CN112561923A - Mikania micrantha accurate monitoring method based on edge calculation - Google Patents
Mikania micrantha accurate monitoring method based on edge calculation Download PDFInfo
- Publication number
- CN112561923A CN112561923A CN202011381532.6A CN202011381532A CN112561923A CN 112561923 A CN112561923 A CN 112561923A CN 202011381532 A CN202011381532 A CN 202011381532A CN 112561923 A CN112561923 A CN 112561923A
- Authority
- CN
- China
- Prior art keywords
- mikania micrantha
- aerial vehicle
- unmanned aerial
- edge calculation
- mikania
- 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.)
- Withdrawn
Links
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a mikania micrantha accurate monitoring method based on edge calculation, which comprises the following steps: acquiring data, namely acquiring a plurality of images of a mikania micrantha generation area by using an unmanned aerial vehicle as an original training sample, acquiring a plurality of aerial mikania micrantha images, transmitting the aerial mikania micrantha images to a computer, and splicing the aerial mikania micrantha images acquired from the mikania micrantha acquisition data by the computer for later use; preprocessing data and making a training sample; and (4) network model selection and mikania micrantha segmentation model training and testing. According to the accurate mikania micrantha monitoring method based on edge calculation, reconnaissance video streams are acquired in real time through unmanned aerial vehicle equipment, the video streams are input into a main controller of the unmanned aerial vehicle equipment to be divided and calculated, a division result is obtained, the division result is transmitted back to a terminal, monitoring of the mikania micrantha is achieved, original images collected by the unmanned aerial vehicle are obtained, and an important foundation is laid for accurate insecticide spraying and elimination of weeds.
Description
Technical Field
The invention relates to a mikania micrantha accurate monitoring method, in particular to a mikania micrantha accurate monitoring method based on edge calculation, and belongs to the technical field of application of mikania micrantha accurate monitoring methods.
Background
Mikania micrantha is also called Mikania micrantha or Mikania micrantha. Is perennial herb or shrub climbing vine of the compositae family, and is smooth to have more soft hair; stem-like, sometimes tubular, with edges; thin leaf, light green, oval heart or halberd, tapered, cauline leaf mostly arrow-shaped or halberd-shaped, with deep concave, near the whole edge to the coarse wavy teeth, or teeth; mikania micrantha is native to south and central america, is widely spread to tropical regions of asia, and becomes one of the most serious harmful weeds in tropical and subtropical regions of the world; mikania micrantha appears as a weed in hong kong in china approximately in 1919, is found in shenzhen in 1984, and has been widely distributed in the zhujiang delta region in 2008; the species has been listed as the first foreign invasive species in China and also as one of the most harmful 100 foreign invasive species in the world; mikania micrantha grows rapidly and is not shade-tolerant, and the attached main plants are wound and covered by climbing edges, so that great influence is caused on forests and farmland lands; due to the rapid growth of mikania micrantha, stem nodes can root and propagate at any time, the habitat is quickly covered, the seeds are rich, the invasion can be quickly realized, and the growth of natural vegetation and crops can be inhibited through competition or other sensibility; as the mikania micrantha often climbs to the upper layer of a 10-meter-high crown or bush, the removal of the mikania micrantha often damages attached crops, so that the effective monitoring of the mikania micrantha makes important preparation work for eradicating the weeds by combining the investigation and pesticide application technologies in the next step, and the method has important practical guiding significance for agricultural development.
And there are a lot of problems in mikania micrantha monitoring process at present, it is relatively poor to have the technical limitation to mikania micrantha monitoring like this, and the mikania micrantha that is not convenient for carries out accurate monitoring, reduces monitoring accuracy, influences the use. Therefore, an accurate mikania micrantha monitoring method based on edge calculation is provided for solving the problems.
Disclosure of Invention
The invention aims to solve the problems and provide an edge calculation-based mikania micrantha accurate monitoring method.
The invention realizes the aim through the following technical scheme, and provides an edge calculation-based mikania micrantha accurate monitoring method, which comprises the following steps:
(1) acquiring data, namely acquiring a plurality of images of a mikania micrantha generation area by using an unmanned aerial vehicle as an original training sample, acquiring a plurality of aerial mikania micrantha images, transmitting the aerial mikania micrantha images to a computer, and splicing the aerial mikania micrantha images acquired from the mikania micrantha acquisition data by the computer for later use;
(2) preprocessing data and manufacturing a training sample, cutting the acquired training sample according to the size of 1024 × 1024 resolution, and then marking a mikania micrantha generation area and a non-mikania micrantha generation area by using different color values by using a marking tool to form a label file, so that a training data sample set is manufactured;
(3) the network model selection and mikania micrantha segmentation model training test is carried out, for a mikania micrantha monitoring task, a D-linknet semantic segmentation network is selected, and the mikania micrantha segmentation model is obtained through the D-linknet semantic segmentation network.
Further, unmanned aerial vehicle adopts four shaft air vehicle in step (1), and unmanned aerial vehicle safety is trouble-free and the noise is little.
Further, in the step (1), the flying height of the unmanned aerial vehicle is 20m to 30m away from the mikania micrantha canopy, the hyperspectral data acquisition module is carried on the unmanned aerial vehicle platform, the air route is planned, and the air flight is carried out in a growth concentrated area of the mikania micrantha to acquire hyperspectral data.
Further, the drone in step (1) is an unmanned aircraft operated with a radio remote control device and a self-contained program control device, or is operated autonomously, either completely or intermittently, by an on-board computer.
Further, the data preprocessing in the step (2) includes sequentially performing geometric correction, data noise reduction, radiation correction and band elimination on a training data sample set to be researched.
Further, the training sample in the step (1) is also called a training area, which is a typical distribution area of various surface feature types determined by an analyst on a remote sensing image, and the accuracy of the selection and evaluation direct relation classification of the training sample is a key of supervision classification.
Further, the training sample cutting device collected in the step (2) adopts a picture divider, and the picture divider comprises two divisions, three divisions, four divisions, eight divisions, nine divisions, twelve divisions and sixteen divisions, which can be selected according to requirements.
Further, the D-linknet network model in the step (3) adopts linknet as a backbone network, the whole structure is in a U-shaped structure, and the main body adopts an Encoder-Decoder idea; semantic information is extracted from the image from shallow to deep on the left side, upsampling spatial information recovery is carried out from deep to shallow on the right side, a thermodynamic diagram is finally generated, in order to enhance the fusion of context information in the upsampling process, a hole convolution group serial-parallel model structure is adopted in the middle layer, and the rate parameters of five serial hole convolution groups are respectively 1, 2, 4, 8 and 16.
Further, in the step (3), the training data sample set in the step (2) is trained and learned by using a D-linknet network, so that a mikania micrantha segmentation model is obtained, and the model is applied to an actual image test, so that the mikania micrantha occurrence region of the farming area can be segmented accurately in real time.
Further, the step (3) network model is a flexible way that the database model is conceived to represent objects and their relationships, and is unique in that it is not limited to a hierarchical structure as seen as a graph with object type nodes and relationship type arcs.
The invention has the beneficial effects that: this kind of accurate monitoring method of mikania micrantha based on edge calculation acquires reconnaissance video stream through unmanned aerial vehicle equipment in real time, cuts apart the calculation and obtains the segmentation result in inputing video stream unmanned aerial vehicle equipment main control unit, thereby at last will cut apart the result and transmit back the terminal and realize the monitoring to mikania micrantha, the original image that unmanned aerial vehicle gathered, accurate laxative eradicates this weeds and has established important basis, the practicality value is higher, is fit for using widely.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
an accurate mikania micrantha monitoring method based on edge calculation comprises the following steps:
(1) acquiring data, namely acquiring a plurality of images of a mikania micrantha generation area by using an unmanned aerial vehicle as an original training sample, acquiring a plurality of aerial mikania micrantha images, transmitting the aerial mikania micrantha images to a computer, and splicing the aerial mikania micrantha images acquired from the mikania micrantha acquisition data by the computer for later use;
(2) preprocessing data and manufacturing a training sample, cutting the acquired training sample according to the size of 1024 × 1024 resolution, and then marking a mikania micrantha generation area and a non-mikania micrantha generation area by using different color values by using a marking tool to form a label file, so that a training data sample set is manufactured;
(3) the network model selection and mikania micrantha segmentation model training test is carried out, for a mikania micrantha monitoring task, a D-linknet semantic segmentation network is selected, and the mikania micrantha segmentation model is obtained through the D-linknet semantic segmentation network.
The unmanned aerial vehicle in the step (1) adopts a four-axis aircraft, and the unmanned aerial vehicle is safe, free of faults and low in noise.
And (2) in the step (1), the flying height of the unmanned aerial vehicle is 20m to 30m away from the mikania micrantha canopy, the hyperspectral data acquisition module is carried on the unmanned aerial vehicle platform, the air route is planned, and the aerial flight is carried out in a region where the mikania micrantha grows and is concentrated, so that hyperspectral data are acquired.
The unmanned aerial vehicle in the step (1) is an unmanned aerial vehicle operated by a radio remote control device and a self-contained program control device, or is completely or intermittently autonomously operated by an on-board computer.
And the data preprocessing in the step (2) comprises the steps of sequentially carrying out geometric correction, data noise reduction, radiation correction and band elimination on a training data sample set to be researched.
The training sample in the step (1) is also called a training area, and refers to a typical distribution area of various ground feature types determined by an analyst on a remote sensing image, and the accuracy of the selection and evaluation direct relation classification of the training sample is the key of supervision classification.
The training sample cutting device collected in the step (2) adopts a picture divider, and the picture divider comprises two divisions, three divisions, four divisions, eight divisions, nine divisions, twelve divisions and sixteen divisions, and can be selected according to requirements.
In the step (3), the D-linknet network model adopts linknet as a backbone network, the whole network has a U-shaped structure, and the main body adopts an Encoder-Decoder idea; semantic information is extracted from the image from shallow to deep on the left side, upsampling spatial information recovery is carried out from deep to shallow on the right side, a thermodynamic diagram is finally generated, in order to enhance the fusion of context information in the upsampling process, a hole convolution group serial-parallel model structure is adopted in the middle layer, and the rate parameters of five serial hole convolution groups are respectively 1, 2, 4, 8 and 16.
And (3) training and learning the training data sample set in the step (2) by using a D-linknet network, so as to obtain a mikania micrantha segmentation model, and applying the model to an actual image test to accurately segment the mikania micrantha occurrence region of the farming area in real time.
The network model of step (3) is a flexible way that the database model assumes to represent objects and their relationships, and is unique in that it is not limited to a hierarchical structure as seen as a graph with object type nodes and relationship type arcs.
According to the method, the unmanned aerial vehicle equipment acquires the reconnaissance video stream in real time, the video stream is input into the main controller of the unmanned aerial vehicle equipment to be subjected to segmentation calculation, segmentation results are obtained, and finally the segmentation results are transmitted back to the terminal, so that monitoring of mikania micrantha is achieved.
Example two:
an accurate mikania micrantha monitoring method based on edge calculation comprises the following steps:
(1) acquiring data, namely acquiring a plurality of images of a mikania micrantha generation area by using an unmanned aerial vehicle as an original training sample, acquiring a plurality of aerial mikania micrantha images, transmitting the aerial mikania micrantha images to a computer, and splicing the aerial mikania micrantha images acquired from the mikania micrantha acquisition data by the computer for later use;
(2) preprocessing data and manufacturing a training sample, cutting the acquired training sample according to the size of 1024 × 1024 resolution, and then marking a mikania micrantha generation area and a non-mikania micrantha generation area by using different color values by using a marking tool to form a label file, so that a training data sample set is manufactured;
(3) the network model selection and mikania micrantha segmentation model training test is carried out, for a mikania micrantha monitoring task, a D-linknet semantic segmentation network is selected, and the mikania micrantha segmentation model is obtained through the D-linknet semantic segmentation network.
The unmanned aerial vehicle in the step (1) adopts a four-axis aircraft, and the unmanned aerial vehicle is safe, free of faults and low in noise.
And (2) in the step (1), the flying height of the unmanned aerial vehicle is 20m to 30m away from the mikania micrantha canopy, the hyperspectral data acquisition module is carried on the unmanned aerial vehicle platform, the air route is planned, and the aerial flight is carried out in a region where the mikania micrantha grows and is concentrated, so that hyperspectral data are acquired.
The unmanned aerial vehicle in the step (1) is an unmanned aerial vehicle operated by a radio remote control device and a self-contained program control device, or is completely or intermittently autonomously operated by an on-board computer.
And the data preprocessing in the step (2) comprises the steps of sequentially carrying out geometric correction, data noise reduction, radiation correction and band elimination on a training data sample set to be researched.
The training sample in the step (1) is also called a training area, and refers to a typical distribution area of various ground feature types determined by an analyst on a remote sensing image, and the accuracy of the selection and evaluation direct relation classification of the training sample is the key of supervision classification.
The training sample cutting device collected in the step (2) adopts a picture divider, and the picture divider comprises two divisions, three divisions, four divisions, eight divisions, nine divisions, twelve divisions and sixteen divisions, and can be selected according to requirements.
In the step (3), the D-linknet network model adopts linknet as a backbone network, the whole network has a U-shaped structure, and the main body adopts an Encoder-Decoder idea; semantic information is extracted from the image from shallow to deep on the left side, upsampling spatial information recovery is carried out from deep to shallow on the right side, a thermodynamic diagram is finally generated, in order to enhance the fusion of context information in the upsampling process, a hole convolution group serial-parallel model structure is adopted in the middle layer, and the rate parameters of five serial hole convolution groups are respectively 1, 2, 4, 8 and 16.
And (3) training and learning the training data sample set in the step (2) by using a D-linknet network, so as to obtain a mikania micrantha segmentation model, and applying the model to an actual image test to accurately segment the mikania micrantha occurrence region of the farming area in real time.
The network model of step (3) is a flexible way that the database model assumes to represent objects and their relationships, and is unique in that it is not limited to a hierarchical structure as seen as a graph with object type nodes and relationship type arcs.
According to the method, the original image acquired by the unmanned aerial vehicle lays an important foundation for accurately spraying pesticide to eradicate the weeds, and the practical value is high.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. An edge calculation-based mikania micrantha accurate monitoring method is characterized by comprising the following steps: the method for accurately monitoring the mikania micrantha comprises the following steps:
(1) acquiring data, namely acquiring a plurality of images of a mikania micrantha generation area by using an unmanned aerial vehicle as an original training sample, acquiring a plurality of aerial mikania micrantha images, transmitting the aerial mikania micrantha images to a computer, and splicing the aerial mikania micrantha images acquired from the mikania micrantha acquisition data by the computer for later use;
(2) preprocessing data and manufacturing a training sample, cutting the acquired training sample according to the size of 1024 × 1024 resolution, and then marking a mikania micrantha generation area and a non-mikania micrantha generation area by using different color values by using a marking tool to form a label file, so that a training data sample set is manufactured;
(3) the network model selection and mikania micrantha segmentation model training test is carried out, for a mikania micrantha monitoring task, a D-linknet semantic segmentation network is selected, and the mikania micrantha segmentation model is obtained through the D-linknet semantic segmentation network.
2. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: the unmanned aerial vehicle in the step (1) adopts a four-axis aircraft, and the unmanned aerial vehicle is safe, free of faults and low in noise.
3. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: and (2) in the step (1), the flying height of the unmanned aerial vehicle is 20m to 30m away from the mikania micrantha canopy, the hyperspectral data acquisition module is carried on the unmanned aerial vehicle platform, the air route is planned, and the aerial flight is carried out in a region where the mikania micrantha grows and is concentrated, so that hyperspectral data are acquired.
4. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: the unmanned aerial vehicle in the step (1) is an unmanned aerial vehicle operated by a radio remote control device and a self-contained program control device, or is completely or intermittently autonomously operated by an on-board computer.
5. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: and the data preprocessing in the step (2) comprises the steps of sequentially carrying out geometric correction, data noise reduction, radiation correction and band elimination on a training data sample set to be researched.
6. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: the training sample in the step (1) is also called a training area, and refers to a typical distribution area of various ground feature types determined by an analyst on a remote sensing image, and the accuracy of the selection and evaluation direct relation classification of the training sample is the key of supervision classification.
7. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: the training sample cutting device collected in the step (2) adopts a picture divider, and the picture divider comprises two divisions, three divisions, four divisions, eight divisions, nine divisions, twelve divisions and sixteen divisions, and can be selected according to requirements.
8. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: in the step (3), the D-linknet network model adopts linknet as a backbone network, the whole network has a U-shaped structure, and the main body adopts an Encoder-Decoder idea; semantic information is extracted from the image from shallow to deep on the left side, upsampling spatial information recovery is carried out from deep to shallow on the right side, a thermodynamic diagram is finally generated, in order to enhance the fusion of context information in the upsampling process, a hole convolution group serial-parallel model structure is adopted in the middle layer, and the rate parameters of five serial hole convolution groups are respectively 1, 2, 4, 8 and 16.
9. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: and (3) training and learning the training data sample set in the step (2) by using a D-linknet network, so as to obtain a mikania micrantha segmentation model, and applying the model to an actual image test to accurately segment the mikania micrantha occurrence region of the farming area in real time.
10. The method for accurately monitoring mikania micrantha based on edge calculation as claimed in claim 1, wherein: the network model of step (3) is a flexible way that the database model assumes to represent objects and their relationships, and is unique in that it is not limited to a hierarchical structure as seen as a graph with object type nodes and relationship type arcs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011381532.6A CN112561923A (en) | 2020-12-01 | 2020-12-01 | Mikania micrantha accurate monitoring method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011381532.6A CN112561923A (en) | 2020-12-01 | 2020-12-01 | Mikania micrantha accurate monitoring method based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561923A true CN112561923A (en) | 2021-03-26 |
Family
ID=75045691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011381532.6A Withdrawn CN112561923A (en) | 2020-12-01 | 2020-12-01 | Mikania micrantha accurate monitoring method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561923A (en) |
-
2020
- 2020-12-01 CN CN202011381532.6A patent/CN112561923A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110309933A (en) | Plant plants data measuring method, work route method and device for planning, system | |
| CN111008733B (en) | Crop growth control method and system | |
| CN109117811A (en) | A kind of system and method based on low-altitude remote sensing measuring technique estimation urban vegetation coverage rate | |
| CN108195767A (en) | Estuarine wetland denizen monitoring method | |
| Estornell et al. | Tree extraction and estimation of walnut structure parameters using airborne LiDAR data | |
| CN102708289A (en) | Method for extracting cultivated area of winter wheat in Huang-Huai plain area by moderate resolution satellite data based on winter wheat planting system | |
| CN115641412A (en) | Hyperspectral data-based three-dimensional semantic map generation method | |
| CN117193347B (en) | Unmanned aerial vehicle flight height control method and device, electronic equipment and storage medium | |
| CN112561923A (en) | Mikania micrantha accurate monitoring method based on edge calculation | |
| Kürpick et al. | The influence of logging on a Malaysian dipterocarp rain forest: a study using a forest gap model | |
| Mialet-Serra et al. | Using plant architectural models for estimation of radiation transfer in a coconut-based agroforestry system | |
| Breure | Relevant factors associated with crown expansion in oil palm (Elaeis guineensis Jacq.) | |
| CN115761475A (en) | Online monitoring and recognizing system for corn and wheat seedlings | |
| CN114694048A (en) | Sparse shrub species identification method and system based on unmanned aerial vehicle remote sensing technology | |
| CN115512233A (en) | Multi-temporal remote sensing extraction method for planting attributes of land scale cultivated land | |
| CN114462485A (en) | Red date jujube witches broom initial-stage control method | |
| CN113361377A (en) | Plant growth control model construction method, electronic device and storage medium | |
| Aycart et al. | Low-intensity landscaping of research facilities increased taxonomic, functional and phylogenetic bird diversity in a lowland rainforest | |
| Papić et al. | On Olive Groves Analysis using UAVs | |
| Letsoin et al. | Analysing Maize Plant Height Using Unmanned Aerial Vehicle (UAV) RGB based on Digital Surface Models (DSM) | |
| Atallaoui et al. | Modeling Vegetative and Reproductive Architecture of Date Palm (Phoenix dactylifera L.) The Case of Two Algerian Cultivars ‘Deglet Nour’and ‘Litima’ | |
| Maulidyah et al. | Water Sprouts Detection of Cacao Tree Using Mask Region-based Convolutional Neural Network | |
| Hardanto et al. | Crop stage classification using supervised algorithm based on UAV and Landsat 8 image | |
| Wen et al. | Virtual fruit tree pruning training system based on agent | |
| Anuar et al. | Analyze the Relationship Between Aboveground Biomass and NDVI Values Derived from UAV Multispectral 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210326 |