CN109816779A - A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter - Google Patents
A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter Download PDFInfo
- Publication number
- CN109816779A CN109816779A CN201910091334.7A CN201910091334A CN109816779A CN 109816779 A CN109816779 A CN 109816779A CN 201910091334 A CN201910091334 A CN 201910091334A CN 109816779 A CN109816779 A CN 109816779A
- Authority
- CN
- China
- Prior art keywords
- forest
- artificial
- smart phone
- model
- tree
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000000605 extraction Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 5
- 239000002023 wood Substances 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000001788 irregular Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 210000000323 shoulder joint Anatomy 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 12
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000012800 visualization Methods 0.000 abstract description 2
- 244000166124 Eucalyptus globulus Species 0.000 description 9
- 241000018651 Pinus tabuliformis Species 0.000 description 6
- 235000011610 Pinus tabuliformis Nutrition 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000000052 comparative effect Effects 0.000 description 4
- 238000007598 dipping method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The present invention discloses a kind of method for rebuilding the single wooden parameter of artificial forest forest model acquisition using smart phone, suitable for the acquisition of artificial forest forest model and forest inventory investigation, belong to computer vision in forestry applications technical field scope, key technology main points include: 1. using smart phone acquisition forest image information;2. obtaining artificial forest forest model using for the improved three-dimensional reconstruction algorithm of forestry;3. measuring single wooden parameter in artificial forest forest model.The critical problem of solution includes: 1. photos that need to obtain target forest land using smart phone in ground investigation, reduces ground investigation workload, investigation efficiency is greatly improved;2. obtaining, visualization artificial forest forest model measure and precision is higher, and human factor is avoided to influence.The invention be suitable for can and and the preferable artificial forest of hayashishita visual environment, be the method for obtaining artificial forest forest model using smart phone for the first time and measuring single wooden parameter, achievement can provide basic data foundation for the investigation work of artificial forest resource fast accurate.
Description
One, technical field
The present invention relates to the artificial forest forest model weights in a kind of computer vision and the crossing domain of forest inventory investigation
Construction method, especially a kind of method for rebuilding artificial forest forest model using smart phone, is obtained suitable for artificial forest forest model
It takes and forest inventory investigation, belongs to computer vision in forestry applications technical field.
Two, technical background
Tree height, the diameter of a cross-section of a tree trunk 1.3 meters above the ground and hat width are single wooden parameters important when carrying out forest inventory investigation, they pass through calculating list respectively
The difference on ebon vertex and tree bottom point, trunk width, the north and south of forest tree crown and east-west direction width at 1.3 meters of Distance-Tree bottom point
Average value react tree growth situation, to complete stand' grade and formulate reasonable Operation Measures.In traditional forest
In investigation method, mainly by artificial every wooden dipping, but there are apparent shortcoming and defect for the conventional method:
(1) artificial limited viewing angle, tall and big forest leafiness for branch, it is difficult to accurate observation to tree crown top to top
Situation;
(2) artificial observation is difficult to accurately obtain forest profile and border, and visual measurement accuracy is low, and human error is big;
(3) artificial observation heavy workload, required time length, inefficiency exist very big in the investigation of a wide range of artificial forest
Limitation.
Therefore, in single wooden forest parameter measurement work, conventional method precision is low, low efficiency, is badly in need of a kind of using calculating
Machine vision means rebuild artificial forest forest model, and measure forest parameter according to model to promote estimated accuracy and estimated efficiency
Method, to provide strong technical support for artificial forest forest survey.
Three, summary of the invention
Existing low precision and poor efficiency when in order to solve the problems, such as that the traditional artificial woods forest reserves manually measure, the present invention
Purpose be to provide a kind of method for using smart phone rebuilding artificial forest forest model to obtain single wooden parameter.It is convenient that it passes through
The forest photo that taking photograph of intelligent mobile phone rapidly and efficiently obtains carries out the reconstruction of artificial forest forest model, and to list on model
The wooden parameter is measured, and is realized the efficient accurate acquisition of single wooden parameter, is promoted working efficiency and precision, overcome traditional artificial every wood
The shortcomings that dipping.
The object of the present invention is achieved like this: it is taken pictures around sample to measurement target region using smart phone,
Forest photo is obtained, and is independently ground in VisualStudio compiler using C++ development language and open source pcl points cloud processing library
Send out artificial forest forest model reconstruction software system, pass sequentially through camera Calibration, sequence image enhancing, feature detection, characteristic matching,
Sparse reconstruction and point cloud encrypting step complete forest Model Reconstruction, after carrying out single wooden dividing processing to forest model, measure
To single wooden diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree height and hat width parameter.
The present invention has the advantage that compared with the analytic method of traditional visually judgement and the single wooden parameter of up short estimation
(1) it only needs surrounding target region take pictures and obtain image photograph, compares conventional method, greatly reduce ground survey
The workload of amount shortens the field survey time, only needs to the square-like that 20 meters of side length 15 minutes photo opporunities, data acquisition is fast
Speed, flow chart of data processing is simple, it can be achieved that automation acquisition, promotes working efficiency;
(2) the true three-dimension point cloud of the available forest of this method in space carries out geometric solution with for forest image
Analysis method pro form bill wood parameter is compared, and compensates for the short slab that geometrical analysis is unable to get true threedimensional model, and obtain artificial
Woods forest model can be directly used for forest visualization and manage;
(3) geometrical analysis method is all made of model of fit approximation and obtains parameter, and precision is difficult to improve, in forest mould in this method
Single wooden parameter is measured in type can promote accuracy in measurement, more objective accurate, avoid staff's level to the shadow of measurement result
It rings.
Four, Detailed description of the invention:
The present invention is further described with example with reference to the accompanying drawing.
Fig. 1 is main technical flows figure of the invention;
Fig. 2 is image enhancement technique flow chart;
Fig. 3 is the increased vertically and horizontally both direction relevant to forest parameter on the basis of SURF feature detective operators
Constraint condition;
Fig. 4 is independent research artificial forest forest model reconstruction software system interface;
Fig. 5 is eucalyptus plantation forest model reconstructed results;
The comparison of Fig. 6 for Chinese pine sample single wooden parameter extraction result and every wooden dipping result;
The comparison of Fig. 7 for eucalyptus sample single wooden parameter extraction result and every wooden dipping result;
Five, specific embodiment:
The present invention: a method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter, the method
The following steps are included:
Step 1: it using having the smart phone of tight shot to carry out multi-angled shooting to standard gridiron pattern scaling board, obtains
Take camera intrinsic parameter;
Step 2: it is taken pictures clockwise with fixed step size surrounding target region using calibrated smart phone, in time
Check photographic quality, it is desirable that reference object is clear;
Step 3: the sequence photographs of shooting are passed sequentially through according to different intensities of illumination, the density of crop and tree species type
Adaptive median filter improves saturation degree, high-pass filtering operation progress image enhancement;
Step 4: enhanced image is loaded into from research and development artificial forest forest model reconstruction software system, is used
Harris corner detection operator carries out multiple scale detecting according to form feature and increases trunk characteristic point quantity, while in SURF spy
Increase the constraint condition in horizontal and vertical both direction on the basis of sign point detective operators, extracts related to single wooden characteristic parameter
Characteristic point cluster;
Step 5: the forest characteristic point that successively will test to carry out characteristic matching, sparse Forest reestablishment characteristic point cloud and
Point cloud plane trigonometry net iterative interpolation encryption;
Step 6: encrypted point cloud data is used into seven-parameter transformation model, it is assumed that A (Xa, Ya, Za) is known coordinate
It is coordinate, B (Xb, Yb, Zb) is coordinate system coordinate undetermined, then has:
Wherein, Tx, Ty, Tz are three translation parameters, and m is a scale parameter, and ω x, ω y, ω z are three rotation parameters.
If the respective coordinates under known three pairs or more of two rectangular coordinate system in space, two space right-angles can be solved according to formula (1)
Seven parameter of conversion between coordinate system, then can be by the point cloud data of generation also according to formula (1) using seven parameter of transformation model
Relative spatial co-ordinates are converted to the coordinate under the earth rectangular coordinate system in space.
Step 7: filtering algorithm is encrypted using asymptotic irregular triangle network, whole point cloud data is separated into tree point cloud
With ground point cloud;
Step 8: tree point cloud is normalized using ground point cloud data, by the tree point cloud after normalization
Single wood segmentation is carried out using Kmeans hierarchical cluster partitioning algorithm;
Step 9: by being defined in artificial forest forest model according to tree height, the diameter of a cross-section of a tree trunk 1.3 meters above the ground and hat width of the point cloud data after segmentation
It is measured, obtains single wooden parameter.
To verify this method validity and measurement accuracy, applicant uses Some Regions in Inner Mongolia Chinese pine plantation
Single wooden parameter is obtained using this method as experimental subjects with Guangxi Zhuang Autonomous Region part eucalyptus plantation, and compares ground
Measured value calculates error.Pinus tabulaeformis forest extraction of values and measured value comparative situation are shown in Table 1, Eucalyptus Stand extraction of values and measured value comparative situation
It is shown in Table 2.
1 Pinus tabulaeformis forest extraction of values of table and measured value comparative situation
Chinese pine mature forest is located in the forest farm Wang Yedian of Chifeng, and sample area 20m*20m, the gradient is larger, sample
16 plants of Chinese pines are inside shared, due to sample the gradient is larger, and Canopy densities are higher, and the forest photo of ground shooting lacks single wooden side
Edge information and treetop information, last complete extraction go out that the diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree be high, trees of three values of hat width have 11, and reconstruction rate is
68.75%.It is compared by the diameter of a cross-section of a tree trunk 1.3 meters above the ground of model extraction, tree height, hat width value and measured data, it can be seen that the chest of model extraction
Diameter value error is smaller, average relative error 4.26%, and sets high generally lower than measured value with hat width, average relative error difference
Reach 13.95% and 25.25%.In practical general artificial forest, seeding row spacing is fixed, and Canopy densities are moderate, can be restored more
Add fine forest marginal information and treetop position, single wooden parameter extraction precision can be increased to 90% or more, meet application and want
It asks.
2 Eucalyptus Stand extraction of values of table and measured value comparative situation
The age of stand is located at Nanning peak forest farm in eucalyptus, sample area 20m*20m, gentle gradient, shares in sample ground
29 plants of eucalyptus, but Eucalyptus is rapid, 3-5 can become a useful person, eucalyptus is intensive in test plot and hat width smaller (even crown diameter is small
In 2m), the forest image got lacks marginal information, and last complete extraction goes out the trees 21 of three diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree height, hat width values
, reconstruction rate is 72.41%.It is compared by the diameter of a cross-section of a tree trunk 1.3 meters above the ground of model extraction, tree height, hat width value and measured data, the diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree are high
1.35%, 9.17%, 45.22% has been respectively reached with the average relative error of hat width.Although this method is in terms of hat width extraction
Error is larger, but is above 90% in the high extraction accuracy with the diameter of a cross-section of a tree trunk 1.3 meters above the ground of tree, can satisfy basic Forestry Investigation demand.
In conclusion the present invention is suitable for, strain spacing is uniform, and Canopy densities are moderate and even crown diameter is artificial greater than 2m
Carry out forest model acquisition and forest inventory investigation to woods sample.
Claims (3)
1. a kind of rebuild the method that artificial forest forest model obtains single wooden parameter using smart phone, it is characterized in that:
It carries out surrounding shooting to obtain image using smart phone surrounding target forest land and restores artificial using own software systems
Woods forest model, after carrying out coordinate conversion and single wood dividing processing to model, extraction obtains single wooden diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree height and hat width number
According to.
2. according to claim 1 obtain artificial forest image using smart phone, it is characterized in that:
With the smart phone with tight shot in artificial forest, with selecting the sample of different condition area and environment, delimitation will be surveyed
The standard site (20m*20m) of amount, around sample with the shooting of same direction pitch of the laps, translating step about 1m, distance of camera lens is to look squarely
Image includes that ground is advisable to the first clear bole height;As axle center flat bat from top to bottom and the shooting posture of bat is faced upward every using shoulder joint
A point shoots three photos, until completely shooting a circle around sample, with obtaining the sample of horizontal, longitudinal high degree of overlapping (being greater than 80%)
Photograph;It to keep camera lens to stablize when shooting as far as possible, prevent from shaking, check photo quality in time, with shooting clear and completely include
Forest image is advisable, if retake will be carried out in time by finding that photo quality is poor.
3. single wooden parameter acquiring method according to claim 1, it is characterized in that:
Using computer vision thought, it is sequentially completed the calibration of smart phone camera Zhang Zhengyou gridiron pattern method, in conjunction with forest feature pair
The sequence image of acquisition is filtered operation, is combined using Harris Corner Detection with the detection of SURF characteristic point and complete forest feature
Characteristic point is encrypted 6 to characteristic matching, sparse Forest reestablishment characteristic point cloud and point cloud plane trigonometry net iterative interpolation is carried out by detection
A step is completed artificial forest forest model and is rebuild, and the point cloud coordinate after reconstruction is converted to the seat under the earth rectangular coordinate system in space
Mark encrypts filtering algorithm by asymptotic irregular triangle network and a cloud is separated into tree point cloud and ground point cloud, uses Kmeans
Hierarchical cluster partitioning algorithm segmentation normalization tree point cloud, according to tree, the definition of the high, diameter of a cross-section of a tree trunk 1.3 meters above the ground and hat width is measured on Individual tree model
Single wood parameter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910091334.7A CN109816779A (en) | 2019-01-30 | 2019-01-30 | A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910091334.7A CN109816779A (en) | 2019-01-30 | 2019-01-30 | A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816779A true CN109816779A (en) | 2019-05-28 |
Family
ID=66605997
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910091334.7A Pending CN109816779A (en) | 2019-01-30 | 2019-01-30 | A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816779A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110207670A (en) * | 2019-06-26 | 2019-09-06 | 北京林业大学 | A method of artificial forest forest hat width parameter is obtained using two dimensional image |
CN111008983A (en) * | 2019-12-06 | 2020-04-14 | 国网湖南省电力有限公司 | Crown multi-threshold segmentation method and system applicable to power transmission line tree height monitoring device |
CN111462312A (en) * | 2020-04-01 | 2020-07-28 | 中国林业科学研究院资源信息研究所 | Dynamic visual simulation method and system for subbranch height considering spatial structure |
CN112991519A (en) * | 2021-03-16 | 2021-06-18 | 中国林业科学研究院资源信息研究所 | Method for solving tree crown branch cross overlapping of three-dimensional model of conifer in forest stand |
CN113009481A (en) * | 2021-01-15 | 2021-06-22 | 扬州哈工科创机器人研究院有限公司 | Forest surface feature imaging inversion method based on interferometric SAR radar |
CN113269825A (en) * | 2021-04-06 | 2021-08-17 | 云南师范大学 | Forest breast diameter value extraction method based on foundation laser radar technology |
CN114777703A (en) * | 2022-04-25 | 2022-07-22 | 贵州省第三测绘院(贵州省国土资源遥感监测中心) | Forestry sample plot accurate positioning method and device based on distance matching |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018084472A (en) * | 2016-11-22 | 2018-05-31 | 国立大学法人信州大学 | Forest resource information calculation method and forest resource information calculation device |
CN109269430A (en) * | 2018-08-12 | 2019-01-25 | 浙江农林大学 | The more plants of standing tree diameter of a cross-section of a tree trunk 1.3 meters above the ground passive measurement methods based on depth extraction model |
CN109285145A (en) * | 2018-08-12 | 2019-01-29 | 浙江农林大学 | The more plants of standing tree height measurement methods based on smart phone |
-
2019
- 2019-01-30 CN CN201910091334.7A patent/CN109816779A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018084472A (en) * | 2016-11-22 | 2018-05-31 | 国立大学法人信州大学 | Forest resource information calculation method and forest resource information calculation device |
CN109269430A (en) * | 2018-08-12 | 2019-01-25 | 浙江农林大学 | The more plants of standing tree diameter of a cross-section of a tree trunk 1.3 meters above the ground passive measurement methods based on depth extraction model |
CN109285145A (en) * | 2018-08-12 | 2019-01-29 | 浙江农林大学 | The more plants of standing tree height measurement methods based on smart phone |
Non-Patent Citations (8)
Title |
---|
丁为民等: "基于机器视觉的果树树冠体积测量方法研究", 《农业机械学报》 * |
冯仲科等: "创建新一代森林资源调查监测技术体系的实践与探索", 《林业资源管理》 * |
张超,王雪峰,李海奎: "立体视觉技术在森林资源调查中的应用" * |
杨书娟等: "螺旋式扫描激光雷达数据的DEM内插算法", 《中国激光》 * |
毛沂新: "无人机遥感在林业调查领域的应用", 《吉林林业科技》 * |
王佳等: "利用轻小型飞机遥感数据建立人工林特征参数模型", 《农业工程学报》 * |
王邱文等: "一种新的样地调查方法――七株木法", 《林业资源管理》 * |
程文生等: "便携式森林资源调查仪研制与试验", 《西北林学院学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110207670A (en) * | 2019-06-26 | 2019-09-06 | 北京林业大学 | A method of artificial forest forest hat width parameter is obtained using two dimensional image |
CN110207670B (en) * | 2019-06-26 | 2021-09-21 | 北京林业大学 | Method for acquiring crown width parameters of artificial forest by using two-dimensional image |
CN111008983A (en) * | 2019-12-06 | 2020-04-14 | 国网湖南省电力有限公司 | Crown multi-threshold segmentation method and system applicable to power transmission line tree height monitoring device |
CN111462312A (en) * | 2020-04-01 | 2020-07-28 | 中国林业科学研究院资源信息研究所 | Dynamic visual simulation method and system for subbranch height considering spatial structure |
CN113009481A (en) * | 2021-01-15 | 2021-06-22 | 扬州哈工科创机器人研究院有限公司 | Forest surface feature imaging inversion method based on interferometric SAR radar |
CN112991519A (en) * | 2021-03-16 | 2021-06-18 | 中国林业科学研究院资源信息研究所 | Method for solving tree crown branch cross overlapping of three-dimensional model of conifer in forest stand |
CN112991519B (en) * | 2021-03-16 | 2023-10-31 | 中国林业科学研究院资源信息研究所 | Method for solving cross overlapping of conifer tree three-dimensional model crown branches in forest stand |
CN113269825A (en) * | 2021-04-06 | 2021-08-17 | 云南师范大学 | Forest breast diameter value extraction method based on foundation laser radar technology |
CN113269825B (en) * | 2021-04-06 | 2022-07-12 | 云南师范大学 | Forest breast diameter value extraction method based on foundation laser radar technology |
CN114777703A (en) * | 2022-04-25 | 2022-07-22 | 贵州省第三测绘院(贵州省国土资源遥感监测中心) | Forestry sample plot accurate positioning method and device based on distance matching |
CN114777703B (en) * | 2022-04-25 | 2024-04-16 | 贵州省第三测绘院(贵州省国土资源遥感监测中心) | Forestry sample plot accurate positioning method and device based on distance matching |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816779A (en) | A method of artificial forest forest model, which is rebuild, using smart phone obtains single wooden parameter | |
Iglhaut et al. | Structure from motion photogrammetry in forestry: A review | |
CN109410256B (en) | Automatic high-precision point cloud and image registration method based on mutual information | |
CN109708578B (en) | Plant phenotype parameter measuring device, method and system | |
Lati et al. | Estimating plant growth parameters using an energy minimization-based stereovision model | |
Rautiainen et al. | Crown envelope shape measurements and models | |
CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
CN103218812B (en) | Method for rapidly acquiring tree morphological model parameters based on photogrammetry | |
CN106651900A (en) | Three-dimensional modeling method of elevated in-situ strawberry based on contour segmentation | |
CN108195736B (en) | Method for extracting vegetation canopy clearance rate through three-dimensional laser point cloud | |
CN109448043A (en) | Standing tree height extracting method under plane restriction | |
CN112200854B (en) | Leaf vegetable three-dimensional phenotype measuring method based on video image | |
CN111429490A (en) | Agricultural and forestry crop three-dimensional point cloud registration method based on calibration ball | |
Li et al. | Retrieving 2-D leaf angle distributions for deciduous trees from terrestrial laser scanner data | |
CN115375842A (en) | Plant three-dimensional reconstruction method, terminal and storage medium | |
CN111179335A (en) | Standing tree measuring method based on binocular vision | |
WO2023174204A1 (en) | Sfm and deep learning-based hyperspectral three-dimensional reconstruction system and method, and use | |
CN110610438B (en) | Crop canopy petiole included angle calculation method and system | |
CN110207670A (en) | A method of artificial forest forest hat width parameter is obtained using two dimensional image | |
CN109191519A (en) | A kind of trees stem volume appraising model construction method, volume estimation method and system | |
Peng et al. | Binocular-vision-based structure from motion for 3-D reconstruction of plants | |
CN102865814A (en) | Plant population three-dimensional reconstruction error measurement method | |
CN112906719A (en) | Standing tree factor measuring method based on consumption-level depth camera | |
CN116883480A (en) | Corn plant height detection method based on binocular image and ground-based radar fusion point cloud | |
CN110580468B (en) | Single wood structure parameter extraction method based on image matching point cloud |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |
|
RJ01 | Rejection of invention patent application after publication |