CN114463403A - Tree carbon sink amount calculation method based on point cloud data and image recognition technology - Google Patents
Tree carbon sink amount calculation method based on point cloud data and image recognition technology Download PDFInfo
- Publication number
- CN114463403A CN114463403A CN202111640468.3A CN202111640468A CN114463403A CN 114463403 A CN114463403 A CN 114463403A CN 202111640468 A CN202111640468 A CN 202111640468A CN 114463403 A CN114463403 A CN 114463403A
- Authority
- CN
- China
- Prior art keywords
- tree
- point cloud
- carbon
- biomass
- data
- 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
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 44
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 44
- 238000005516 engineering process Methods 0.000 title claims abstract description 22
- 238000004364 calculation method Methods 0.000 title claims abstract description 18
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 230000009919 sequestration Effects 0.000 claims abstract 5
- 239000002028 Biomass Substances 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 26
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 8
- 238000009825 accumulation Methods 0.000 claims description 7
- 210000000481 breast Anatomy 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 4
- 239000001569 carbon dioxide Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 241000894007 species Species 0.000 description 13
- 238000012216 screening Methods 0.000 description 8
- 239000002023 wood Substances 0.000 description 6
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000005431 greenhouse gas Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Probability & Statistics with Applications (AREA)
- Optics & Photonics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a tree carbon sink amount calculation method based on point cloud data and an image recognition technology. The carbon sink amount calculation method based on the laser radar point cloud data and the image recognition technology comprises the following steps of: firstly, collecting high-precision LiDAR point cloud data of trees by using laser radar equipment; obtaining specification data of each tree through a single tree division algorithm; then, combining a deep learning image recognition algorithm, and using tree image data to obtain stem density and carbon content calculation factors corresponding to different tree species; and finally, calculating the carbon sink amount of the tree by using a carbon sink estimation formula. The carbon sequestration amount calculation method based on the laser radar point cloud data and the image recognition technology can accurately calculate the carbon sequestration amount of each tree, and has remarkable precision advantage compared with the existing carbon sequestration amount calculation method based on a forest canopy model.
Description
The technical field is as follows:
the invention relates to the technical field of computer technology, laser radar technology and image recognition, in particular to a tree carbon sink amount calculation method based on point cloud data and image recognition technology.
Background art:
since the industrial revolution, the human society has discharged CO in large quantities2The main greenhouse gas causes the greenhouse effect to be enhanced, the global climate to be warmed, a series of ecological problems are caused, and the survival and the development of human beings are seriously threatened. Forests are one of the most important natural resources, the largest organic carbon reservoir in the global terrestrial ecosystem. The accurate estimation of forest resources plays a vital role in the accurate management and management of forest resources in China. Only by accurately estimating the reserve of forest resources, the carbon sink function of the forest can be effectively evaluated, and further the future environmental protection development direction and the greenhouse gas emission reduction target of China are determined.
With the improvement of computer technology and spatial information technology, aerial image data is widely applied to forest resource investigation. Forest canopy models obtained by orthographic and oblique incidence are the data basis for carbon sink amount calculation which is common at present. Although optical remote sensing images and aerial photographs are widely applied, the accuracy of the carbon sink amount calculated based on the forest canopy model is still low due to the influence of spectral and spatial factors on the surface reflectivity of the forest canopy and the limitation of the spectral and spatial structure of the image sensor. The number information extraction method of forest natural resources is improved due to the appearance of airborne LiDAR, the laser radar LiDAR is used as an active remote sensing technology, high-precision forest space structure and under-forest terrain information are obtained by emitting laser energy and receiving return signals, the method has remarkable advantages in the aspect of space structure measurement, and the three-dimensional structure characteristics of the forest can be well described. Meanwhile, deep learning techniques have been widely applied to LiDAR data-based tree classification. However, no one has been able to perform a method for obtaining single tree specification data and tree information to calculate the carbon sink amount of trees after extracting single tree images based on LiDAR data and performing tree species classification by deep learning.
The invention content is as follows:
the present invention has been made in view of the above. The invention aims to provide a tree carbon sink amount calculation method based on point cloud data and an image recognition technology.
According to the tree carbon sink amount calculation method based on the point cloud data and the image recognition technology, the calculation method comprises the following steps:
the method comprises the steps of acquiring LiDAR point cloud and image data of trees by adopting an unmanned aerial vehicle, a backpack type or a vehicle-mounted type laser radar, and selecting different acquisition modes according to different scenes and precision requirements.
The collected point cloud and image data are subjected to denoising processing, and air noise points are removed, so that the data quality is improved.
And performing subdivision on the processed data, separating ground points and ground points, and then performing normalization processing to remove the influence of the terrain on the tree data.
And performing single tree segmentation on the point cloud data by adopting a K-means clustering algorithm based on the processed point cloud data.
The veneer dividing method comprises the following steps:
(1) carrying out same height layering processing on the point cloud by combining ground height information, and extracting a point cloud local maximum value in a layering plane;
(2) performing clustering algorithm processing on the extracted local maximum value of the point cloud to obtain a clustering center point, calculating the distance from the point cloud to the clustering center point, classifying according to a set threshold value and the distance from the point cloud to the clustering center point, calculating the center point of a newly generated class again, and repeating the iteration in the above way, and ending clustering when the position deviation of the center point is smaller than the set threshold value;
(3) setting minimum distance thresholds of different hierarchical clustering center points, screening multi-layer point cloud clustering center points, fusing center points meeting threshold conditions, and obtaining clustered point cloud which is single-tree segmentation data;
(4) and calculating the maximum cross-sectional area of the single-wood point cloud according to the information of the divided single-wood point cloud to serve as the single-wood crown width, taking the center of the trunk point cloud with the same height as the position coordinate of the single wood, and taking the highest point of the point cloud as the tree height of the single wood.
And selecting point cloud data at a position 130cm away from the ground according to the data obtained after the single tree segmentation, and extracting the breast height (DBH) of the tree by adopting a fitting circle mode.
The method comprises the steps of obtaining image information of a single tree by utilizing point cloud data collected by a laser radar and image data obtained by synchronous shooting in a correlation mode, carrying out classification marking processing on collected massive tree image data, obtaining a tree species high-precision object detection model through iterative training of fast R-CNN, SSD and YOLO (least squares) target detection technologies, automatically processing image data obtained after single tree segmentation in batch after releasing a deployment model, and obtaining accurate tree species information of the single tree.
Calculating the carbon sink amount of the tree by a biomass inventory method based on the obtained tree related data and the tree species information, wherein the carbon sink formula is C ═ V × D/R × Cc/TcWherein V is the amount of tree accumulation; d is the trunk density; r is the ratio of the biomass of the trunk to the biomass of the tree; ccIs the carbon content in the plant; t iscIs the ratio of the molecular weight of the carbon element to the molecular weight of carbon dioxide (3/11).
Description of the drawings:
fig. 1 is a technical route diagram of a tree carbon sink calculation method based on point cloud data and an image recognition technique.
FIG. 2 shows the trunk density of each tree species obtained by the research of the institute of forestry science, China in 1982.
FIG. 3 is a plot of trunk biomass as a proportion of tree biomass collated from the results of Wangxicaceae 1998 study on forest ecosystem biomass in China.
The specific implementation mode is as follows:
in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
A tree carbon sink amount calculation method based on point cloud data and an image recognition technology is composed of tree point cloud information acquisition, point cloud data single tree segmentation, tree species image recognition technology and carbon sink amount calculation of a biomass inventory method. The point cloud information is acquired while images are acquired synchronously to ensure the integrity of data.
Further, the tree point cloud information collection is divided into three collection modes, namely unmanned aerial vehicle laser radar, vehicle-mounted laser radar and backpack laser radar. The unmanned aerial vehicle laser radar can acquire ground target space data in a large range from high altitude through different visual angles and automatic route routes, the backpack laser radar can acquire high-precision three-dimensional point cloud data with a scanning range of 0-360 degrees horizontally and-90-degrees vertically under a shielded complex scene, and the vehicle-mounted laser radar is suitable for moving to acquire roadside ground feature and tree information. And customizing different single or mixed acquisition modes according to different scenes and precision requirements.
Further, the lidar is greatly affected by weather and atmosphere when working. The laser is less attenuated in a clear weather and has a longer propagation distance. In bad weather such as heavy rain, heavy smoke, heavy fog, and the like, attenuation is increased rapidly, and the propagation distance is greatly influenced. The atmospheric circulation can also distort and shake the laser beam, and directly influences the measurement accuracy of the laser radar. Therefore, the field needs to be selected to collect on sunny weather.
Furthermore, in the process of collecting the point cloud data by using the laser radar equipment, unnecessary shielding needs to be reduced, for example, a backpack radar needs to be carried out in an environment with less personnel flow, and the point cloud data is prevented from being lost due to excessive shielding, so that the subsequent processing of the point cloud data is prevented from being influenced. Meanwhile, the radar scanning coverage area is considered when the route is established, and more complete point cloud result data is guaranteed to be obtained.
Furthermore, video data need to be synchronously acquired when laser radar is used for scanning, and the point cloud data and the video data are associated by depending on an accurate positioning track and a time stamp in the acquisition process to form a basis for separating and acquiring the tree image.
Further, the collected point cloud data needs to be further processed to form single-tree segmentation result data. The method is roughly divided into seven steps: (1) removing air noise and improving data quality; (2) separating ground points from the point cloud data; (3) the ground point data is classified finely, and the classification precision is improved; (4) normalizing the point cloud to remove the influence of the terrain; (5) and selecting point cloud data at a position 1.3 meters away from the ground, extracting the tree breast Diameter (DBH) by adopting a circle fitting mode, and acquiring the tree ID, the breast diameter and the number of plants. If the tree grows obliquely, a fitting cylinder method is adopted; if the trunk is an ellipse, fitting a two-dimensional ellipse by using the plane coordinates of the point cloud data and using least squares; (6) and checking and editing the fitting result through a single-wood screening tool, and displaying, hiding, deleting and extracting the DBH fitting result according to the screening range. The screening operation comprises the following steps: screening by confidence, screening by tree ID, screening by DBH, and screening by tree height. (7) The DBH fitting results can be saved as a csv file containing the tree ID, the location of the tree, and the DBH.
Further, tree species recognition based on deep learning is carried out on the individual plant data after the individual plant segmentation. Before tree species are identified, a sufficient amount of tree samples to be detected need to be collected, iterative labeling is carried out on training tree samples depending on target detection technologies such as fast R-CNN, SSD and YOLO, a tree species high-precision object detection model is obtained by adjusting iterative detection according to a regression rate, an image obtained by cutting a single tree is identified after a deployment model is issued, and tree species information is obtained automatically in batches.
Furthermore, after the information of the single tree is extracted, carbon sink calculation can be carried out according to a biomass inventory method. The biomass list method is to calculate the biomass of each tree species according to the accumulation amount and the trunk density of each tree species; then, calculating the biomass of the tree according to the proportion of the trunk biomass to the biomass of the tree; then theAnd calculating the carbon sink amount of the tree according to the carbon density of the tree species. The estimation formula is that C is V multiplied by D/R multiplied by Cc/TcAcquiring the carbon sink amount of the tree, wherein V is the accumulation amount of the tree; d is the trunk density, and as the trunk densities of different trees are different, in order to accurately estimate the biomass of different trees, the result is rearranged according to the results measured by the institute of forestry and science, China in 1982 and shown in the figure I; r is the proportion of the trunk biomass to the tree biomass, and the proportion of the trunk biomass to the tree biomass is shown in figure two, which is obtained according to the research result of Wangxicake on the biomass of Chinese forest ecosystems in 1998; ccIs the carbon content in the plant; t iscIs the ratio of the molecular weight of the carbon element to the molecular weight of carbon dioxide (3/11). The accumulation (V) of the tree is represented by V ═ pi × r2The formula of x H is calculated, wherein r is the position 130cm away from the ground, and the DBH (diameter at breast height)/2 of the tree; h is the tree height (meters).
Claims (7)
1. A tree carbon sink amount calculation method based on point cloud data and an image recognition technology is characterized by comprising the following steps:
acquiring complete tree LiDAR point cloud and image data through unmanned aerial vehicle-mounted, vehicle-mounted and backpack mobile laser radar acquisition equipment;
performing interior processing on LiDAR point cloud data to remove aerial noise and improve data quality, segmenting the data by using a single-tree segmentation technology, and extracting the breast diameter and crown area of each tree in a fitting cylinder mode;
acquiring tree species information of a tree by using image information of a single tree and utilizing a tree species identification technology based on deep learning;
carbon sequestration estimation formula C ═ V × D/R × C based on biomass inventory methodc/TcAcquiring the carbon sink amount of the tree, wherein V is the accumulation amount of the tree; d is the trunk density; r is the ratio of the biomass of the trunk to the biomass of the tree; ccIs the carbon content in the plant; t iscIs the ratio of the molecular weight of the carbon element to the molecular weight of carbon dioxide (3/11).
2. The tree carbon sink amount calculation method based on point cloud data and image recognition technology of claim 1, wherein the collection device adopts an unmanned aerial vehicle, a backpack type or a vehicle-mounted type laser radar, and different implementation modes are selected according to different scenes and precision requirements. The unmanned aerial vehicle laser radar can acquire ground target space data in a large range from high altitude by planning different visual angles and automatic route routes, the backpack laser radar can acquire high-precision three-dimensional point cloud and image data of a scanning range of 0-360 degrees horizontally and-90 degrees vertically under a shielded complex scene, and the vehicle-mounted laser radar is suitable for moving to acquire roadside tree information. After field collection is completed, point cloud data needs to be processed, including removing noise point data in point cloud, separating and classifying ground points to remove influence of terrain on tree height, and normalizing the point cloud data.
3. The method for calculating the amount of carbon sequestration for trees according to claim 1, wherein the single-tree segmentation technique uses K-means clustering algorithm to perform single-tree segmentation on the point cloud information scanned by laser radar, performs same-height hierarchical processing on the point cloud in combination with ground height information, extracts local maximum values in hierarchical planes, performs clustering algorithm processing on the extracted maximum values to obtain clustering center points, calculates the distance between the point cloud and the clustering center points, classifies the point cloud according to the set threshold value and the distance between the point cloud and the center point, calculates the center point of a newly generated class again, iterates in such a cycle, finishes clustering when the final center point position deviation is smaller than the set threshold value, sets the minimum distance threshold values of different hierarchical clustering center points, screens the clustering center points of multi-layer point clouds, and fuses the center points meeting the threshold condition, the clustered point cloud is single-tree segmentation data, the maximum cross-sectional area of the single-tree point cloud is calculated according to the information of the segmented single-tree point cloud to serve as the crown width of the single tree, the center of the trunk point cloud with the same height as the local ground is used as the position coordinate of the single tree, and the highest point of the point cloud serves as the tree height of the single tree.
4. The method for calculating the carbon sink amount of the tree according to claim 1, wherein the tree species recognition technology acquires image information of a single tree by associating point cloud data acquired by laser radar and image data acquired by synchronous shooting, classifies and marks the acquired image data of the large number of trees, acquires a tree species high-precision object detection model through iterative training of fast R-CNN, SSD and YOLO, and automatically processes image data after single tree segmentation in batch after releasing the deployment model to acquire accurate tree species information of the single tree.
5. The method of claim 1, wherein the biomass inventory method is a plant carbon storage estimation method based on biomass-storage relationship, and the estimation formula is C-V x D/R x Cc/TcWherein V is the amount of tree accumulation; d is the trunk density; r is the ratio of the biomass of the trunk to the biomass of the tree; ccIs the carbon content in the plant; t iscIs the ratio of the molecular weight of the carbon element to the molecular weight of carbon dioxide (3/11).
6. The biomass inventory method of claim 5, wherein the biomass inventory method calculates the biomass of each tree species based on the accumulation and trunk density of each tree species; then, calculating the biomass of the tree according to the proportion of the trunk biomass to the biomass of the tree; and then calculating the carbon sink amount of the tree according to the carbon density of the tree species.
7. The biomass inventory method of claim 5, wherein the amount of trees (V) accumulated is selected from the group consisting of V pi x r2The formula of x H is calculated, wherein r is the position 130cm away from the ground, and the DBH (diameter at breast height)/2 of the tree; h is the tree height (meters).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111640468.3A CN114463403A (en) | 2021-12-29 | 2021-12-29 | Tree carbon sink amount calculation method based on point cloud data and image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111640468.3A CN114463403A (en) | 2021-12-29 | 2021-12-29 | Tree carbon sink amount calculation method based on point cloud data and image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114463403A true CN114463403A (en) | 2022-05-10 |
Family
ID=81407690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111640468.3A Pending CN114463403A (en) | 2021-12-29 | 2021-12-29 | Tree carbon sink amount calculation method based on point cloud data and image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114463403A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114894254A (en) * | 2022-07-13 | 2022-08-12 | 四川省林业和草原调查规划院(四川省林业和草原生态环境监测中心) | Dynamic metering method for carbon sink of single-plant wood |
| CN115512244A (en) * | 2022-08-19 | 2022-12-23 | 中国林业科学研究院资源信息研究所 | Method and system for determining carbon reserve of single tree |
| CN115578602A (en) * | 2022-11-09 | 2023-01-06 | 北京信息科技大学 | Natural tree species identification method based on improved YOLOv7 |
| CN115936953A (en) * | 2023-01-06 | 2023-04-07 | 深圳润澄金景科技服务有限公司 | Carbon sink calculation method, electronic device and storage medium |
| CN116311010A (en) * | 2023-03-06 | 2023-06-23 | 中国科学院空天信息创新研究院 | Method and system for woodland resource investigation and carbon sink metering |
| CN116429988A (en) * | 2023-06-09 | 2023-07-14 | 海南中南标质量科学研究院有限公司 | Dynamic remote sensing monitoring device for ocean plant carbon sink |
| CN116992191A (en) * | 2023-09-27 | 2023-11-03 | 西安中碳环境科技有限公司 | Forest carbon sink dynamic monitoring and evaluating system driven by multi-source remote sensing data |
| CN117036944A (en) * | 2023-08-09 | 2023-11-10 | 中科海慧（天津）科技有限公司 | Tree carbon sink amount calculating method and system based on point cloud data and image recognition |
| CN117114194A (en) * | 2023-08-30 | 2023-11-24 | 北京林业大学 | Method and device for determining carbon sink quantity and optimizing carbon sink benefit and related equipment |
-
2021
- 2021-12-29 CN CN202111640468.3A patent/CN114463403A/en active Pending
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114894254B (en) * | 2022-07-13 | 2022-11-08 | 四川省林业和草原调查规划院(四川省林业和草原生态环境监测中心) | Dynamic metering method for carbon sink of single-plant wood |
| US11921097B2 (en) | 2022-07-13 | 2024-03-05 | Sichuan Provincial Institute of Forestry and Grassland Inventory and Planning | Method for dynamic measurement of individual tree carbon sink |
| CN114894254A (en) * | 2022-07-13 | 2022-08-12 | 四川省林业和草原调查规划院(四川省林业和草原生态环境监测中心) | Dynamic metering method for carbon sink of single-plant wood |
| CN115512244B (en) * | 2022-08-19 | 2024-01-05 | 中国林业科学研究院资源信息研究所 | Method and system for determining carbon reserves of single tree |
| CN115512244A (en) * | 2022-08-19 | 2022-12-23 | 中国林业科学研究院资源信息研究所 | Method and system for determining carbon reserve of single tree |
| CN115578602A (en) * | 2022-11-09 | 2023-01-06 | 北京信息科技大学 | Natural tree species identification method based on improved YOLOv7 |
| CN115936953A (en) * | 2023-01-06 | 2023-04-07 | 深圳润澄金景科技服务有限公司 | Carbon sink calculation method, electronic device and storage medium |
| CN116311010A (en) * | 2023-03-06 | 2023-06-23 | 中国科学院空天信息创新研究院 | Method and system for woodland resource investigation and carbon sink metering |
| CN116429988B (en) * | 2023-06-09 | 2024-02-13 | 海南中南标质量科学研究院有限公司 | Dynamic remote sensing monitoring device for ocean plant carbon sink |
| CN116429988A (en) * | 2023-06-09 | 2023-07-14 | 海南中南标质量科学研究院有限公司 | Dynamic remote sensing monitoring device for ocean plant carbon sink |
| CN117036944A (en) * | 2023-08-09 | 2023-11-10 | 中科海慧（天津）科技有限公司 | Tree carbon sink amount calculating method and system based on point cloud data and image recognition |
| CN117036944B (en) * | 2023-08-09 | 2024-03-01 | 中科海慧（天津）科技有限公司 | Tree carbon sink amount calculating method and system based on point cloud data and image recognition |
| CN117114194A (en) * | 2023-08-30 | 2023-11-24 | 北京林业大学 | Method and device for determining carbon sink quantity and optimizing carbon sink benefit and related equipment |
| CN117114194B (en) * | 2023-08-30 | 2024-03-08 | 北京林业大学 | Method and device for determining carbon sink quantity and optimizing carbon sink benefit and related equipment |
| CN116992191B (en) * | 2023-09-27 | 2023-12-08 | 西安中碳环境科技有限公司 | Forest carbon sink dynamic monitoring and evaluating system driven by multi-source remote sensing data |
| CN116992191A (en) * | 2023-09-27 | 2023-11-03 | 西安中碳环境科技有限公司 | Forest carbon sink dynamic monitoring and evaluating system driven by multi-source remote sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114463403A (en) | Tree carbon sink amount calculation method based on point cloud data and image recognition technology | |
| Guerra-Hernández et al. | Comparison of ALS-and UAV (SfM)-derived high-density point clouds for individual tree detection in Eucalyptus plantations | |
| Miraki et al. | Individual tree crown delineation from high-resolution UAV images in broadleaf forest | |
| Ferraz et al. | 3-D mapping of a multi-layered Mediterranean forest using ALS data | |
| Van Leeuwen et al. | Retrieval of forest structural parameters using LiDAR remote sensing | |
| CN107085710B (en) | Single-tree automatic extraction method based on multispectral LiDAR data | |
| CN111898688B (en) | Airborne LiDAR data tree classification method based on three-dimensional deep learning | |
| CN109164459A (en) | A kind of method that combination laser radar and high-spectral data classify to forest species | |
| Dong et al. | Multi-layered tree crown extraction from LiDAR data using graph-based segmentation | |
| CN108896021B (en) | Method for extracting artificial forest stand structure parameters based on aerial photogrammetry point cloud | |
| CN112907520A (en) | Single tree crown detection method based on end-to-end deep learning method | |
| Panagiotidis et al. | Detection of fallen logs from high-resolution UAV images | |
| CN115690081A (en) | Tree counting method, system, storage medium, computer equipment and terminal | |
| Hakula et al. | Individual tree segmentation and species classification using high-density close-range multispectral laser scanning data | |
| Dersch et al. | Towards complete tree crown delineation by instance segmentation with Mask R–CNN and DETR using UAV-based multispectral imagery and lidar data | |
| Millikan et al. | Automated individual tree detection in Amazon tropical forest from airborne laser scanning data | |
| Wang et al. | A wavelet-based echo detector for waveform LiDAR data | |
| Liu et al. | Detection of Firmiana danxiaensis canopies by a customized imaging system mounted on an UAV platform | |
| You et al. | Segmentation of individual mangrove trees using UAV-based LiDAR data | |
| CN114078211A (en) | Method for intelligently detecting tree lodging based on laser radar | |
| Maizah Saad et al. | Tree stump height estimation using canopy height model at tropical forest in Ulu Jelai Forest Reserve, Pahang, Malaysia | |
| CN114862872B (en) | Mangrove single wood segmentation method based on Faster R-CNN | |
| Azizi et al. | Individual urban trees detection based on point clouds derived from UAV-RGB imagery and local maxima algorithm, a case study of Fateh Garden, Iran | |
| Westin | Quantification of a continuous-cover forest in Sweden using remote sensing techniques | |
| Hyyppä et al. | Forest inventory using laser scanning |
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 |