CN107577989A - It is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane - Google Patents
It is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane Download PDFInfo
- Publication number
- CN107577989A CN107577989A CN201710665036.5A CN201710665036A CN107577989A CN 107577989 A CN107577989 A CN 107577989A CN 201710665036 A CN201710665036 A CN 201710665036A CN 107577989 A CN107577989 A CN 107577989A
- Authority
- CN
- China
- Prior art keywords
- pear tree
- tree
- century
- top view
- pear
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, comprise the following steps:a:It is determined that height of taking photo by plane, vertical shooting to be identified the top view of the pear tree of the century-old age of tree;b:Standard a century pear tree is determined, vertically shoots its top view;c:The pear tree in all top views is partitioned into using convolutional neural networks;d:Two concentric circles of picture are overlooked to resulting all pear trees;e:According to shadowing method principle, two circles are subtracted each other to obtain class the first side shoot image top view;f:Compare all the first side shoot of class image top views and obtain result.The present invention is not suitable for the problem of century-old age of tree of a wide range of pear tree of identification for prior art, there is provided a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, the area for possessing a large amount of pear trees, the century-old pear tree therein that can quickly identify.
Description
Technical field
It is specifically a kind of quickly to be identified based on the pear tree a century age of tree taken photo by plane the present invention relates to computer picture recognition field
Method.
Background technology
The estimation of the pear tree age of tree is to differentiate the important evidence of pear tree grade, and existing tree age evaluation method mainly wraps
Include:Annual ring identification method, 14C estimation algorithms, interview estimation method, document back tracking method, Analog Reasoning method etc..Annual ring identification method was sampling
Cheng Zhonghui causes to damage to tree body, and 14C estimation algorithms are not sensitive accurate enough for the age of tree of many decades, and interview estimation method and document chase after
Track method excessively relies on documents and materials and social investigation information, and this several method is for identifying the century-old age of tree of a wide range of pear tree not
It is too suitable.For possessing the area of hundreds thousand of pear trees, it is necessary to a kind of quickly pear tree a century age of tree recognition methods.
The content of the invention it is an object of the invention to provide a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, with
Solve the problems, such as that prior art is difficult to quickly identify the century-old pear tree age of tree in a wide range of pear tree.
In order to achieve the above object, the technical solution adopted in the present invention is:
It is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Comprise the following steps:
(1), determine take photo by plane height, vertically shoot pear tree to be identified, obtain the top view of pear tree to be identified;
(2), determine standard a century pear tree, identical take photo by plane high perpendicular shooting standard a century pear tree, obtain standard a century pears
The top view of tree;
(3), using convolutional neural networks, from step(1)All single pear trees to be identified are partitioned into obtained top view
Top view, from step(2)The top view of standard a century pear tree is partitioned into obtained top view;
(4), to step(3)The top view of obtained all single pear trees draws two concentric circles respectively, wherein first concentric circles
Comprising pear tree trunk, second concentric circles includes pear tree trunk and the first side shoot;
(5), according to shadowing method principle, in step(4)In each single pear tree top view in second concentric circles subtract the
One concentric circles, reuses binarization method, obtains class the first side shoot top view of each single pear tree, wherein to be identified
What single pear tree top view obtained is class the first side shoot top view of pear tree to be identified, is obtained from standard a century pear tree top view
It is class the first side shoot top view of standard a century pear tree;
(6), by class the first side shoot top view of single pear tree to be identified, class the first side shoot top view with standard a century pear tree
It is compared, the pear tree to be identified that the first side shoot area is more than standard a century pear tree the first side shoot area is century-old pear tree.
Described is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:The step(1)
In, according to the video memory amount of server video card, unmanned plane height is determined, vertically shoots the top view of pear tree to be identified.
Described is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Step(1)Middle vertical view
The pear tree of 20 ± 2 is included in figure.
Described is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Step(2)Determine
Standard a century pear tree, the diameter of its first side shoot is representative, i.e. the diameter of the century-old side shoot of pear tree first of the overwhelming majority all should
More than or equal to the diameter of standard a century the first side shoot of pear tree.
The present invention is not suitable for the problem of century-old age of tree of a wide range of pear tree of identification for prior art, there is provided one kind is based on
The pear tree a century age of tree method for quickly identifying taken photo by plane, its method and step clear and definite, reasonable in design and realization is convenient, for right
In the area for possessing a large amount of pear trees, the century-old pear tree therein that can quickly identify.
Compared to prior art, the present invention has advantages below:
First, based on the thought of Analog Reasoning method, the wherein super century-old age of tree can be quickly identified to a large amount of pear trees, solve existing side
Method can not quickly identify the problem of century-old age of tree of a wide range of pear tree.
Second, the data main source used can both be shot using unmanned plane, can also directly be bought from picture of taking photo by plane
Satellite photo, reduce the difficulty for obtaining data.
Brief description of the drawings
Fig. 1 is the inventive method FB(flow block).
Embodiment
As shown in figure 1, it is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, comprise the following steps:
(1), determine take photo by plane height, vertically shoot pear tree to be identified, obtain the top view of pear tree to be identified;
In this step, typically carry out shooting image using unmanned plane, unmanned plane highly, according to the video memory amount of server video card,
The height of the pear tree of 20 or so is included in a general top view, vertical shooting to be identified the pear tree of the century-old age of tree
Top view.
In this step, according to the video memory amount of server video card, unmanned plane height is determined, vertically shoots pears to be identified
The top view of tree.
The pear tree of 20 ± 2 is included in this step, in top view.
(2), determine standard a century pear tree, identical take photo by plane high perpendicular shooting standard a century pear tree, obtain standard hundred
The top view of year pear tree;
In this step, it is desirable to determine standard a century pear tree, mainly require that the diameter of its first side shoot is representative, i.e., it is big absolutely
Partly the diameter of the century-old side shoot of pear tree first all should be greater than or the diameter equal to standard a century the first side shoot of pear tree.
(3), using convolutional neural networks, from step(1)All single pears to be identified are partitioned into obtained top view
The top view of tree, from step(2)The top view of standard a century pear tree is partitioned into obtained top view;
In this step, training set of images is made, using Caffe frameworks, training set covers the pear tree top view for having obvious characteristic, instruction
Practice Faster RCNN models, the figure of segmentation is changed to circle, is partitioned into the top view of all pear trees.
(4), to step(3)The top view of obtained all single pear trees draws two concentric circles respectively, wherein first same
Heart circle includes pear tree trunk, and second concentric circles includes pear tree trunk and the first side shoot;
(5), according to shadowing method principle, in step(4)In each single pear tree top view in second concentric circles subtract the
One concentric circles, reuses binarization method, obtains class the first side shoot top view of each single pear tree, wherein to be identified
What single pear tree top view obtained is class the first side shoot top view of pear tree to be identified, is obtained from standard a century pear tree top view
It is class the first side shoot top view of standard a century pear tree;
(6), by class the first side shoot top view of single pear tree to be identified, class the first side shoot top view with standard a century pear tree
It is compared, the pear tree to be identified that the first side shoot area is more than standard a century pear tree the first side shoot area is century-old pear tree.
Claims (4)
- It is 1. a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Comprise the following steps:(1), determine take photo by plane height, vertically shoot pear tree to be identified, obtain the top view of pear tree to be identified;(2), determine standard a century pear tree, identical take photo by plane high perpendicular shooting standard a century pear tree, obtain standard a century pears The top view of tree;(3), using convolutional neural networks, from step(1)All single pear trees to be identified are partitioned into obtained top view Top view, from step(2)The top view of standard a century pear tree is partitioned into obtained top view;(4), to step(3)The top view of obtained all single pear trees draws two concentric circles respectively, wherein first concentric circles Comprising pear tree trunk, second concentric circles includes pear tree trunk and the first side shoot;(5), according to shadowing method principle, in step(4)In each single pear tree top view in second concentric circles subtract the One concentric circles, reuses binarization method, obtains class the first side shoot top view of each single pear tree, wherein to be identified What single pear tree top view obtained is class the first side shoot top view of pear tree to be identified, is obtained from standard a century pear tree top view It is class the first side shoot top view of standard a century pear tree;(6), by class the first side shoot top view of single pear tree to be identified, class the first side shoot top view with standard a century pear tree It is compared, the pear tree to be identified that the first side shoot area is more than standard a century pear tree the first side shoot area is century-old pear tree.
- It is 2. according to claim 1 a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Institute State step(1)In, according to the video memory amount of server video card, unmanned plane height is determined, vertically shoots pear tree to be identified Top view.
- It is 3. according to claim 1 a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Step Suddenly(1)The pear tree of 20 ± 2 is included in middle top view.
- It is 4. according to claim 1 a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane, it is characterised in that:Step Suddenly(2)Standard a century pear tree of determination, the diameter of its first side shoot is representative, i.e. the century-old side shoot of pear tree first of the overwhelming majority Diameter all should be greater than or the diameter equal to standard a century the first side shoot of pear tree.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710665036.5A CN107577989B (en) | 2017-08-07 | 2017-08-07 | Aerial photography-based pear tree hundred-year age rapid identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710665036.5A CN107577989B (en) | 2017-08-07 | 2017-08-07 | Aerial photography-based pear tree hundred-year age rapid identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107577989A true CN107577989A (en) | 2018-01-12 |
CN107577989B CN107577989B (en) | 2020-11-24 |
Family
ID=61034522
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710665036.5A Active CN107577989B (en) | 2017-08-07 | 2017-08-07 | Aerial photography-based pear tree hundred-year age rapid identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107577989B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348403A (en) * | 2019-07-15 | 2019-10-18 | 华瑞新智科技(北京)有限公司 | A kind of trees quantity real-time measurement statistical method, system and unmanned plane |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100158314A1 (en) * | 2008-12-24 | 2010-06-24 | Weyerhaeuser Company | Method and apparatus for monitoring tree growth |
CN106018679A (en) * | 2016-05-10 | 2016-10-12 | 中国科学院地球化学研究所 | Method for calculating age of mangrove forest |
-
2017
- 2017-08-07 CN CN201710665036.5A patent/CN107577989B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100158314A1 (en) * | 2008-12-24 | 2010-06-24 | Weyerhaeuser Company | Method and apparatus for monitoring tree growth |
CN106018679A (en) * | 2016-05-10 | 2016-10-12 | 中国科学院地球化学研究所 | Method for calculating age of mangrove forest |
Non-Patent Citations (2)
Title |
---|
刘晓双 等: "高空间分辨率遥感的单木树冠自动提取方法与应用", 《浙江林学院学报》 * |
廖彩霞: "树冠表面积及体积的预估", 《科技信息》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348403A (en) * | 2019-07-15 | 2019-10-18 | 华瑞新智科技(北京)有限公司 | A kind of trees quantity real-time measurement statistical method, system and unmanned plane |
Also Published As
Publication number | Publication date |
---|---|
CN107577989B (en) | 2020-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Few-shot adaptive faster r-cnn | |
US11455831B2 (en) | Method and apparatus for face classification | |
CN102542058B (en) | Hierarchical landmark identification method integrating global visual characteristics and local visual characteristics | |
CN106407958B (en) | Face feature detection method based on double-layer cascade | |
CN106909941A (en) | Multilist character recognition system and method based on machine vision | |
CN106610969A (en) | Multimodal information-based video content auditing system and method | |
CN103793702A (en) | Pedestrian re-identifying method based on coordination scale learning | |
CN106920256A (en) | A kind of effective missing child searching system | |
CN112364803B (en) | Training method, terminal, equipment and storage medium for living body identification auxiliary network | |
Liu et al. | Automated status inspection of fastening bolts on freight trains using a machine vision approach | |
Xu et al. | Pig face recognition based on trapezoid normalized pixel difference feature and trimmed mean attention mechanism | |
Libo et al. | Real-time detection of cole diseases and insect pests in wireless sensor networks | |
CN102750526A (en) | Identity verification and recognition method based on face image | |
Wang et al. | Lightweight SM-YOLOv5 tomato fruit detection algorithm for plant factory | |
WO2021127916A1 (en) | Facial emotion recognition method, smart device and computer-readabel storage medium | |
Tatsuma et al. | Food image recognition using covariance of convolutional layer feature maps | |
CN106203448B (en) | A kind of scene classification method based on Nonlinear Scale Space Theory | |
Ji et al. | Fast segmentation of colour apple image under all-weather natural conditions for vision recognition of picking robots | |
Feng et al. | A novel saliency detection method for wild animal monitoring images with WMSN | |
CN107577989A (en) | It is a kind of based on the pear tree a century age of tree method for quickly identifying taken photo by plane | |
Zhang et al. | A deep neural network-based vehicle re-identification method for bridge load monitoring | |
CN111079617A (en) | Poultry identification method and device, readable storage medium and electronic equipment | |
CN111539362A (en) | Unmanned aerial vehicle image target detection device and method | |
CN106846527B (en) | A kind of attendance checking system based on recognition of face | |
Paczolay et al. | Wlab of university of szeged at lifeclef 2014 plant identification task |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |