2019-07-30 | 平安科技（深圳）有限公司 | Floristic recognition methods and device, storage medium, computer equipment |
| CN111160079A (en) * | 2019-06-28 | 2020-05-15 | 广西慧云信息技术有限公司 | Method for rapidly identifying flowering phase of citrus |
| CN110544251A (en) * | 2019-09-08 | 2019-12-06 | 刘凡 | Dam crack detection method based on multi-migration learning model fusion |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332849A (en) * | 2022-03-16 | 2022-04-12 | 科大天工智能装备技术（天津）有限公司 | Crop growth state combined monitoring method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110599451B (en) | Medical image focus detection and positioning method, device, equipment and storage medium | |
| CN109035299B (en) | Target tracking method and device, computer equipment and storage medium | |
| JP7167306B2 (en) | Neural network model training method, apparatus, computer equipment and storage medium | |
| CN107392091B (en) | Agricultural artificial intelligence crop detection method, mobile terminal and computer readable medium | |
| CN109344843B (en) | Method and device for extracting rice seedling row line, computer equipment and storage medium | |
| CN110807491A (en) | License plate image definition model training method, definition detection method and device | |
| CN111723863B (en) | Fruit tree flower identification and position acquisition method and device, computer equipment and storage medium | |
| CN113705685B (en) | Disease feature recognition model training, disease feature recognition method, device and equipment | |
| CN111476191B (en) | Artificial intelligent image processing method based on intelligent traffic and big data cloud server | |
| CN111897695B (en) | Method and device for acquiring KPI abnormal data sample and computer equipment | |
| CN110555875A (en) | Pupil radius detection method and device, computer equipment and storage medium | |
| CN110008082B (en) | Abnormal task intelligent monitoring method, device, equipment and storage medium | |
| JP2011180845A5 (en) | Inference apparatus, control method thereof, and program | |
| CN112132278A (en) | Model compression method and device, computer equipment and storage medium | |
| CN109711381B (en) | Target identification method and device of remote sensing image and computer equipment | |
| CN111124898B (en) | Question-answering system testing method and device, computer equipment and storage medium | |
| CN111723736A (en) | Fruit tree flowering phase monitoring method and device, computer equipment and storage medium | |
| CN110837783A (en) | Automatic warning method, device and storage medium for suspicious people coming from outside in intelligent community | |
| CN113763960B (en) | Post-processing method and device for model output and computer equipment | |
| CN111178126A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN117315466B (en) | Growth monitoring management method and system | |
| CN111444833B (en) | Fruit actual measurement production method, device, computer equipment and storage medium | |
| CN109407630B (en) | Parameter calculation method, device, terminal and readable storage medium | |
| CN111898035A (en) | Data processing strategy configuration method and device based on Internet of things and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |