CN109948563A - A kind of withered tree detection localization method of the pine nematode based on deep learning - Google Patents
A kind of withered tree detection localization method of the pine nematode based on deep learning Download PDFInfo
- Publication number
- CN109948563A CN109948563A CN201910229945.3A CN201910229945A CN109948563A CN 109948563 A CN109948563 A CN 109948563A CN 201910229945 A CN201910229945 A CN 201910229945A CN 109948563 A CN109948563 A CN 109948563A
- Authority
- CN
- China
- Prior art keywords
- tree
- pine
- withered
- image
- deep learning
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of withered tree detection localization method of the pine nematode based on deep learning, comprising the following steps: (1) capturing sample image pre-processes sample image, and is labeled to pine tree, obtains training sample；(2) it is trained with deep learning frame and convolutional neural networks tree training sample withered to pine nematode, obtains detection model；(3) unmanned plane carries out high-altitude fixed point shooting to target area, acquires image and location information；(4) by the image transmitting after acquisition into detection model, detection model carries out withered tree to the image after acquisition and identifies, and the detection image after the completion of detection is exported, coordinate position in the picture is set according to withered, finally obtains the withered tree geographical location information prescription map of pine nematode.The present invention quickly, detect efficiently and accurately the pine tree of illness can judge the position of illness pine tree, so as to subsequent processing.
Description
Technical field
The present invention relates to a kind of withered tree detection methods of pine nematode, and in particular to a kind of pine based on deep learning
The withered tree of nematodiasis detects localization method.
Background technique
Pine nematode is a kind of China's pine tree destructiveness epidemic disease very harmful to pine forests at present, infected pine
The external symptom of tree shows as needle and gradually becomes yellowish-brown, and the pine needle of severe illness can be in bronzing, final to wilt directly
It is extremely withered.The pathogenecity of pine nematode is strong and has fatal influence to host, and often infected pine tree will soon
Dead and can infect rapidly to other pine trees, in addition to this, which is often taken by surprise, and leads once appearance will quickly be spread
Cause a large amount of pine deaths, if therefore cannot find and carry out processing the pine tree of pine nematode occur in time, it will bring huge
Economic loss and certain destruction is generated to ecological environment.According to incomplete statistics, pine nematode is in Zhejiang, wide
244 administrative areas at the county level in 16 provinces such as east, Sichuan occur, and add up lethal pine tree and reach more than 500,000,000 plants, caused by directly and
It connects economic loss and reaches about 27,500,000,000 yuan.
The plant of illness is found as early as possible and is cut down, and can be prevented pine nematode expansion sprawling, can greatly be subtracted
Few destruction and bring economic loss of the disease to ecological environment.The method that pine nematode is administered in China's detection at present is usual
It is by manually going in pine forests the pine tree for finding illness the processing such as to be administered and cut down again to pine tree, this method is not only
It spends human and material resources and inefficient, it is clear that this is not optimal detection administering method.
Summary of the invention
The purpose of the present invention is to overcome the deficiency in the prior art, and it is withered to provide a kind of pine nematode based on deep learning
Tree detection localization method, this method quickly, detect efficiently and accurately the pine tree of illness, and can be judged to suffer from
The position of sick pine tree, so as to subsequent treatment and other processing.
The purpose of the present invention is achieved through the following technical solutions:
A kind of withered tree detection localization method of the pine nematode based on deep learning, which is characterized in that including following step
It is rapid:
(1) there is the pine forests panorama of the withered tree of pine nematode using the fixed point shooting of unmanned plane high-altitude, after shooting
Sample image is pre-processed, and is labeled to the pine tree in pretreated sample image, and it is withered to obtain pine nematode
Set training sample；
(2) it is trained with deep learning frame and convolutional neural networks tree training sample withered to pine nematode,
Obtain can be used to detect the detection model of the withered tree of pine nematode in pine forests；
(3) high-altitude fixed point shooting is carried out to target area by the unmanned plane with GPS positioning module, acquires target area
Image and location information；And concatenation is carried out to shooting image, obtaining the target area with geographic coordinate information just
Penetrate striograph；
(4) orthophotoquad after acquisition is input in detection model, detection model to the image after acquisition into
Row withered tree identification is found out and withered tree region similar in training sample and exports the detection image after the completion of detecting；Meanwhile
The coordinate position for exporting each pixel in orthophotoquad sets coordinate position in the picture according to withered, finds each withered tree
Corresponding geographical coordinate finally obtains the withered tree geographical location information prescription map of pine nematode.
A preferred embodiment of the invention, wherein step pre-processes the photo after shooting in (1), the pretreatment
Including by the image in each region of shooting is spliced, image border removes dryness and cutting operation.
Preferably, when marking to the pine tree in pretreated photo, pine tree tree is divided into normal pine tree, just morbidity pine
Tree, half withered pine tree and complete withered four seed type of pine tree, and carried out four kinds of corresponding pine tree surfaces as example
Mark, and add corresponding label.By mark disease send out different at degree pine tree, so that the detection model after training can be more
Add the truth for accurately judging disease hair pine tree, is also beneficial to the subsequent pine tree to different sick hair degree and is controlled accordingly
It treats and processing, raising detects quality.
Preferably, according to the result and test result shown after training, by increasing training the number of iterations, increasing training sample
Sheet and the mode of optimization loss function and deep learning network frame are adjusted and improve to the detection model trained, until
The detection effect of detection module meets preset standard.
A preferred embodiment of the invention, the camera of the UAV flight in step (1) are Visible Light Camera, the visible light
Camera is arranged on the holder of unmanned plane.Using Visible Light Camera, there are 20,000,000 pixels, be conducive to unmanned plane high aerial
The surface of the withered tree of clearly pine nematode is shot, to be conducive to improve the accuracy of identification of the model trained.
Preferably, the camera of the UAV flight in step (3) is Visible Light Camera, and Visible Light Camera setting is being taken photo by plane
On the holder for positioning unmanned plane.
A preferred embodiment of the invention, trained detection model are arranged in base station, will be passed through by transmission device
The image of the target area of unmanned plane acquisition is input in base station, carries out withered tree by image of the detection model to target area
Detection identification.Trained detection model is arranged in base station, rather than is set up directly on unmanned plane, can reduce nobody
The electric quantity consumption and computational burden of machine are conducive to that shooting is more comprehensive, and range is more to extend the cruise duration of unmanned plane
Big pine forests are conducive to the speed for improving detection.
A preferred embodiment of the invention passes through each pixel in the orthophotoquad after splicing in step (3)
Have geographic coordinate information；By obtaining the coordinate position of each pixel in orthophotoquad, and according to withered tree in image
Middle coordinate position exports the corresponding geographical coordinate of each withered tree, finally obtains the specific location of withered tree and export complete mesh
Mark the withered tree geographical location information prescription map of pine nematode in region.
Compared with the prior art, the invention has the following beneficial effects:
1, the present invention acquires the pine forests photo of target area by unmanned plane, and is transferred in trained detection model
Carry out recognition detection, and combine the navigation system on unmanned plane, the case where finally determining the withered tree in target area and
More specific location information；It not only can greatly save the time spent in manually finding withered tree, reduce manpower and material resources and spent
The cost taken, and the processing to the withered tree of pine nematode is accelerated, effectively pine nematode can be avoided further to spread
With spread to other healthy pine trees, prevent pest and disease damage from further deteriorating brought economic loss, realize quick, efficient, smart
The withered tree detection of quasi- pine nematode.
It 2, is in yellowish-brown in first occurrent time due to infected pine tree, in half withered period (severe illness period) in red
The feature of brown, the two is particularly evident, and the present invention knows the withered tree of pine nematode using the detection mode of deep learning
It does not detect, detection effect is good.
Detailed description of the invention
Fig. 1 is the flow diagram of the withered tree detection localization method of the pine nematode of the invention based on deep learning.
Fig. 2 is VGG16 convolutional neural networks training flowage structure figure used in the present invention.
Fig. 3 is the schematic diagram being labeled in the present invention to training sample.
Specific embodiment
Below with reference to embodiment and attached drawing, the invention will be further described, but embodiments of the present invention are not limited only to
This.
Referring to Fig. 1, the withered tree of the pine nematode based on deep learning of the present embodiment detects localization method, including following
Step:
(1) acquisition and pretreatment of training sample and mark.It is gone to using the unmanned plane of taking photo by plane for carrying Visible Light Camera
It has been known that there is the sample images that the pine forests of the withered tree of pine nematode carry out high-altitude shooting, collecting pine nematode, to filmed
Sample image such as is denoised, is spliced, being cut at the pretreatment (existing matlab and python tool specifically can be used), and by sample
The size dimension of this image is normalized to 224mm × 224mm × 3mm, forms training sample；To acquired and pre-processed
Training sample is labeled, and pine tree is divided into normal pine tree respectively in mark, just fall ill pine tree, half withered pine tree and complete
Complete withered pine tree, and the surface of corresponding pine tree is labeled as example, and add label, such as mark shown in Fig. 3
Training sample after note.When marking sample, the progress of annotation tool labelImg software also can use.
(2) training sample is trained with deep learning frame and convolutional neural networks, obtains detection model.With
Tensorflow is as deep learning frame, with the faster-rcnn deep learning network based on VGG16 to having pre-processed simultaneously
The training sample marked is trained, as shown in Fig. 2, VGG16 includes 13 3 × 3 layer convolutional layers, 5 maximum pond layers
With 3 full articulamentums, the neuronal quantity of the last one full articulamentum FC, corresponding to the quantity of class categories, due to pine
Classification includes normal pine tree, the pine tree that just falls ill, half withered pine tree and complete withered pine when the withered tree of material nematodiasis is labeled
Four classes are set, so the neuronal quantity of the last one full articulamentum FC is 4.In the training process, pass through the convolution in VGG16
Layer, pond layer and activation primitive carry out feature extraction to the example mark in image, are carried out by the iteration tests set anti-
Refreshment, which is practiced, to be exported to obtain the detection model for detecting the withered tree of pine nematode eventually by full articulamentum, after training,
It is optimal to judge whether the model has reached according to training result and test result, by modification the number of iterations, increases data training
The modes such as sample and optimization algorithm constantly adjust improvement and obtain the best detection model of detection effect.
(3) Image Acquisition and reading position information are carried out to target area.Use the unmanned plane pair for having GPS positioning module
Target area carries out Image Acquisition, and used unmanned plane is equipped with for carrying the unmanned machine head of Visible Light Camera, being used for
It positions the GPS positioning module of target position information, the remote sensing equipment unmanned aerial vehicle platform for controlling unmanned plane during flying shooting and takes
The Visible Light Camera being loaded on unmanned aerial vehicle platform.To guarantee to cover all ranges of object detection area in shooting process, and
And the GPS positioning information of target area is acquired, after the Image Acquisition for completing target area, by Photoscan tool to image
Concatenation is carried out, the orthophotoquad of the target area with geographic coordinate information is formed.
(4) the orthogonal projection image after acquisition is input in detection model and carries out recognition detection.In the detection process,
The image after acquisition is first transferred to the detection model in base station by transmission device, can wirelessly be passed in real time
It returns, can also be transmitted after completing picture collection by wired mode；In identification process, detection model can automatic identification and step
(1) the similar target of example mark feature in marks out come with frame and shows confidence level, including normal pine tree, first morbidity pine
Tree, half withered pine tree and withered pine tree completely all can be marked out, the detection image that final output detection is completed.
Geographic coordinate information is had by each pixel in the orthophotoquad after splicing in step (3), is passed through
ArcGIS software can export the coordinate position of each pixel in orthophotoquad.According to the withered tree of pine nematode in image
Middle coordinate position exports each corresponding withered tree geographical coordinate (including the pine tree that just falls ill, half withered pine tree and complete withered pine
Tree) particular geographic coordinates location information, and show its specific geographical position coordinates, final output completely includes disease inspection
Survey the detection prescription map of the withered tree of pine nematode of result and particular geographic location coordinate information.
Above-mentioned is the preferable embodiment of the present invention, but embodiments of the present invention are not limited by the foregoing content,
His any changes, modifications, substitutions, combinations, simplifications done without departing from the spirit and principles of the present invention, should be
The substitute mode of effect, is included within the scope of the present invention.
Claims (8)
1. a kind of withered tree of the pine nematode based on deep learning detects localization method, which comprises the following steps:
(1) there is the pine forests panorama of the withered tree of pine nematode using the fixed point shooting of unmanned plane high-altitude, to the sample after shooting
Image is pre-processed, and is labeled to the pine tree in pretreated sample image, and the withered tree instruction of pine nematode is obtained
Practice sample；
(2) it is trained, obtains with deep learning frame and convolutional neural networks tree training sample withered to pine nematode
It can be used to detect the detection model of the withered tree of pine nematode in pine forests；
(3) high-altitude fixed point shooting is carried out to target area by the unmanned plane with GPS positioning module, acquires the figure of target area
Picture and location information；And concatenation is carried out to shooting image, obtain the orthogonal projection of the target area with geographic coordinate information
As figure；
(4) orthophotoquad after acquisition is input in detection model, detection model carries out the image after acquisition withered
Dead tree identification is found out and withered tree region similar in training sample and exports the detection image after the completion of detection；Meanwhile it exporting
The coordinate position of each pixel in orthophotoquad sets coordinate position in the picture according to withered, finds each withered tree and corresponds to
Geographical coordinate, finally obtain the withered tree geographical location information prescription map of pine nematode.
2. the withered tree of the pine nematode based on deep learning according to claim 1 detects localization method, feature exists
In step pre-processes the photo after shooting in (1), which includes spelling the image in each region of shooting
It connects, image border removes dryness and cutting operation.
3. the withered tree of the pine nematode based on deep learning according to claim 2 detects localization method, feature exists
In, in pretreated image pine tree mark when, by pine tree be divided into normal pine tree, just fall ill pine tree, half withered pine tree
And complete withered four seed type of pine tree, and be labeled using four kinds of corresponding pine tree surfaces as example, and addition pair
The label answered.
4. the withered tree of the pine nematode based on deep learning according to claim 1-3 detects localization method,
It is characterized in that, according to the result and model test results that are shown after training, by increasing training the number of iterations, increasing training sample
Sheet and the mode of optimization loss function and deep learning network frame are adjusted and improve to the detection model trained, directly
Detection effect to detection module meets preset standard.
5. the withered tree of the pine nematode based on deep learning according to claim 1 detects localization method, feature exists
In the camera of the UAV flight in step (1) is Visible Light Camera, which is arranged on the holder of unmanned plane.
6. the withered tree of the pine nematode based on deep learning according to claim 1 detects localization method, feature exists
In the camera of the UAV flight in step (3) is Visible Light Camera, which is arranged on the holder of unmanned plane.
7. the withered tree of the pine nematode based on deep learning according to claim 1 detects localization method, feature exists
In trained detection model is arranged in base station, by transmission device by the image of the target area acquired by unmanned plane
It is input in base station, withered tree detection identification is carried out by image of the detection model to target area.
8. a kind of withered tree of the pine nematode of deep learning according to claim 1 detects localization method, feature exists
In: in step (3), geographic coordinate information is had by each pixel in the orthophotoquad after splicing；By obtaining
The coordinate position of each pixel in orthophotoquad is taken, and sets coordinate position in the picture according to withered, exports each withered tree
Corresponding geographical coordinate finally obtains the specific location of withered tree and exports the withered tree ground of pine nematode in complete object region
Manage location information prescription map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229945.3A CN109948563A (en) | 2019-03-22 | 2019-03-22 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229945.3A CN109948563A (en) | 2019-03-22 | 2019-03-22 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109948563A true CN109948563A (en) | 2019-06-28 |
Family
ID=67011423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910229945.3A Pending CN109948563A (en) | 2019-03-22 | 2019-03-22 | A kind of withered tree detection localization method of the pine nematode based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948563A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348403A (en) * | 2019-07-15 | 2019-10-18 | 华瑞新智科技（北京）有限公司 | A kind of trees quantity real-time measurement statistical method, system and unmanned plane |
| CN110517228A (en) * | 2019-07-30 | 2019-11-29 | 浙江农林大学 | Trunk image rapid detection method based on convolutional neural networks and transfer learning |
| CN110533595A (en) * | 2019-09-03 | 2019-12-03 | 北京麦飞科技有限公司 | A kind of method and system of crop disease and insect Spatial distributions distribution monitoring |
| CN111177443A (en) * | 2020-01-17 | 2020-05-19 | 陈虎 | Pine wood nematode disease control and supervision method |
| CN111582176A (en) * | 2020-05-09 | 2020-08-25 | 湖北同诚通用航空有限公司 | Visible light remote sensing image withered and dead wood recognition software system and recognition method |
| CN111768363A (en) * | 2020-05-13 | 2020-10-13 | 华南农业大学 | Deep learning-based circuit board surface defect detection method and detection system |
| CN111881851A (en) * | 2020-07-30 | 2020-11-03 | 湖南省建筑科学研究院有限责任公司 | Garden seedling intelligent detection and counting method based on UAV and convolutional neural network |
| CN112084989A (en) * | 2020-09-16 | 2020-12-15 | 湖南三湘绿谷生态科技有限公司 | Unmanned aerial vehicle and CNN-based large-range pine wood nematode withered vertical wood intelligent detection method |
| CN112329594A (en) * | 2020-11-02 | 2021-02-05 | 南京新向量信息科技有限公司 | Pine wood nematode disease wood monitoring system and monitoring method thereof |
| CN112329703A (en) * | 2020-11-20 | 2021-02-05 | 北京林业大学 | Construction method of deep convolutional neural network suitable for identifying remote sensing images of pine wilt disease |
| CN112598265A (en) * | 2020-12-18 | 2021-04-02 | 武汉大学 | Decoupling risk estimation-based rapid detection method for hyperspectral pine nematode disease of unmanned aerial vehicle |
| CN112633161A (en) * | 2020-12-21 | 2021-04-09 | 重庆英卡电子有限公司 | Pine wood nematode disease withered and dead tree detection and positioning method based on high-altitude pan-tilt recognition |
| CN112753456A (en) * | 2020-12-30 | 2021-05-07 | 山东农业大学 | Accurate prevention and control method and system for pine wood nematode disease based on space-time law |
| CN112800867A (en) * | 2021-01-13 | 2021-05-14 | 重庆英卡电子有限公司 | Pine wood nematode withered tree detection method based on two-stage high-altitude pan-tilt video |
| CN113011355A (en) * | 2021-03-25 | 2021-06-22 | 东北林业大学 | Pine wood nematode disease image recognition detection method and device |
| CN113128281A (en) * | 2019-12-31 | 2021-07-16 | 中国移动通信集团福建有限公司 | Automatic base station opening method and device |
| CN113537089A (en) * | 2021-07-20 | 2021-10-22 | 浙江点创信息科技有限公司 | Pine wood nematode disease infected wood identification and positioning method based on unmanned aerial vehicle aerial photography original sheet |
| US20220198641A1 (en) * | 2020-12-23 | 2022-06-23 | International Business Machines Corporation | Tree fall management |
| CN114782844A (en) * | 2022-05-06 | 2022-07-22 | 华南农业大学 | Pine wood nematode disease tree identification method, system and storage medium |
| CN116310793A (en) * | 2023-02-08 | 2023-06-23 | 西南林业大学 | Mountain dead tree identification positioning method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910309A (en) * | 2017-04-18 | 2017-06-30 | 南昌航空大学 | Forest fire detecting system based on unmanned plane during flying platform |
| CN106915462A (en) * | 2017-02-14 | 2017-07-04 | 福建兴宇信息科技有限公司 | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information |
| CN108334110A (en) * | 2018-02-06 | 2018-07-27 | 首欣（北京）科技有限公司 | A kind of forestry disease monitoring method and apparatus based on unmanned plane |
| CN108921814A (en) * | 2018-05-16 | 2018-11-30 | 华南农业大学 | A kind of Citrus Huanglongbing pathogen on-line quick detection system and method based on deep learning |
-
2019
- 2019-03-22 CN CN201910229945.3A patent/CN109948563A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106915462A (en) * | 2017-02-14 | 2017-07-04 | 福建兴宇信息科技有限公司 | Forestry pests ＆ diseases intelligent identifying system based on multi-source image information |
| CN106910309A (en) * | 2017-04-18 | 2017-06-30 | 南昌航空大学 | Forest fire detecting system based on unmanned plane during flying platform |
| CN108334110A (en) * | 2018-02-06 | 2018-07-27 | 首欣（北京）科技有限公司 | A kind of forestry disease monitoring method and apparatus based on unmanned plane |
| CN108921814A (en) * | 2018-05-16 | 2018-11-30 | 华南农业大学 | A kind of Citrus Huanglongbing pathogen on-line quick detection system and method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 孙钰等: ""基于深度学习的森林虫害无人机实时监测方法"", 《农业工程学报》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348403A (en) * | 2019-07-15 | 2019-10-18 | 华瑞新智科技（北京）有限公司 | A kind of trees quantity real-time measurement statistical method, system and unmanned plane |
| CN110517228A (en) * | 2019-07-30 | 2019-11-29 | 浙江农林大学 | Trunk image rapid detection method based on convolutional neural networks and transfer learning |
| CN110533595A (en) * | 2019-09-03 | 2019-12-03 | 北京麦飞科技有限公司 | A kind of method and system of crop disease and insect Spatial distributions distribution monitoring |
| CN113128281A (en) * | 2019-12-31 | 2021-07-16 | 中国移动通信集团福建有限公司 | Automatic base station opening method and device |
| CN111177443A (en) * | 2020-01-17 | 2020-05-19 | 陈虎 | Pine wood nematode disease control and supervision method |
| CN111582176A (en) * | 2020-05-09 | 2020-08-25 | 湖北同诚通用航空有限公司 | Visible light remote sensing image withered and dead wood recognition software system and recognition method |
| CN111768363A (en) * | 2020-05-13 | 2020-10-13 | 华南农业大学 | Deep learning-based circuit board surface defect detection method and detection system |
| CN111881851A (en) * | 2020-07-30 | 2020-11-03 | 湖南省建筑科学研究院有限责任公司 | Garden seedling intelligent detection and counting method based on UAV and convolutional neural network |
| CN112084989A (en) * | 2020-09-16 | 2020-12-15 | 湖南三湘绿谷生态科技有限公司 | Unmanned aerial vehicle and CNN-based large-range pine wood nematode withered vertical wood intelligent detection method |
| CN112329594A (en) * | 2020-11-02 | 2021-02-05 | 南京新向量信息科技有限公司 | Pine wood nematode disease wood monitoring system and monitoring method thereof |
| CN112329703A (en) * | 2020-11-20 | 2021-02-05 | 北京林业大学 | Construction method of deep convolutional neural network suitable for identifying remote sensing images of pine wilt disease |
| CN112598265B (en) * | 2020-12-18 | 2022-06-07 | 武汉大学 | Decoupling risk estimation-based rapid detection method for hyperspectral pine nematode disease of unmanned aerial vehicle |
| CN112598265A (en) * | 2020-12-18 | 2021-04-02 | 武汉大学 | Decoupling risk estimation-based rapid detection method for hyperspectral pine nematode disease of unmanned aerial vehicle |
| CN112633161A (en) * | 2020-12-21 | 2021-04-09 | 重庆英卡电子有限公司 | Pine wood nematode disease withered and dead tree detection and positioning method based on high-altitude pan-tilt recognition |
| CN112633161B (en) * | 2020-12-21 | 2023-05-09 | 重庆英卡电子有限公司 | Pine wood nematode disease dead tree detection positioning method based on high-altitude holder identification |
| US20220198641A1 (en) * | 2020-12-23 | 2022-06-23 | International Business Machines Corporation | Tree fall management |
| CN112753456A (en) * | 2020-12-30 | 2021-05-07 | 山东农业大学 | Accurate prevention and control method and system for pine wood nematode disease based on space-time law |
| CN112753456B (en) * | 2020-12-30 | 2021-12-21 | 山东农业大学 | Accurate prevention and control method and system for pine wood nematode disease based on space-time law |
| CN112800867A (en) * | 2021-01-13 | 2021-05-14 | 重庆英卡电子有限公司 | Pine wood nematode withered tree detection method based on two-stage high-altitude pan-tilt video |
| CN112800867B (en) * | 2021-01-13 | 2023-05-12 | 重庆英卡电子有限公司 | Pine wood nematode disease dead tree detection method based on two-stage high-altitude tripod head video |
| CN113011355A (en) * | 2021-03-25 | 2021-06-22 | 东北林业大学 | Pine wood nematode disease image recognition detection method and device |
| CN113537089A (en) * | 2021-07-20 | 2021-10-22 | 浙江点创信息科技有限公司 | Pine wood nematode disease infected wood identification and positioning method based on unmanned aerial vehicle aerial photography original sheet |
| CN114782844A (en) * | 2022-05-06 | 2022-07-22 | 华南农业大学 | Pine wood nematode disease tree identification method, system and storage medium |
| CN114782844B (en) * | 2022-05-06 | 2023-05-12 | 华南农业大学 | Pine wood nematode disease tree identification method, system and storage medium |
| CN116310793A (en) * | 2023-02-08 | 2023-06-23 | 西南林业大学 | Mountain dead tree identification positioning method, device, equipment and storage medium |
| CN116310793B (en) * | 2023-02-08 | 2024-01-23 | 西南林业大学 | Mountain dead tree identification positioning method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948563A (en) | A kind of withered tree detection localization method of the pine nematode based on deep learning | |
| CN109977813B (en) | Inspection robot target positioning method based on deep learning framework | |
| Chen et al. | A YOLOv3-based computer vision system for identification of tea buds and the picking point | |
| CN107657639A (en) | A kind of method and apparatus of quickly positioning target | |
| CN106909886B (en) | A kind of high-precision method for traffic sign detection and system based on deep learning | |
| CN109919157A (en) | A kind of vision positioning method and device | |
| CN111881728A (en) | Grassland mouse damage monitoring method based on low-altitude remote sensing | |
| CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
| CN113743358B (en) | Landscape vision feature recognition method adopting omnibearing collection and intelligent calculation | |
| CN111626241B (en) | Face detection method and device | |
| CN113095441A (en) | Pig herd bundling detection method, device, equipment and readable storage medium | |
| CN114972177A (en) | Road disease identification management method and device and intelligent terminal | |
| CN116543386A (en) | Agricultural pest image identification method based on convolutional neural network | |
| CN115649501A (en) | Night driving illumination system and method for unmanned aerial vehicle | |
| Xiang et al. | Measuring stem diameter of sorghum plants in the field using a high-throughput stereo vision system | |
| WO2021051268A1 (en) | Machine vision-based tree type identification method and apparatus | |
| CN111060518A (en) | Stamping part defect identification method based on instance segmentation | |
| CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| CN110298366A (en) | Crops are distributed extracting method and device | |
| Xiang et al. | PhenoStereo: a high-throughput stereo vision system for field-based plant phenotyping-with an application in sorghum stem diameter estimation | |
| CN113378754A (en) | Construction site bare soil monitoring method | |
| Jia et al. | Location of the maize plant with machine vision | |
| Liu et al. | Improvement of Detection Accuracy of Aircraft in Remote Sensing Images Based on YOLOV5 Model | |
| CN113538389B (en) | Pigeon egg quality identification method | |
| Kalmukov et al. | Methods for Automated Remote Sensing and Counting of Animals |
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: 20190628 |
|
| RJ01 | Rejection of invention patent application after publication |