CN111339954B - Mikania micrantha monitoring method based on image recognition - Google Patents
Mikania micrantha monitoring method based on image recognition Download PDFInfo
- Publication number
- CN111339954B CN111339954B CN202010123179.5A CN202010123179A CN111339954B CN 111339954 B CN111339954 B CN 111339954B CN 202010123179 A CN202010123179 A CN 202010123179A CN 111339954 B CN111339954 B CN 111339954B
- Authority
- CN
- China
- Prior art keywords
- mikania micrantha
- image
- threshold segmentation
- segmentation algorithm
- algorithm
- 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.)
- Active
Links
- 241001440840 Mikania micrantha Species 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 230000011218 segmentation Effects 0.000 claims abstract description 31
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 10
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 10
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 12
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000011514 reflex Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 3
- 238000004880 explosion Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 11
- 241001473283 Mikania Species 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000208838 Asteraceae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241000735527 Eupatorium Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a mikania micrantha monitoring method based on image recognition, and belongs to the technical field of image intelligent recognition. The method comprises the following steps: shooting the area to be monitored at equal intervals through a camera carried by the unmanned aerial vehicle to obtain a plurality of mikania micrantha aerial photography images, and transmitting the mikania micrantha aerial photography images to a computer; constructing a threshold segmentation algorithm, debugging an average value parameter and a standard deviation parameter of the threshold segmentation algorithm by using aerial images of mikania micrantha in a sampling set, and calibrating the threshold segmentation algorithm for identifying the mikania micrantha; the mikania micrantha aerial photography image is processed through an image synthesis algorithm, transmitted to a threshold segmentation algorithm, and processed through an image enhancement algorithm to obtain a binary image containing mikania micrantha identification information; and according to the flight height parameter of the unmanned aerial vehicle and the wide-angle parameter of the camera, combining the binary image to obtain a mikania micrantha distribution map and a mikania micrantha distribution area. The invention overcomes the defect of low efficiency of monitoring the explosion point of the mikania micrantha in full bloom stage in the prior art.
Description
Technical Field
The invention belongs to the technical field of image intelligent identification, and particularly relates to a mikania micrantha monitoring method based on image identification.
Background
Mikania micrantha (Mikania micrantha), a genus of Eupatorium of Compositae, native to the America, is a highly harmful invasive weed. In the early 80 s of the 20 th century, mikania micrantha was found to be introduced into the south China, endangering local vegetation and agricultural and forestry crops and causing huge economic losses.
At present, the research aiming at the automatic identification of mikania micrantha is few, and at present, there are related researches based on a satellite remote sensing technology, a hyperspectral remote sensing technology and a deep learning technology, but all have greater limitations. Therefore, with the increasing severity of the harm of mikania micrantha and the defects of the existing monitoring method, the development of a high-precision monitoring method for quickly, accurately and effectively acquiring mikania micrantha distribution data is urgently needed.
Disclosure of Invention
The invention aims to provide a mikania micrantha monitoring method based on image recognition, and overcomes the defect that the existing mikania micrantha explosion point monitoring method in full bloom is low in efficiency.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a mikania micrantha monitoring method based on image recognition comprises the following steps:
step S1, shooting the area to be monitored at equal intervals through a camera carried by the unmanned aerial vehicle to obtain a plurality of mikania micrantha aerial photography images, and transmitting the mikania micrantha aerial photography images to a computer;
step S2, constructing a threshold segmentation algorithm, dividing a plurality of aerial mikania micrantha images into a sampling set and a testing set, debugging average value parameters and standard deviation parameters of the threshold segmentation algorithm by using the aerial mikania micrantha images of the sampling set, and calibrating the threshold segmentation algorithm for identifying mikania micrantha; verifying the accuracy of the generated threshold segmentation algorithm by using the aerial image of the mikania micrantha in the test set, adjusting an average value parameter and a standard deviation parameter in the threshold segmentation algorithm when the accuracy is smaller than a preset threshold, testing the accuracy again, and repeating the step until the accuracy is larger than or equal to the preset threshold, so as to finish parameter debugging of the threshold segmentation algorithm;
step S3, the mikania micrantha aerial photography image is processed by an image synthesis algorithm, transmitted to a threshold segmentation algorithm, and processed by an image enhancement algorithm to obtain a binary image containing mikania micrantha identification information;
and step S4, combining the binary image according to the flight height parameter of the unmanned aerial vehicle and the wide-angle parameter of the camera to obtain a mikania micrantha distribution map and a mikania micrantha distribution area.
Furthermore, the flying height of the unmanned aerial vehicle is 20-30m away from the top of the canopy, and the camera is a full-picture single-lens reflective digital camera.
Further, in step S2, the ratio of the number of images in the sample set to the number of images in the test set is 1: 3.
further, in the step S2, the preset threshold is 90%.
Further, in step S3, the image synthesis algorithm includes an image stitching technique and a ground control point accurate correction technique, and the image synthesis algorithm processes the mikania micrantha aerial photograph to obtain an RGB three-channel image.
Further, in step S3, the threshold segmentation algorithm uses a range of (μ -1.5 σ, μ +1.5 σ) as a value range of different color channels of mikania micrantha, where μ is an average value of the different color channels obtained in the sample set, and σ is a standard deviation of the different color channels obtained in the sample set, and when a corresponding channel value of a pixel point in the RGB three-channel image falls within the value range, the pixel point is considered to belong to a pixel point of mikania micrantha; otherwise, it is not.
Further, in step S3, the image enhancement algorithm includes morphological open and close operations.
Further, the binary image contains coordinate information of mikania micrantha.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
1. the threshold segmentation algorithm is formed by combining the average value parameter and the standard deviation parameter obtained according to the sampling set through a specific proportionality coefficient, inherits the characteristics of simple operation, high operation efficiency and high speed of the traditional threshold segmentation algorithm, has stronger pertinence to monitoring mikania micrantha, and has the advantages of high precision, high accuracy, strong timeliness and low cost; compared with the existing satellite remote sensing technology, the method has higher precision and efficiency, and has great advantages particularly in the field of small-scale mikania micrantha monitoring; compared with the existing hyperspectral technology and deep learning technology, the method has the advantages of short training time, high efficiency, lower requirement on the computing power of a computer and low cost.
2. The image enhancement algorithm comprises morphological operation, the morphological operation has the advantage of fast extracting image features, and the mikania micrantha information extracted by the morphological operation enhancement threshold segmentation algorithm has the characteristics of high precision, high accuracy, strong anti-variation performance and low cost, and particularly can improve the monitoring efficiency of the explosion point of the mikania micrantha in the full bloom stage.
3. The image preprocessing technology comprises an image splicing technology and a ground control point accurate correction technology, so that a mikania micrantha RGB three-channel image can be acquired more accurately.
4. The method can obtain the mikania micrantha distribution map, can intelligently calculate the mikania micrantha distribution area according to the flight height parameter of the unmanned aerial vehicle and the camera wide-angle parameter, and is favorable for accurately judging the harm degree of the mikania micrantha.
Drawings
Fig. 1 is a flow chart of a mikania monitoring method based on image recognition according to the present invention;
fig. 2 is a system diagram of a mikania monitoring method based on image recognition according to the present invention;
fig. 3 is a flowchart of steps S3 and S4 according to the present invention.
The main reference symbols in the drawings are as follows:
in the attached drawing, 1-the area to be monitored, 2-a camera, 3-an unmanned aerial vehicle and 4-a computer.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
As shown in fig. 1 to 3, a mikania micrantha monitoring method based on image recognition includes the following steps:
step S1, shooting the area to be monitored at equal intervals through the camera 2 carried by the unmanned aerial vehicle 3 to obtain a plurality of mikania micrantha aerial photography images, and transmitting the mikania micrantha aerial photography images to the computer 4;
step S2, constructing a threshold segmentation algorithm, dividing a plurality of aerial mikania micrantha images into a sampling set and a testing set, debugging average value parameters and standard deviation parameters of the threshold segmentation algorithm by using the aerial mikania micrantha images in the sampling set, and calibrating the threshold segmentation algorithm for identifying mikania micrantha; verifying the accuracy of the generated threshold segmentation algorithm by using the aerial image of the mikania micrantha in the test set, adjusting an average value parameter and a standard deviation parameter in the threshold segmentation algorithm when the accuracy is smaller than a preset threshold, testing the accuracy again, and repeating the step until the accuracy is larger than or equal to the preset threshold, so as to finish parameter debugging of the threshold segmentation algorithm; in step S2, the ratio of the number of images in the sample set to the number of images in the test set is 1: 3. in step S2, the preset threshold is 90%.
Step S3, the aerial image of mikania micrantha is processed by an image synthesis algorithm, transmitted to a threshold segmentation algorithm, and processed by an image enhancement algorithm to obtain a binary image containing mikania micrantha identification information; the image synthesis algorithm comprises an image splicing technology and a ground control point accurate correction technology, the image enhancement algorithm comprises morphological opening and closing operation, and the binary image comprises coordinate information of mikania micrantha.
In this embodiment, the process of processing the aerial image of mikania micrantha by the image synthesis algorithm is as follows:
the acquired aerial images of mikania micrantha are spliced by adopting Agisoft Photoshop professional v1.4.0(Agisoft LLC, Russia), and three-dimensional point cloud, a Digital Surface Model (DSM), a Digital Elevation Model (DEM) and a digital orthophoto image (DOM) of the area to be monitored are obtained through the processes of arranging images, generating dense point cloud, generating network, generating texture and the like. And finally, accurately correcting the space coordinates of the spliced images through the ground control points to generate an RGB three-channel image.
In this embodiment, the process of processing the RGB three-channel image by the threshold segmentation algorithm and the image enhancement algorithm is as follows:
the method comprises the steps of randomly acquiring values of R channels and G channels and B channels of 100 mikania micrantha from RGB three-channel images, manually removing obvious unreasonable values, and calculating the average value mu and the variance sigma of each color channel to use the range of (mu-1.5 sigma, mu +1.5 sigma) as the value range of different color channels of the mikania micrantha. According to the value range, when the corresponding channel value of the pixel point in the RGB three-channel image falls within the value range, the pixel is considered to belong to the pixel point of the mikania micrantha; otherwise, it is not. Extracting pixel point coordinates meeting the conditions, and setting the value corresponding to the pixel point coordinates as 1; and if the condition is not met, setting the value corresponding to the pixel point coordinate as 0, and performing morphological opening and closing operation to obtain a binary image.
And step S4, combining the binary image according to the flight height parameter of the unmanned aerial vehicle 3 and the wide-angle parameter of the camera 2 to obtain a mikania micrantha distribution map and a mikania micrantha distribution area. The flying height of the unmanned aerial vehicle 3 is 20-30m away from the top of the canopy, and the camera 2 is a full-picture single-lens reflective digital camera.
The process of processing the binary image comprises the following steps:
in the binary image, extracting a pixel point coordinate with a value of 1, setting an R channel value, a G channel value and a B channel value of the pixel point coordinate in the RGB three-channel image as 255, 255 and 0, and obtaining a mikania micrantha distribution map, wherein yellow is labeled mikania micrantha. In the binary image, the number of pixels with the calculated value of 1 is calculated, the total number of pixels of the binary image is calculated, and the percentage of the distribution area of the mikania micrantha is obtained by dividing the total number of pixels by the number of pixels with the value of 1. And obtaining the actual corresponding area of the image represented by the RGB three-channel image according to the flight height parameter of the unmanned aerial vehicle 3 and the wide angle parameter of the camera 2. And multiplying the percentage of the distribution area of the mikania micrantha by the actual corresponding area of the image to obtain the distribution area of the mikania micrantha.
The above description is directed to the preferred embodiments of the present invention, but the embodiments are not intended to limit the scope of the claims of the present invention, and all equivalent changes and modifications made within the technical spirit of the present invention should fall within the scope of the claims of the present invention.
Claims (8)
1. A mikania micrantha monitoring method based on image recognition is characterized by comprising the following steps:
step S1, shooting the area to be monitored at equal intervals through a camera carried by the unmanned aerial vehicle to obtain a plurality of mikania micrantha aerial photography images, and transmitting the mikania micrantha aerial photography images to a computer;
step S2, constructing a threshold segmentation algorithm, dividing a plurality of aerial mikania micrantha images into a sampling set and a testing set, debugging average value parameters and standard deviation parameters of the threshold segmentation algorithm by using the aerial mikania micrantha images of the sampling set, and calibrating the threshold segmentation algorithm for identifying mikania micrantha; verifying the accuracy of the generated threshold segmentation algorithm by using the aerial image of the mikania micrantha in the test set, adjusting an average value parameter and a standard deviation parameter in the threshold segmentation algorithm when the accuracy is smaller than a preset threshold, testing the accuracy again, and repeating the step until the accuracy is larger than or equal to the preset threshold, so as to finish parameter debugging of the threshold segmentation algorithm;
step S3, the mikania micrantha aerial photography image is processed by an image synthesis algorithm, transmitted to a threshold segmentation algorithm, and processed by an image enhancement algorithm to obtain a binary image containing mikania micrantha identification information;
and step S4, combining the binary image according to the flight height parameter of the unmanned aerial vehicle and the wide-angle parameter of the camera to obtain a mikania micrantha distribution map and a mikania micrantha distribution area.
2. The image recognition-based mikania micrantha monitoring method of claim 1, wherein the unmanned aerial vehicle flying height is 20-30m above the canopy, and the camera is a full-frame single-lens reflex digital camera.
3. The image recognition-based mikania micrantha monitoring method according to claim 1, wherein in step S2, the ratio of the number of images in the sample set to the number of images in the test set is 1: 3.
4. the image recognition-based mikania micrantha monitoring method according to claim 1, wherein in the step S2, the preset threshold is 90%.
5. The image recognition-based mikania micrantha monitoring method of claim 1, wherein in the step S3, the image synthesis algorithm includes an image stitching technique and a ground control point accurate correction technique, and the image synthesis algorithm obtains an RGB three-channel image after aerial image processing of mikania micrantha.
6. The mikania micrantha monitoring method based on image recognition as claimed in claim 5, wherein in step S3, the threshold segmentation algorithm uses a range of (μ -1.5 σ, μ +1.5 σ) as a value range of different color channels of mikania micrantha, where μ is an average value of the different color channels obtained in the sample set, and σ is a standard deviation of the different color channels obtained in the sample set, and when a corresponding channel value of a pixel in the RGB three-channel image falls within the value range, the pixel is considered to belong to a pixel of mikania micrantha; otherwise, it is not.
7. The image recognition-based mikania micrantha monitoring method of claim 1, wherein in the step S3, the image enhancement algorithm includes morphological on and off operations.
8. The image recognition-based mikania micrantha monitoring method of claim 1, wherein the binary image contains coordinate information of mikania micrantha.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010123179.5A CN111339954B (en) | 2020-02-27 | 2020-02-27 | Mikania micrantha monitoring method based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010123179.5A CN111339954B (en) | 2020-02-27 | 2020-02-27 | Mikania micrantha monitoring method based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111339954A CN111339954A (en) | 2020-06-26 |
CN111339954B true CN111339954B (en) | 2022-08-09 |
Family
ID=71183722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010123179.5A Active CN111339954B (en) | 2020-02-27 | 2020-02-27 | Mikania micrantha monitoring method based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111339954B (en) |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103914680B (en) * | 2013-01-07 | 2018-03-23 | 上海宝信软件股份有限公司 | A kind of spray printing character picture identification and check system and method |
CN103488988B (en) * | 2013-09-06 | 2017-02-01 | 广东电网公司电力科学研究院 | Method for extracting insulators in electrical equipment based on unmanned aerial vehicle line patrol visible light image |
CN103699903B (en) * | 2013-12-24 | 2017-02-15 | 中国科学院深圳先进技术研究院 | City roof green area calculation method and system based on image identification |
CN104217215B (en) * | 2014-08-28 | 2017-11-28 | 哈尔滨工程大学 | A kind of classifying identification method of water surface foggy image and picture rich in detail |
CN105225228B (en) * | 2015-09-08 | 2018-08-21 | 广西大学 | Leifsonia image partition method under the natural background of field |
CN106503695B (en) * | 2016-12-02 | 2019-07-09 | 汕头大学 | A kind of tobacco plant identification and method of counting based on Aerial Images |
CN107346434A (en) * | 2017-05-03 | 2017-11-14 | 上海大学 | A kind of plant pest detection method based on multiple features and SVMs |
CN107464260A (en) * | 2017-07-06 | 2017-12-12 | 山东农业大学 | A kind of rice canopy image processing method using unmanned plane |
CN108875620B (en) * | 2018-06-06 | 2021-11-05 | 中国农业科学院深圳农业基因组研究所 | Invasive plant monitoring method and system |
CN108764199B (en) * | 2018-06-06 | 2022-03-25 | 中国农业科学院深圳农业基因组研究所 | Automatic identification method and system for invasive plant mikania micrantha |
CN109410168B (en) * | 2018-08-31 | 2021-11-16 | 清华大学 | Modeling method of convolutional neural network for determining sub-tile classes in an image |
CN109583378A (en) * | 2018-11-30 | 2019-04-05 | 东北大学 | A kind of vegetation coverage extracting method and system |
CN109376728A (en) * | 2018-12-28 | 2019-02-22 | 华南农业大学 | A kind of weeds in paddy field recognition methods and its application based on multiple features fusion and BP neural network |
CN110516648B (en) * | 2019-09-02 | 2022-04-19 | 湖南农业大学 | Ramie plant number identification method based on unmanned aerial vehicle remote sensing and pattern identification |
CN110796076A (en) * | 2019-10-29 | 2020-02-14 | 北京环境特性研究所 | Hyperspectral image river detection method |
-
2020
- 2020-02-27 CN CN202010123179.5A patent/CN111339954B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111339954A (en) | 2020-06-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI709109B (en) | A non-transitory computer-readable medium and system for detecting objects from aerial imagery and a method for detecting objects from aerial imagery | |
CN108009542B (en) | Weed image segmentation method in rape field environment | |
CN111723654B (en) | High-altitude parabolic detection method and device based on background modeling, YOLOv3 and self-optimization | |
CN109146889B (en) | Farmland boundary extraction method based on high-resolution remote sensing image | |
CN106951836B (en) | crop coverage extraction method based on prior threshold optimization convolutional neural network | |
CN111898651A (en) | Tree detection method based on Tiny Yolov3 algorithm | |
CN108629368B (en) | Multi-modal foundation cloud classification method based on joint depth fusion | |
CN111080526A (en) | Method, device, equipment and medium for measuring and calculating farmland area of aerial image | |
CN110110618B (en) | SAR target detection method based on PCA and global contrast | |
CN109784205B (en) | Intelligent weed identification method based on multispectral inspection image | |
CN111339953B (en) | Clustering analysis-based mikania micrantha monitoring method | |
CN114692991A (en) | Wolfberry yield prediction method and system based on deep learning | |
CN117409339A (en) | Unmanned aerial vehicle crop state visual identification method for air-ground coordination | |
Xiang et al. | Measuring stem diameter of sorghum plants in the field using a high-throughput stereo vision system | |
CN112884795A (en) | Power transmission line inspection foreground and background segmentation method based on multi-feature significance fusion | |
CN112613437B (en) | Method for identifying illegal buildings | |
CN111339954B (en) | Mikania micrantha monitoring method based on image recognition | |
CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
CN115760885B (en) | High-closure-degree wetland forest parameter extraction method based on consumer-level unmanned aerial vehicle image | |
CN116721385A (en) | Machine learning-based RGB camera data cyanobacteria bloom monitoring method | |
CN116721344A (en) | Vegetation detection method, device and equipment based on aerial photographing equipment | |
KR20180096966A (en) | Automatic Counting Method of Rice Plant by Centroid of Closed Rice Plant Contour Image | |
Li et al. | Image processing for crop/weed discrimination in fields with high weed pressure | |
Lin et al. | A multi-target detection framework for multirotor UAV | |
TWI785436B (en) | Systems for object detection from aerial imagery, methods for detecting object in aerial imagery and non-transitory computer readable medium thereof |
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 |