CN113011355A - Pine wood nematode disease image recognition detection method and device - Google Patents
Pine wood nematode disease image recognition detection method and device Download PDFInfo
- Publication number
- CN113011355A CN113011355A CN202110321019.6A CN202110321019A CN113011355A CN 113011355 A CN113011355 A CN 113011355A CN 202110321019 A CN202110321019 A CN 202110321019A CN 113011355 A CN113011355 A CN 113011355A
- Authority
- CN
- China
- Prior art keywords
- image
- pine wood
- wood nematode
- nematode disease
- image recognition
- 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
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Vascular Medicine (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of pine wood nematode disease image recognition and detection, and particularly relates to a pine wood nematode disease image recognition and detection method and device, which can effectively improve the recognition efficiency of diseased trees and have higher detection precision by setting a target detection technology adopting deep learning to detect the pine wood nematode disease; the image intelligent identification positioning method adopts a unified discrimination standard, so that the coverage rate of the identification result is effectively improved, and the generalization capability is strong. By integrating the advantages, the pine wood nematode disease image recognition and detection method can find infected pine trees in time and determine the distribution conditions of the infected pine trees, effectively monitor the development dynamics of the pine wood nematode disease, and provide timely and accurate information for pine wood managers and forest protection personnel.
Description
Technical Field
The invention belongs to the technical field of pine wood nematode disease image recognition and detection, and particularly relates to a pine wood nematode disease image recognition and detection method and device.
Background
The identification of the pine wood nematode disease tree is influenced by noise, illumination, seasons and a plurality of other factors, and the identification aspect comprises the problems of missing judgment and erroneous judgment of the color-changing tree. The condition of missed judgment, such as that the color-changing tree canopy is shielded, the diameter of the color-changing tree canopy is too small, and the color-changing tree in partial areas is difficult to judge due to poor image splicing; and judging the false condition as that other land objects such as yellow shrubs, bare soil, withered and dead grasslands or trees which are felled on the ground and are not sealed are the color-changing trees. This requires that the recognition algorithm overcome the interference of complex and multi-scene to improve the recognition accuracy of the chameleon. At present, the level of visual interpretation still remains in the image extraction of the color-changing pine, and the working scheme of completely depending on manual visual interpretation of the color-changing pine has low efficiency and strong subjectivity. The deep learning method has a self-learning function, can learn some high-level abstract spatial features or spectral features, and has stronger generalization capability, so that the identification accuracy of the pine wood nematode disease image in a complex environment can be improved.
Disclosure of Invention
The invention aims to provide a method and a device for identifying and detecting an image of bursaphelenchus xylophilus to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: acquiring pine wood nematode disease data, wherein an unmanned aerial vehicle is provided with a digital camera to acquire images of an experimental area, a global navigation satellite system and an inertia measurement unit module are integrated into an unmanned aerial vehicle platform, the images are acquired according to weather conditions, actual terrain and vegetation conditions, the data quality of each image is checked, and the images are enhanced through an AS-SMOTE Boost algorithm;
secondly, denoising the pine wood nematode disease image, shooting the pine wood nematode disease data image in a natural background, wherein the research area is a mountain area forest area, removing the interference generated by the natural background of non-pines, extracting a characteristic weight value from the interference generated by the background, setting the characteristic weight value as A1, A2, A3, A4, A5, A6, A7 and A8, weighting average An on the characteristic value of the interference (A1+ A2+ A3+ A4+ A5+ A6+ A7+ A8)/8, and inputting the value of the weighted average number An into the bispectrum gray image for recombination denoising;
step three, dividing the image of the pine wood nematode disease, wherein the dividing of the image of the pine wood nematode disease is a process of subdividing the image of the pine wood nematode disease into characteristic subregions, extracting and constructing a classifier according to the color and texture characteristic values of the pine wood nematode disease in the image dividing of the pine wood nematode disease, the dividing of the image of the pine wood nematode disease comprises a threshold dividing method, an edge detection method, a mathematical morphology method and a fuzzy clustering method, and the divided images are synthesized through a SMOTE algorithm sample;
extracting the image features of the pine wood nematode disease, wherein the extraction of the image features of the pine wood nematode disease comprises the image feature description and extraction of the pine wood nematode disease, the feature description is a certain image attribute of an image obtained after the pine wood nematode disease image is segmented, the extraction is to calculate a subset of the features, screen information to a target space for dimensionality reduction, facilitate target identification, extract the image features by extracting the features according to specific morphology, color and texture features, and integrate the extracted features through a Boosting ensemble learning algorithm;
and fifthly, classifying and identifying the pine wood nematode disease image, establishing a classifier based on the extracted pine wood nematode disease image characteristics, processing and classifying the pine wood nematode disease image, analyzing by using a SMART algorithm, distinguishing the morphological characteristics, the color characteristics and the texture characteristics by establishing the classifier, and identifying the pine wood nematode disease image after analyzing the morphological characteristics, the color characteristics and the texture characteristics by using an AS-SMOTE Boost algorithm.
In a preferred embodiment, the features in step three include structure, color and texture of the image.
An image recognition and detection device for pine wood nematode diseases comprises a device installation fixing table, wherein the upper surface of the device installation fixing table is in threaded connection with a fixing table fastening bolt, the upper surface of the device installation fixing table is rotatably connected with a rotary supporting rod, the upper surface of the rotary supporting rod is rotatably connected with an image recognition and detection outer shell, an image recognition and detection assembly is arranged on the inner surface of the image recognition and detection outer shell, the image recognition and detection assembly comprises an image imaging lens, an imaging processing circuit board, a background processor, an image denoising lens, a median filter, an image segmentation processor, an image characteristic detector and an image output data plug, the image imaging lens is arranged on the front surface of the right side of the image recognition and detection outer shell, the imaging processing circuit board is arranged in the middle of the image recognition and detection outer shell, and the background processor is arranged on the upper surface of the imaging processing circuit board, the image denoising lens is arranged on the front surface of the left side of the image identification detection shell, the median filter, the image segmentation processor and the image characteristic detector are arranged on the upper surface of the imaging processing circuit board, and the background processor is connected with the image output data plug.
In a preferred embodiment, the device mounting fixture and the image recognition and detection housing are made of alloy steel.
In a preferred embodiment, the image imaging lens and the image denoising lens are symmetrically mounted and fixed to each other.
In a preferred embodiment, the median filter is electrically connected to the image segmentation processor.
As a preferred embodiment, a rotary bearing is arranged at the rotary connection position of the rotary support rod and the image recognition detection outer shell.
As a preferred implementation, the image imaging lens and the image denoising lens are electrically connected to the imaging processing circuit board.
In a preferred embodiment, the rotation support rod is made of alloy steel.
In a preferred embodiment, the inner surface of the image output data plug is provided with a copper sheet.
Compared with the prior art, the invention has the beneficial effects that:
the pine wood nematode disease is detected by setting a target detection technology adopting deep learning, so that the identification efficiency of the diseased wood can be effectively improved, and the detection precision is higher; the image intelligent identification positioning method adopts a unified discrimination standard, so that the coverage rate of the identification result is effectively improved, and the generalization capability is strong. By integrating the advantages, the pine wood nematode disease image recognition and detection method can find infected pine trees in time and determine the distribution conditions of the infected pine trees, effectively monitor the development dynamics of the pine wood nematode disease, and provide timely and accurate information for pine wood managers and forest protection personnel.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic front view of the structure of the present invention;
FIG. 3 is a schematic partial front view of the structure of the present invention;
FIG. 4 is a front view of the structure of the present invention;
FIG. 5 is a left side view of the structure of the present invention;
FIG. 6 is a top view of a structure of the present invention;
in the figure: 1. a device mounting and fixing table; 11. a fixed stand fastening bolt; 2. rotating the support rod; 21. an image recognition detection outer shell; 3. an image recognition detection component; 31. an image imaging lens; 311. an imaging processing circuit board; 32. a background processor; 33. an image denoising lens; 34. a median filter; 35. an image segmentation processor; 36. an image feature detector; 4. and an image output data plug.
Detailed Description
The present invention will be further described with reference to the following examples.
The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention. The conditions in the examples are further adjusted according to specific conditions, and simple modifications of the method of the present invention based on the concept of the present invention are within the scope of the claimed invention.
Referring to fig. 1-6, the present invention provides a method for identifying and detecting bursaphelenchus xylophilus disease images, comprising the steps of collecting data, acquiring images of an experimental area by using an unmanned aerial vehicle equipped with a digital camera, integrating a global navigation satellite system and an inertial measurement unit module into an unmanned aerial vehicle platform to ensure that information is attached to each image, knowing geographical conditions of the experimental area and making a corresponding flight plan according to weather conditions, considering actual terrain, vegetation conditions and an area to be covered, checking data quality of each image after each flight, deleting invalid images and shooting again, and finally performing image enhancement by an AS-SMOTE Boost algorithm to enhance the images, denoising the images, shooting the data images in a natural background, wherein the selected research area is a mountain area, except for a pine to be researched, and a large number of mountain road, field, bare soil and rock interference items, extracting feature weights from interference generated in the background by bispectrum gray level images, setting the extracted feature weights as A1, A2, A3, A4, A5, A6, A7 and A8, performing weighted average An on the feature values (A1+ A2+ A3+ A4+ A5+ A6+ A7+ A8)/8), inputting the weighted average An value into bispectrum gray level images for recombination and denoising, removing the complex backgrounds to improve the subsequent pine wood nematode disease tree identification precision, step three, image segmentation, which is a process of subdividing An image into feature areas, namely, structure, color and grammatical subregion of the image, realizing feature value extraction and classifier construction in the image segmentation process, wherein the classical methods of image segmentation include threshold segmentation, edge detection, morphological fuzzy mathematical morphology and clustering method, step four, image feature extraction, wherein the image feature extraction comprises two processes of image feature description and extraction, the classification efficiency and the classification precision are determined, the feature description refers to a certain image attribute of the image after image segmentation, quantitatively describing or expressing, extracting refers to calculating a subset of the features, screening useful information to perform dimension reduction on a target space, facilitating target identification, extracting according to specific attributes, wherein the main method comprises the steps of extracting morphological characteristics, color characteristics and texture characteristics, integrating the extracted features by Boosting ensemble learning algorithm, classifying and identifying the image, establishing a classifier based on the extracted image features, the processing and classification of the images are carried out through a series of algorithms, and the image recognition of the pine wood nematode disease is carried out after morphological characteristics, color characteristics and texture characteristics are analyzed through an AS-SMOTE Boost algorithm.
Wherein, the features in the third step include the structure, color and literary property of the image.
The pine wood nematode disease image recognition and detection device is used as a carrier, the pine wood nematode disease image recognition and detection device comprises a device installation fixing table 1, the upper surface of the device installation fixing table 1 is in threaded connection with a fixing table fastening bolt 11, the upper surface of the device installation fixing table 1 is in rotary connection with a rotary supporting rod 2, the upper surface of the rotary supporting rod 2 is in rotary connection with an image recognition detection outer shell 21, an image recognition detection assembly 3 is arranged on the inner surface of the image recognition detection outer shell 21, the image recognition detection assembly 3 comprises an image imaging lens 31, an imaging processing circuit board 311, a background processor 32, an image denoising lens 33, a median filter 34, an image segmentation processor 35, an image characteristic detector 36 and an image output data plug 4, the image imaging lens 31 is arranged on the front right side surface of the image recognition detection outer shell 21, the imaging processing circuit board 311 is arranged in the middle of the image recognition, the upper surface of the imaging processing circuit board 311 is provided with a background processor 32, the left front surface of the image recognition detection outer shell 21 is provided with an image denoising lens 33, the upper surface of the imaging processing circuit board 311 is provided with a median filter 34, an image segmentation processor 35 and an image feature detector 36, the image feature extraction by the image feature detector 36 determines the classification efficiency and classification precision, and the background processor 32 is connected with an image output data plug 4.
The device installation fixing table 1 and the image recognition detection outer shell 21 are made of alloy steel, and the mechanical strength of the image recognition detection outer shell 21 is effectively improved through the device installation fixing table 1 and the image recognition detection outer shell 21 made of alloy steel.
The image imaging lens 31 and the image denoising lens 33 are symmetrically installed and fixed with each other, and the image can be more clear by symmetrically installing the image imaging lens 31 and the image denoising lens 33 with each other.
The median filter 34 is electrically connected to the image segmentation processor 35, and the median filter 34 is electrically connected to the image segmentation processor 35 for filtering and then performing image segmentation.
Wherein, the joint that the rotation of the rotation support rod 2 and the image recognition detection shell body 21 is provided with a rolling bearing, and the joint that the rotation support rod 2 and the image recognition detection shell body 21 rotate is provided with a rolling bearing so that the rotation support rod 2 rotates.
The image imaging lens 31 and the image denoising lens 33 are electrically connected to the imaging processing circuit board 311, and data can be effectively circulated through the imaging processing circuit board 311.
Wherein, the rotation support rod 2 adopts alloy steel material, has improved the intensity of support through rotation support rod 2 adoption alloy steel material.
The inner surface of the image output data plug 4 is provided with a copper sheet, and the inner surface of the image output data plug 4 is provided with the copper sheet, so that the transmission stability is improved.
The working principle and the using process of the invention are as follows: firstly, an unmanned aerial vehicle equipped with a digital camera is used for acquiring images of an experimental area to acquire data, in the image denoising, the data image is shot in a natural background, the selected research area is a mountain area and forest area, besides the pine trees to be researched, a large number of mountain roads, fields, bare soil and rock interference items are also included, a median filter 34 and an image segmentation processor 35 are provided through the upper surface of the imaging processing circuit board 311 as carriers for filtering and image segmentation, realizes the characteristic value extraction and the classifier construction in the image segmentation process to segment the image, the image feature extraction is carried out by the image feature detector 36, the efficiency of classification and the precision of classification are determined by two processes of image feature description and extraction, and the image data is output by connecting the image output data plug 4 with the background processor 32.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A pine wood nematode disease image identification detection method is characterized in that: the method comprises the following steps:
acquiring pine wood nematode disease data, wherein an unmanned aerial vehicle is provided with a digital camera to acquire images of an experimental area, a global navigation satellite system and an inertia measurement unit module are integrated into an unmanned aerial vehicle platform, the images are acquired according to weather conditions, actual terrain and vegetation conditions, the data quality of each image is checked, and the images are enhanced through an AS-SMOTE Boost algorithm;
secondly, denoising the pine wood nematode disease image, shooting the pine wood nematode disease data image in a natural background, wherein the research area is a mountain area forest area, removing the interference generated by the natural background of non-pines, extracting a characteristic weight value from the interference generated by the background, setting the characteristic weight value as A1, A2, A3, A4, A5, A6, A7 and A8, weighting average An on the characteristic value of the interference (A1+ A2+ A3+ A4+ A5+ A6+ A7+ A8)/8, and inputting the value of the weighted average number An into the bispectrum gray image for recombination denoising;
step three, dividing the image of the pine wood nematode disease, wherein the dividing of the image of the pine wood nematode disease is a process of subdividing the image of the pine wood nematode disease into characteristic subregions, extracting and constructing a classifier according to the color and texture characteristic values of the pine wood nematode disease in the image dividing of the pine wood nematode disease, the dividing of the image of the pine wood nematode disease comprises a threshold dividing method, an edge detection method, a mathematical morphology method and a fuzzy clustering method, and the divided images are synthesized through a SMOTE algorithm sample;
extracting the image features of the pine wood nematode disease, wherein the extraction of the image features of the pine wood nematode disease comprises the image feature description and extraction of the pine wood nematode disease, the feature description is a certain image attribute of an image obtained after the pine wood nematode disease image is segmented, the extraction is to calculate a subset of the features, screen information to a target space for dimensionality reduction, facilitate target identification, extract the image features by extracting the features according to specific morphology, color and texture features, and integrate the extracted features through a Boosting ensemble learning algorithm;
and fifthly, classifying and identifying the pine wood nematode disease image, establishing a classifier based on the extracted pine wood nematode disease image characteristics, processing and classifying the pine wood nematode disease image, analyzing by using a SMART algorithm, distinguishing the morphological characteristics, the color characteristics and the texture characteristics by establishing the classifier, and identifying the pine wood nematode disease image after analyzing the morphological characteristics, the color characteristics and the texture characteristics by using an AS-SMOTE Boost algorithm.
2. The image recognition and detection method for the pine wilt disease of claim 1, wherein: and in the third step, the pine wood nematode disease characteristics comprise structure, color and culture of images.
3. The utility model provides a pine wood nematode disease image identification detection device which characterized in that: the device comprises a device installation fixing table (1), wherein a fixing table fastening bolt (11) is connected to the upper surface of the device installation fixing table (1) in a threaded manner, a rotary supporting rod (2) is rotatably connected to the upper surface of the device installation fixing table (1), an image recognition detection outer shell (21) is rotatably connected to the upper surface of the rotary supporting rod (2), an image recognition detection component (3) is arranged on the inner surface of the image recognition detection outer shell (21), the image recognition detection component (3) comprises an image imaging lens (31), an imaging processing circuit board (311), a background processor (32), an image denoising lens (33), a median filter (34), an image segmentation processor (35), an image characteristic detector (36) and an image output data plug (4), the image imaging lens (31) is arranged on the front surface of the right side of the image recognition detection outer shell (21), the image recognition detection device is characterized in that the imaging processing circuit board (311) is arranged in the middle of the image recognition detection outer shell (21), the background processor (32) is arranged on the upper surface of the imaging processing circuit board (311), the image denoising lens (33) is arranged on the front surface of the left side of the image recognition detection outer shell (21), the median filter (34), the image segmentation processor (35) and the image feature detector (36) are arranged on the upper surface of the imaging processing circuit board (311), and the background processor (32) is connected with the image output data plug (4).
4. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the device installation fixing table (1) and the image recognition detection outer shell (21) are made of alloy steel.
5. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the image imaging lens (31) and the image denoising lens (33) are symmetrically arranged and fixed with each other.
6. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the median filter (34) is electrically connected to the image segmentation processor (35).
7. The image recognition and detection device for the pine wilt disease of claim 3, wherein: and a rotary bearing is arranged at the rotary connection part of the rotary support rod (2) and the image recognition detection outer shell (21).
8. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the image imaging lens (31) and the image denoising lens (33) are electrically connected with the imaging processing circuit board (311).
9. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the rotary supporting rod (2) is made of alloy steel.
10. The image recognition and detection device for the pine wilt disease of claim 3, wherein: the inner surface of the image output data plug (4) is provided with a copper sheet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110321019.6A CN113011355B (en) | 2021-03-25 | 2021-03-25 | Pine wood nematode disease image recognition detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110321019.6A CN113011355B (en) | 2021-03-25 | 2021-03-25 | Pine wood nematode disease image recognition detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113011355A true CN113011355A (en) | 2021-06-22 |
| CN113011355B CN113011355B (en) | 2022-10-11 |
Family
ID=76407229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110321019.6A Active CN113011355B (en) | 2021-03-25 | 2021-03-25 | Pine wood nematode disease image recognition detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011355B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609913A (en) * | 2021-07-08 | 2021-11-05 | 三峡大学 | Pine wood nematode disease tree detection method based on sampling threshold interval weighting |
| CN114550017A (en) * | 2022-04-25 | 2022-05-27 | 北京林业大学 | Pine wilt disease integrated early warning and detecting method and device based on mobile terminal |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330892A (en) * | 2017-07-24 | 2017-11-07 | 内蒙古工业大学 | A kind of sunflower disease recognition method based on random forest method |
| CN108875911A (en) * | 2018-05-25 | 2018-11-23 | 同济大学 | One kind is parked position detecting method |
| CN109948563A (en) * | 2019-03-22 | 2019-06-28 | 华南农业大学 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
| CN110533644A (en) * | 2019-08-22 | 2019-12-03 | 深圳供电局有限公司 | Insulator detection method based on image recognition |
| CN111665199A (en) * | 2019-03-06 | 2020-09-15 | 东莞中科蓝海智能视觉科技有限公司 | Wire and cable color detection and identification method based on machine vision |
| CN111985504A (en) * | 2020-08-17 | 2020-11-24 | 中国平安人寿保险股份有限公司 | Copying detection method, device, equipment and medium based on artificial intelligence |
| US20210073435A1 (en) * | 2019-09-06 | 2021-03-11 | BeamUp, Ltd. | Structural design systems and methods for selective simulation of equipment coverage in a floor plan |
-
2021
- 2021-03-25 CN CN202110321019.6A patent/CN113011355B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330892A (en) * | 2017-07-24 | 2017-11-07 | 内蒙古工业大学 | A kind of sunflower disease recognition method based on random forest method |
| CN108875911A (en) * | 2018-05-25 | 2018-11-23 | 同济大学 | One kind is parked position detecting method |
| CN111665199A (en) * | 2019-03-06 | 2020-09-15 | 东莞中科蓝海智能视觉科技有限公司 | Wire and cable color detection and identification method based on machine vision |
| CN109948563A (en) * | 2019-03-22 | 2019-06-28 | 华南农业大学 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
| CN110533644A (en) * | 2019-08-22 | 2019-12-03 | 深圳供电局有限公司 | Insulator detection method based on image recognition |
| US20210073435A1 (en) * | 2019-09-06 | 2021-03-11 | BeamUp, Ltd. | Structural design systems and methods for selective simulation of equipment coverage in a floor plan |
| CN111985504A (en) * | 2020-08-17 | 2020-11-24 | 中国平安人寿保险股份有限公司 | Copying detection method, device, equipment and medium based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| LIPING SUN 等: "《Advances in Polymer Technology》", 17 June 2019 * |
| 周宏威 等: "《昆虫学报》", 20 September 2020 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609913A (en) * | 2021-07-08 | 2021-11-05 | 三峡大学 | Pine wood nematode disease tree detection method based on sampling threshold interval weighting |
| CN114550017A (en) * | 2022-04-25 | 2022-05-27 | 北京林业大学 | Pine wilt disease integrated early warning and detecting method and device based on mobile terminal |
| CN114550017B (en) * | 2022-04-25 | 2022-07-12 | 北京林业大学 | Pine wilt disease integrated early warning and detecting method and device based on mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113011355B (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11615615B2 (en) | Method and apparatus for extracting mountain landscape buildings based on high-resolution remote sensing images | |
| Jing et al. | Automated delineation of individual tree crowns from LiDAR data by multi-scale analysis and segmentation | |
| CN106971146B (en) | Based on three water body exception remote sensing dynamic monitoring and controlling method, the device and system for looking into technology | |
| Jing et al. | An individual tree crown delineation method based on multi-scale segmentation of imagery | |
| Véga et al. | PTrees: A point-based approach to forest tree extraction from lidar data | |
| Ke et al. | A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing | |
| CN113011355B (en) | Pine wood nematode disease image recognition detection method and device | |
| Trier et al. | Automatic detection of circular structures in high‐resolution satellite images of agricultural land | |
| CN111932567B (en) | Satellite image-based ice lake contour automatic extraction method | |
| CN106915462A (en) | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information | |
| CN102214298A (en) | Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism | |
| CN103400156A (en) | CFAR (Constant False Alarm Rate) and sparse representation-based high-resolution SAR (Synthetic Aperture Radar) image ship detection method | |
| Fytsilis et al. | A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images | |
| CN105719283A (en) | Road surface crack image detection method based on Hessian matrix multi-scale filtering | |
| CN106530281A (en) | Edge feature-based unmanned aerial vehicle image blur judgment method and system | |
| CN105512622B (en) | A kind of visible remote sensing image sea land dividing method based on figure segmentation and supervised learning | |
| CN108764284A (en) | The classification denoising method and system of a kind of high resolution image to pine tree Deceased wood | |
| CN110889840A (en) | Effectiveness detection method of high-resolution 6 # remote sensing satellite data for ground object target | |
| Millan et al. | Vineyard pruning weight assessment by machine vision: towards an on-the-go measurement system: This article is published in cooperation with the 21th GIESCO International Meeting, June 23-28 2019, Thessaloniki, Greece. Guests editors: Stefanos Koundouras and Laurent Torregrosa | |
| CN111597930A (en) | Coastline extraction method based on remote sensing cloud platform | |
| Tao et al. | Recognition of ecological vegetation fairy circles in intertidal salt marshes from UAV LiDAR point clouds | |
| Ke et al. | Comparison of individual tree crown detection and delineation methods | |
| Li et al. | A novel approach for the 3D localization of branch picking points based on deep learning applied to longan harvesting UAVs | |
| CN102231190B (en) | Automatic extraction method for alluvial-proluvial fan information | |
| Larsen et al. | Automatic avalanche mapping using texture classification of optical satellite imagery |
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 |