CN108573199A - A kind of disaster-stricken grade determination method of Chinese pine and its decision-making system - Google Patents
A kind of disaster-stricken grade determination method of Chinese pine and its decision-making system Download PDFInfo
- Publication number
- CN108573199A CN108573199A CN201710150677.7A CN201710150677A CN108573199A CN 108573199 A CN108573199 A CN 108573199A CN 201710150677 A CN201710150677 A CN 201710150677A CN 108573199 A CN108573199 A CN 108573199A
- Authority
- CN
- China
- Prior art keywords
- disaster
- chinese pine
- stricken
- sample
- chinese
- 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.)
- Granted
Links
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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23211—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with adaptive number of clusters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The present invention discloses a kind of disaster-stricken grade determination method of Chinese pine and its decision-making system, wherein the determination method includes the following steps：S1：Pass through the video camera that is carried on unmanned plane with shooting Chinese pine sample image；S2：Region segmentation is carried out using the disaster-stricken Chinese pine in two type fuzzy clustering algorithms to the Chinese pine sample image, and calculates the ratio in disaster-stricken Chinese pine region with accounting for Chinese pine sample region；S3：The mistake leaf rate of combined ground investigation statistics judges the disaster-stricken grade of Chinese pine.
Description
Technical field
The present invention relates to forest pest control technical field, more particularly to the disaster-stricken grade determination method of a kind of Chinese pine and its
Decision-making system.
Background technology
Forest disease and pest is the primary factor for threatening Forest Health, and that a situation arises is very serious for the forest disease and pest in China,
The disaster-stricken rate of forestry disease pest is far above worldwide average level, and the improvement of the ecological environment and forestry forest to China produce band
Tremendous influence is carried out.How to monitor and prevents the important topic that forest disease and pest is domestic and international forestry expert research for many years.It passes
The monitoring means of system forestry pests ＆ diseases mainly has following three kinds：One, forest farm staff is regularly scheduled to easily disaster-stricken emphasis woods
Area is manually patrolled, and is marked if finding doubtful disaster-stricken forest and samples and assay；Two, main in forest zone by traping
Calamity disease pest, the correlated measures such as investigation insect density is caused to judge the disaster-stricken situation in forest zone；Three, mobilize the resident in forest zone daily
Forest state is observed in life in time, found the abnormal situation and report local forest prevention station to adopt an effective measure in time.Normal conditions
Under, these monitoring means all existence time hysteresis qualitys and subjective, the area that and action relatively dangerous in topography is limited, work people
Member can not have found insect pest the condition of a disaster in time.Therefore there is an urgent need to the monitoring of forest disease and pest is carried out using new technology.
Invention content
The purpose of the present invention is unmanned plane and image analysis summation are applied to forestry pests ＆ diseases to monitor field, to
Improve the efficiency of forestry pests ＆ diseases monitoring and prevention.
In order to achieve the above object, the present invention takes following technological means：
A kind of disaster-stricken grade determination method of Chinese pine, includes the following steps：
S1：Pass through the video camera that is carried on unmanned plane with shooting Chinese pine sample image；
S2：Region segmentation is carried out using the disaster-stricken Chinese pine in two type fuzzy clustering algorithms to the Chinese pine sample image, and
Calculate the ratio in disaster-stricken Chinese pine region with accounting for Chinese pine sample region；
S3：The mistake leaf rate of combined ground investigation statistics judges the disaster-stricken grade of Chinese pine.
According to the disaster-stricken grade determination method of Chinese pine proposed by the present invention, wherein carried out to disaster-stricken Chinese pine in the step S2
The step of region segmentation includes：
S21:Clustering initialization：For n vector xiLimited data set X={ the x of composition1,x2,x3…xn, wherein n is
Natural number gives initial cluster center V={ v0,v1,......,vc-1, primary iteration number k=0, clusters number c, weighting refer to
Number 2, end condition are more than maximum iteration 10；
S22：Seek membership function μ(k)：WhenWhen,
S23：To membership function μ(k)It is converted：
S24：Seek new cluster centre v(k+1)：
S25：Judge cluster termination condition：If k>10, then stop, otherwise enabling k=k+1, turns to step S22；
Wherein, r and j is the central point of class, and i is sample point, dijAnd dirThe Euclidean distance and i and r of i and j are indicated respectively
Euclidean distance.
According to the disaster-stricken grade determination method of Chinese pine proposed by the present invention, wherein ground investigation counts in the step S3
Losing leaf rate calculation formula is：
Wherein P is the mistake leaf rate on monoblock Chinese pine sample ground, and N is sample tree number in Chinese pine sample ground, piFor i-th plant of Chinese pine sample
Tree loses leaf rate.
According to the disaster-stricken grade determination method of Chinese pine proposed by the present invention, wherein the standard for judging the disaster-stricken grade of Chinese pine
For：As 0 ＜ P≤0.4, it is determined as healthy or slight disaster-stricken；As 0.4 ＜ P≤0.8, it is determined as that moderate is disaster-stricken；As 0.8 ＜ P
When ＜ 1, it is determined as that severe is disaster-stricken.
The present invention also provides a kind of disaster-stricken grade decision-making system of Chinese pine simultaneously, including：
Image capture module, for passing through the video camera that is carried on unmanned plane with shooting Chinese pine sample image；
Disaster-stricken Chinese pine region segmentation module, is connected with described image acquisition module, for utilizing two type fuzzy clustering algorithms
To the Chinese pine sample the disaster-stricken Chinese pine in image carries out region segmentation, and calculates disaster-stricken Chinese pine region and account for the Chinese pine sample area
The ratio in domain；
The disaster-stricken grade determination module of Chinese pine is connected with the disaster-stricken Chinese pine region segmentation module, is investigated for combined ground
The mistake leaf rate of statistics judges the disaster-stricken grade of Chinese pine.
According to the disaster-stricken grade decision-making system of Chinese pine proposed by the present invention, wherein in the disaster-stricken Chinese pine region segmentation module
Include to the step of disaster-stricken Chinese pine progress region segmentation：
Clustering initialization：For n vector xiLimited data set X={ the x of composition1,x2,x3…xn, wherein n is nature
Number gives initial cluster center V={ v0,v1,......,vc-1, primary iteration number k=0, clusters number c, Weighted Index 2,
End condition is more than maximum iteration 10；
Seek membership function μ(k)：WhenWhen,
To membership function μ(k)It is converted：
Seek new cluster centre v(k+1)：
Judge cluster termination condition：If k>10, then stop, otherwise enabling k=k+1, turns to step S22；
Wherein, r and j is the central point of class, and i is sample point, dijAnd dirThe Euclidean distance and i and r of i and j are indicated respectively
Euclidean distance.
According to the disaster-stricken grade decision-making system of Chinese pine proposed by the present invention, wherein the mistake leaf rate meter of the ground investigation statistics
Calculating formula is：
Wherein P is the mistake leaf rate on monoblock Chinese pine sample ground, and N is sample tree number in Chinese pine sample ground, piFor i-th plant of Chinese pine sample
Tree loses leaf rate.
According to the disaster-stricken grade decision-making system of Chinese pine proposed by the present invention, wherein the standard for judging the disaster-stricken grade of Chinese pine
For：As 0 ＜ P≤0.4, it is determined as healthy or slight disaster-stricken；As 0.4 ＜ P≤0.8, it is determined as that moderate is disaster-stricken；As 0.8 ＜ P
When ＜ 1, it is determined as that severe is disaster-stricken.
Compared with prior art, unmanned plane is applied to forestry pests ＆ diseases monitoring field by the present invention, is shot using unmanned plane
Disaster-stricken forest zone orthograph picture, and it is based on Computer imaging analysis system, forest disease and pest image is analysed in depth, not only may be used
To effectively reduce manpower and material resources cost, make the overall condition that researcher is more intuitive, comprehensive grasp forest is disaster-stricken, and propose
More quickly and effectively counter-measure, and the heavy losses that Related Disasters bring the forest reserves can be reduced, improve forestry life
The economic benefit of production ensures the sound development of ecological environment.
Description of the drawings
Fig. 1 is the structural schematic diagram of the disaster-stricken grade decision-making system of Chinese pine of the present invention；
Fig. 2 is the flow chart of the disaster-stricken grade determination method of Chinese pine of the present invention；
Fig. 3 is the flow chart of fuzzy clustering algorithm in the present invention；
Fig. 4 A and Fig. 4 B are respectively the disaster-stricken unmanned plane orthograph with the disaster-stricken Chinese pine sample ground of moderate of severe；
Fig. 4 C and Fig. 4 D are respectively the segmentation result figure for Fig. 4 A and Fig. 4 B.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of not making the creative labor
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the disaster-stricken grade decision-making system of Chinese pine proposed by the present invention includes the video camera carried on unmanned plane, figure
As capture card, disaster-stricken Chinese pine region segmentation module and the disaster-stricken grade module of Chinese pine, wherein unmanned plane, video camera, image pick-up card
Etc. the image capture module constituted in the present invention.The major function of the disaster-stricken grade decision-making system of Chinese pine of the present invention is based on figure
As the Chinese pine image progress devastated segmentation that analytical technology is just penetrating unmanned plane, calculates its devastated and account for entire Chinese pine region
Ratio, realize with Chinese pine lose the matched disaster-stricken grade decision-making system of leaf rate.The system is to utilize to be carried on unmanned plane first
Camera shoot forest zone image, digital signal is switched to by image pick-up card, is stored in buffering area；By captured figure
As being pre-processed, color of image feature is extracted, Chinese pine devastated is split.It can be divided into whole system among these
Two modules：The disaster-stricken grade judgement of Chinese pine of leaf rate is lost in disaster-stricken Chinese pine region segmentation, combined ground investigation.The present invention is according to above-mentioned
The flow for the disaster-stricken grade determination method of Chinese pine that system proposes is as shown in Figure 2.
(1) disaster-stricken Chinese pine region segmentation
The present invention disaster-stricken Chinese pine region segmentation module use Type-2FCM algorithms, based on the color characteristic of image to by
The Chinese pine region of calamity is split.Type-2FCM algorithms are a kind of two type fuzzy clustering algorithms, it is by one group of physics or to take out
The object of elephant classifies to it according to certain clustering criteria, keeps sample in class as similar as possible, sample phase as far as possible between class
It is different.The algorithm flow chart can be found in Fig. 3.
Type-2FCM algorithm key steps are as follows：
Clustering initialization：For n vector xiLimited data set X={ the x of composition1,x2,x3…xn, wherein n is nature
Number gives initial cluster center V={ v0,v1,......,vc-1, primary iteration number k=0, clusters number c, Weighted Index 2,
End condition is more than maximum iteration 10；
Seek membership function μ(k)：WhenWhen,
To membership function μ(k)It is converted：
Seek new cluster centre v(k+1)：
Judge cluster termination condition：If k>10, then stop, otherwise enabling k=k+1, turns to step S22；
Wherein, r and j is the central point of class, and i is sample point, dijAnd dirThe Euclidean distance and i and r of i and j are indicated respectively
Euclidean distance.
The Chinese pine sample that severe is disaster-stricken and moderate is disaster-stricken is illustrated in Fig. 4 unmanned plane orthograph picture and) be based on type-
The image segmentation result figure of 2FCM algorithms, by the devastated that can clearly mark off Chinese pine in segmentation result.
(2) the disaster-stricken grade judgement of Chinese pine of leaf rate is lost in combined ground investigation
Disaster-stricken grade judgement is carried out for monoblock Chinese pine sample, this system uses type-2FCM algorithms to Chinese pine sample first
Ground unmanned plane orthograph picture is split, and then calculates the ratio that disaster-stricken Chinese pine region in image accounts for entire Chinese pine region in sample ground
Value, and coupled with the average mistake leaf rate on the sample ground, it realizes and the disaster-stricken grade on monoblock Chinese pine sample ground is judged.
The mistake leaf rate on monoblock Chinese pine sample ground is calculated as shown in formula (1)：
Wherein, P' is the mistake leaf rate on monoblock Chinese pine sample ground, and N is sample tree number in Chinese pine sample ground, piFor i-th plant of Chinese pine sample
This tree loses leaf rate.
Image devastated than calculating such as formula (2) shown in：
Wherein, RiFor the disaster-stricken Chinese pine region ratio of image, ndFor disaster-stricken Chinese pine region area, ncpFor monoblock Chinese pine area surface
Product.
This system is divided into the Disaster degree on Chinese pine sample ground that healthy ＆ is slight, moderate is disaster-stricken and the disaster-stricken three grades of severe, and
Long-term change trend comparison is carried out with calculating gained sample averagely mistake leaf rate, completes the disaster-stricken grading standard on Chinese pine sample ground, finally
The results are shown in Table 1.
Averagely lose leaf rate and the disaster-stricken grades of feature VS to 1 monoblock Chinese pine sample of table
It is real disaster-stricken grade judgement has been carried out to 15 pieces of Chinese pine samples of the disaster-stricken grading standard pair of Chinese pine of this system based on table 1
It tests, as can be seen from Table 2, Chinese pine devastated ratio (Ri) is to it in the unmanned plane orthograph picture by calculating monoblock Chinese pine sample ground
The accuracy rate for carrying out disaster-stricken grade judgement is 73.33%.
The image devastated ratio on 2 monoblock Chinese pine sample ground of table and mistake leaf rate matching rate
| Feature | Matching accuracy rate |
| Image devastated ratio (Ri) | 73.33% |
In conclusion the present invention judges the disaster-stricken grade on monoblock Chinese pine sample ground by the color characteristic of image, adopt
It is split and calculates its proportion to the devastated in monoblock Chinese pine sample ground with based on two type Fuzzy C-Means Algorithms, with
It averagely loses leaf rate to the Chinese pine sample that ground investigation obtains to be coupled, Chinese pine sample is divided into healthy slight, moderate and severe three
A disaster-stricken grade has obtained the disaster-stricken grading standard on monoblock Chinese pine sample ground, and then has been commented according to the disaster-stricken grade of the Chinese pine obtained
Calibration will definitely realize the oil based on unmanned plane to evaluate the health degree of Chinese pine by analyzing Chinese pine unmanned plane orthograph picture
The disaster-stricken monitoring system of pine.
One of ordinary skill in the art will appreciate that：Attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Flow is not necessarily implemented necessary to the present invention.
One of ordinary skill in the art will appreciate that：The module in device in embodiment can describe to divide according to embodiment
It is distributed in the device of embodiment, respective change can also be carried out and be located in one or more devices different from the present embodiment.On
The module for stating embodiment can be merged into a module, can also be further split into multiple submodule.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
To modify to the technical solution recorded in previous embodiment or equivalent replacement of some of the technical features；And
These modifications or replacements, the spirit and model of technical solution of the embodiment of the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (8)
1. a kind of disaster-stricken grade determination method of Chinese pine, which is characterized in that include the following steps：
S1：Pass through the video camera that is carried on unmanned plane with shooting Chinese pine sample image；
S2：Region segmentation is carried out using the disaster-stricken Chinese pine in two type fuzzy clustering algorithms to the Chinese pine sample image, and is calculated
The ratio in disaster-stricken Chinese pine region with accounting for Chinese pine sample region；
S3：The mistake leaf rate of combined ground investigation statistics judges the disaster-stricken grade of Chinese pine.
2. the disaster-stricken grade determination method of Chinese pine according to claim 1, which is characterized in that disaster-stricken oil in the step S2
Pine carry out region segmentation the step of include：
S21:Clustering initialization：For n vector xiLimited data set X={ the x of composition1,x2,x3…xn, wherein n is nature
Number gives initial cluster center V={ v0,v1,......,vc-1, primary iteration number k=0, clusters number c, Weighted Index 2,
End condition is more than maximum iteration 10；
S22：Seek membership function μ(k)：WhenWhen,
S23：To membership function μ(k)It is converted：
S24：Seek new cluster centre v(k+1)：
S25：Judge cluster termination condition：If k>10, then stop, otherwise enabling k=k+1, turns to step S22；
Wherein, r and j is the central point of class, and i is sample point, dijAnd dirThe Europe of the Euclidean distance and i and r of i and j is indicated respectively
Formula distance.
3. the disaster-stricken grade determination method of Chinese pine according to claim 2, which is characterized in that ground investigation in the step S3
The mistake leaf rate calculation formula of statistics is：
Wherein P is the mistake leaf rate on monoblock Chinese pine sample ground, and N is sample tree number in Chinese pine sample ground, piIt is lost for i-th plant of Chinese pine sample tree
Leaf rate.
4. the disaster-stricken grade determination method of Chinese pine according to claim 3, which is characterized in that the disaster-stricken grade of the judgement Chinese pine
Standard be：As 0 ＜ P≤0.4, it is determined as healthy or slight disaster-stricken；As 0.4 ＜ P≤0.8, it is determined as that moderate is disaster-stricken；When
When 0.8 ＜ P ＜ 1, it is determined as that severe is disaster-stricken.
5. a kind of disaster-stricken grade decision-making system of Chinese pine, which is characterized in that including：
Image capture module, for passing through the video camera that is carried on unmanned plane with shooting Chinese pine sample image；
Disaster-stricken Chinese pine region segmentation module, is connected with described image acquisition module, for utilizing two type fuzzy clustering algorithms to institute
Disaster-stricken Chinese pine in image carries out region segmentation with stating Chinese pine sample, and calculates disaster-stricken Chinese pine region with accounting for Chinese pine sample region
Ratio；
The disaster-stricken grade determination module of Chinese pine is connected with the disaster-stricken Chinese pine region segmentation module, is used for combined ground investigation statistics
Mistake leaf rate judge the disaster-stricken grade of Chinese pine.
6. the disaster-stricken grade decision-making system of Chinese pine according to claim 5, which is characterized in that the disaster-stricken Chinese pine region segmentation
Include to the step of disaster-stricken Chinese pine progress region segmentation in module：
S21:Clustering initialization：For n vector xiLimited data set X={ the x of composition1,x2,x3…xn, wherein n is nature
Number gives initial cluster center V={ v0,v1,......,vc-1, primary iteration number k=0, clusters number c, Weighted Index 2,
End condition is more than maximum iteration 10；
Seek membership function μ(k)：WhenWhen,
To membership function μ(k)It is converted：
Seek new cluster centre v(k+1)：
Judge cluster termination condition：If k>10, then stop, otherwise enabling k=k+1, turns to step S22；
Wherein, r and j is the central point of class, and i is sample point, dijAnd dirThe Europe of the Euclidean distance and i and r of i and j is indicated respectively
Formula distance.
7. the disaster-stricken grade decision-making system of Chinese pine according to claim 6, which is characterized in that the mistake of the ground investigation statistics
Leaf rate calculation formula is：
Wherein P is the mistake leaf rate on monoblock Chinese pine sample ground, and N is sample tree number in Chinese pine sample ground, piIt is lost for i-th plant of Chinese pine sample tree
Leaf rate.
8. the disaster-stricken grade decision-making system of Chinese pine according to claim 7, which is characterized in that the disaster-stricken grade of the judgement Chinese pine
Standard be：As 0 ＜ P≤0.4, it is determined as healthy or slight disaster-stricken；As 0.4 ＜ P≤0.8, it is determined as that moderate is disaster-stricken；When
When 0.8 ＜ P ＜ 1, it is determined as that severe is disaster-stricken.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710150677.7A CN108573199B (en) | 2017-03-14 | 2017-03-14 | Method and system for judging disaster level of Chinese pine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710150677.7A CN108573199B (en) | 2017-03-14 | 2017-03-14 | Method and system for judging disaster level of Chinese pine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108573199A true CN108573199A (en) | 2018-09-25 |
| CN108573199B CN108573199B (en) | 2022-02-01 |
Family
ID=63578398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710150677.7A Active CN108573199B (en) | 2017-03-14 | 2017-03-14 | Method and system for judging disaster level of Chinese pine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108573199B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101545479B1 (en) * | 2015-03-31 | 2015-08-24 | 김명준 | Damaged wood detecting method for forest insect and disease using orthophotograph of uav |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
| CN104881727A (en) * | 2015-01-13 | 2015-09-02 | 北京师范大学 | Crop disaster situation loss assessment method based on remote-sensing sampling |
| CN105825177A (en) * | 2016-03-09 | 2016-08-03 | 西安科技大学 | Remote-sensing crop disease identification method based on time phase and spectrum information and habitat condition |
-
2017
- 2017-03-14 CN CN201710150677.7A patent/CN108573199B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881727A (en) * | 2015-01-13 | 2015-09-02 | 北京师范大学 | Crop disaster situation loss assessment method based on remote-sensing sampling |
| KR101545479B1 (en) * | 2015-03-31 | 2015-08-24 | 김명준 | Damaged wood detecting method for forest insect and disease using orthophotograph of uav |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
| CN105825177A (en) * | 2016-03-09 | 2016-08-03 | 西安科技大学 | Remote-sensing crop disease identification method based on time phase and spectrum information and habitat condition |
Non-Patent Citations (2)
| Title |
|---|
| MC HATFIELD，ET AL: "《Evalution of Forest Health Conditions using Unmanned Aircraft Systems》", 《AGU FALL MEETING ABSTRACTS》 * |
| 费运巧: "《森林病虫害图像分析算法研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108573199B (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dhakate et al. | Diagnosis of pomegranate plant diseases using neural network | |
| CN109299683B (en) | Security protection evaluation system based on face recognition and behavior big data | |
| Pydipati et al. | Identification of citrus disease using color texture features and discriminant analysis | |
| Yun et al. | PNN based crop disease recognition with leaf image features and meteorological data | |
| CN106997475B (en) | A kind of pest image-recognizing method based on parallel-convolution neural network | |
| CN107103306B (en) | Winter wheat powdery mildew remote-sensing monitoring method based on wavelet analysis and support vector machines | |
| CN101299237B (en) | High spectroscopic data supervision classifying method based on information quantity dimensionality sequence | |
| CN104881865A (en) | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis | |
| Kodama et al. | Development of classification system of rice disease using artificial intelligence | |
| CN110008905A (en) | Regional scale stripe rust of wheat monitoring method based on the red side wave section of remote sensing image | |
| Janssen et al. | Beetle diversity in a matrix of old‐growth boreal forest: influence of habitat heterogeneity at multiple scales | |
| CN109118548A (en) | A kind of comprehensive intelligent water quality recognition methods | |
| King et al. | Modelling and mapping damage to forests from an ice storm using remote sensing and environmental data | |
| CN106056069A (en) | Unmanned aerial vehicle image analysis-based forest land resource asset evaluation method and evaluation system | |
| CN115631421B (en) | Intelligent protection method and system for cultivated land | |
| Kiranyaz et al. | Collective network of binary classifier framework for polarimetric SAR image classification: An evolutionary approach | |
| CN107657633A (en) | A kind of soil improving straw mulching rate measuring method based on BP neural network and sensor data acquisition | |
| Devi et al. | Web enabled paddy disease detection using Compressed Sensing | |
| CN111401310B (en) | Kitchen sanitation safety supervision and management method based on artificial intelligence | |
| CN107256409A (en) | The High Resolution SAR image change detection method detected based on SAE and conspicuousness | |
| CN103093243A (en) | High resolution panchromatic remote sensing image cloud discriminating method | |
| Zhuang et al. | Drought stress impact on the performance of deep convolutional neural networks for weed detection in Bahiagrass | |
| Li et al. | Development of a real-time fruit recognition system for pineapple harvesting robots | |
| CN108573199A (en) | A kind of disaster-stricken grade determination method of Chinese pine and its decision-making system | |
| Jesse et al. | Summer-habitat suitability modeling of Myotis sodalis (Indiana bat) in the eastern mountains of West Virginia |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |