CN111179335A - Standing tree measuring method based on binocular vision - Google Patents
Standing tree measuring method based on binocular vision Download PDFInfo
- Publication number
- CN111179335A CN111179335A CN201911385049.2A CN201911385049A CN111179335A CN 111179335 A CN111179335 A CN 111179335A CN 201911385049 A CN201911385049 A CN 201911385049A CN 111179335 A CN111179335 A CN 111179335A
- Authority
- CN
- China
- Prior art keywords
- camera
- coordinate system
- binocular
- point
- image
- 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 24
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 210000000481 breast Anatomy 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 9
- 238000000691 measurement method Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000003708 edge detection Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000011835 investigation Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012549 training Methods 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
- G06T7/60—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
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
一种基于双目视觉的立木测定方法。本发明是为了解决现有技术的测定员需要接触测量，且测定员需要大量经验、人力资源消耗的问题。本发明的具体过程为：对双目相机进行标定，获取双目相机内外参数；双目相机校正，立体匹配计算获取视差图，双目距离测量；树种的识别；测算出真正的胸径数据；将树种类别与获取的树木的胸径数据录入保存。本发明属于林木统计领域。
A method for measuring standing trees based on binocular vision. The present invention is to solve the problems that the measuring personnel in the prior art need contact measurement, and the measuring personnel need a lot of experience and human resource consumption. The specific process of the invention is as follows: calibrating the binocular camera to obtain the internal and external parameters of the binocular camera; calibrating the binocular camera, obtaining the disparity map through stereo matching calculation, and measuring the binocular distance; identifying the tree species; The tree species category and the DBH data of the obtained trees are entered and saved. The invention belongs to the field of forest statistics.
Description
Technical Field
The invention relates to a standing tree measuring method based on binocular vision.
Background
Forest resource investigation is an important means for checking the quantity, quality and distribution of forest resources. The breast height measurement of standing trees and the tree species are important items in forest resource investigation. The breast diameter measurement is also an important basis for evaluating the site conditions and the growth condition of the forest trees. In conventional resource investigation, a great deal of experience is required from the surveyor to identify the tree species. The traditional breast-height diameter measurement of the standing tree comprises caliper measurement, wheel ruler measurement, diameter tape measurement and the like, the contact measurement methods are low in efficiency and high in labor intensity, and an investigator may not reach the vicinity of the standing tree to perform contact measurement when measuring the breast-height diameter of the tree in a forest land in the field. In order to meet the requirements of intelligent development of forestry in China, researchers develop breast-height measuring methods such as a digital forestry diameter measuring instrument, a digital forestry side height distance measuring instrument, an electronic tree measuring gun, an electronic angle gauge, an electronic theodolite, a binocular fixed-focus camera and the like in sequence. Non-contact measurement becomes a practical requirement, and an intelligent determination method is provided for meeting the requirement: the images are acquired by using a USB binocular camera, and the type identification and the breast diameter measurement of the trees are acquired by performing subsequent processing on the images by using a notebook computer (tx2 development board).
Disclosure of Invention
The invention aims to solve the problems that in the prior art, when forest resources are measured in the field, a measurer needs to be in contact with the forest resources to measure, and the measurer needs a large amount of experience and manpower resource consumption, and provides a standing tree measuring method based on binocular vision.
The invention relates to a binocular vision-based stumpage determination method, which comprises the following steps:
firstly, calibrating a binocular camera to obtain internal and external parameters of the binocular camera;
correcting the binocular camera, acquiring a disparity map, and measuring binocular distance;
step three, identifying tree species;
step four, measuring and calculating real breast diameter data;
the invention has the beneficial effects that: the invention solves the problems that the prior art needs contact measurement and a determinator needs a large amount of experience when measuring the field forest resources, realizes automatic statistical calculation, has the advantage of non-contact measurement, measures in forest lands with complex environment, solves the problem of huge physical consumption of the determinator, and has the advantages of low cost, small volume and convenient carrying, and the measurement result can be processed by a computer in real time.
Drawings
FIG. 1 is an overall flow chart for measuring the breast height of a standing tree;
FIG. 2 is a diagram of the effect of a target detection test on a single picture;
FIG. 3 is a schematic diagram of binocular range finding;
FIG. 4 is a schematic view of a cross-cut of a stumpage;
fig. 5 is a flow chart of target detection.
Detailed Description
The first embodiment is as follows: the diameter at breast height of the tree is the diameter of a trunk at 1.3 meters above the ground, and is an important factor in various applications such as acquisition calculation, decision analysis and the like; with reference to fig. 1, the standing tree measurement method based on binocular vision according to the present embodiment includes the following steps:
firstly, calibrating a binocular camera to obtain internal and external parameters of the binocular camera;
correcting the binocular camera, acquiring a disparity map, and measuring binocular distance;
step three, identifying tree species;
step four, measuring and calculating real breast diameter data;
and step five, recording and storing the tree species and the acquired breast-height diameter data of the trees.
The second embodiment is as follows: the difference between the first embodiment and the second embodiment is that, in the first step, the binocular camera is calibrated to obtain the internal and external parameters of the binocular camera, and the specific process is as follows:
the left camera and the right camera are fixed to be a rigid body, the distance between the left camera and the right camera is 10cm, the distortion degree of each lens of the binocular camera cannot be completely the same, internal and external parameters of the cameras can be obtained through camera calibration, and the internal parameters K of the cameras comprise the focal length f of the cameras, the center distance T between the two cameras, the position of a principal point p (a point where a principal axis intersects with an image plane) and the size proportion of pixels to a real environment; the camera extrinsic parameters comprise a three-dimensional calibration rotation matrix R and a three-dimensional calibration translation vector t; 1. opening a camera 2, synchronously grabbing 3 two camera frame images, placing a chessboard calibration plate in front of the two cameras, grabbing more than 20 views, and changing the angle and distance between the plane of the calibration plate and an imaging plane every time a complete chessboard angular point is successfully detected;
xc1＝R1xw+t1
xc2＝R2xw+t2
wherein x isc1Presentation Camera C1Non-homogeneous coordinates in a coordinate system, xc2Presentation Camera C2Non-homogeneous coordinates in a coordinate system, xwRepresenting the non-homogeneous coordinate of any point Q in space in a world coordinate system, and a rotation matrix R1And a translation vector t1Is a camera C1External parameter of relative position to world coordinate system, rotation matrix R2And a translation vector t2Is a camera C2External parameters of relative position to the world coordinate system; r represents a stereo calibration rotation matrix, and t represents a stereo calibration translation vector.
Other steps and parameters are the same as those in the first embodiment.
The third concrete implementation mode: the difference between the first embodiment and the second embodiment is that the method comprises the following steps of correcting the binocular camera, acquiring a disparity map, and measuring the binocular distance:
according to monocular internal reference data (center distance T, principal point p and distortion coefficient) and binocular external reference data (rotation matrix and translation vector) obtained after camera calibration, respectively carrying out distortion elimination and row calibration on left and right views, enabling the imaging origin coordinates of the left and right views to be consistent, enabling the optical axes of the two cameras to be parallel, enabling left and right imaging planes to be coplanar, and adjusting the left and right views into an ideal mode of completely parallel alignment;
1. correcting the binocular camera:
(1) acquiring left and right views; (2) eliminating distortion for left and right views; (3) binocular parallel correction; (4) image cutting;
2. and (3) stereo matching calculation disparity map: (stereo matching is mainly to find out the corresponding relation between each pair of images, obtain a disparity map according to the triangulation principle, and obtain the depth information and three-dimensional information of an original image according to a projection model after obtaining disparity information):
(1) and (3) calculating matching cost: carrying out gray level similarity measurement under different parallaxes by adopting a gray level difference square method;
(2) matching cost superposition: the reliability of matching cost is enhanced through window superposition by a region algorithm, and the method is mean square error;
(3) parallax acquisition: selecting a point with the optimal superposition matching cost in a certain range, namely, taking a point with the minimum mean square error as a corresponding matching point;
(4) parallax refinement
3. Binocular ranging:
wherein x islThe abscissa, x, representing the target point P in the left camera planerDenotes the abscissa of the target point P on the right camera plane, T denotes the center-to-center distance (distance between the right and left camera optical centers), Z denotes the vertical distance (as shown in fig. 3, i.e., the distance of OD in fig. 4) of the target point P from the center-to-center distance, and f denotes the focal length of the camera.
Other steps and parameters are the same as those in the first or second embodiment.
The fourth concrete implementation mode: the difference between this embodiment and one of the first to third embodiments is that the identification of tree species in the third step includes the following specific processes:
after the image is obtained, trunk information in the image is extracted by using a target detection technology based on a depth convolution neural network (a target detection process is shown in fig. 5, a convolution network in the image is used for extracting features, an RPN network generates a candidate frame of a target region, a full connection layer is used for classifying a feature map and regressing the target region after ROI pooling is carried out), the category of the tree is obtained, a data set and a label need to be prepared in advance for a model for target detection, a plurality of images of various trees need to be collected as much as possible for labeling in the previous preparation, then a target detection model with high accuracy and robustness is obtained by training, the height of a camera is adjusted to be 1.3 meters, the optical axis of the camera (the ray of which the central point of the camera is vertical to the image plane) is parallel to the ground as much as possible, 3-5 frames of images are extracted from a video of one tree for subsequent processing, and the trunk information in each picture can be predicted and position fitted by the model for, the reliability and location parameters are averaged and output (the effect of the target detection test on a single picture is shown in fig. 2).
Other steps and parameters are the same as those in one of the first to third embodiments.
The fifth concrete implementation mode: the difference between this embodiment and one of the first to fourth embodiments is that the step four calculates the true diameter at breast height data, and the specific process is as follows:
because the left view and the right view of the binocular camera are different, according to the disparity map obtained in the second step, three-dimensional information is obtained through the trigonometry principle, the binocular camera observes the same object from two points to obtain images under different visual angles, the offset between pixels is calculated through the triangulation principle according to the pixel matching relation between the images to obtain the three-dimensional information of the object, the depth of field information of the object is obtained, the distance between the trunk and the camera can be calculated, graying is carried out in the trunk frame extracted by the target detection algorithm, edge detection is carried out through a canny operator, and two-point coordinates (x coordinate) for measuring the diameter of the tree in the image coordinate system are obtained (x is x)A,yA) And (x)B,yB)：
Wherein, XARepresenting (x) in the image coordinate systemA,yA) Abscissa, X, of the world coordinate system corresponding to the pointBRepresenting (x) in the image coordinate systemB,yB) The abscissa of the world coordinate system corresponding to the point, Z represents the vertical distance from the target point P to the center distance, f represents the focal length of the camera, u represents the focal length of the camera0Representing the offset, v, of the image plane coordinate system to the x-axis of the image coordinate system0Indicating the offset, Y, of the image plane coordinate system to the Y-axis of the image coordinate systemARepresenting (x) in the image coordinate systemA,yA) Ordinate, Y, of the world coordinate system corresponding to the pointBRepresenting (x) in the image coordinate systemB,yB) The vertical coordinate of the corresponding world coordinate system;
assuming that the trunk is a cylinder, when observing a cylindrical object, the diameter of the object reflected by the light is a bright point straight line (i.e. two lines OA and OB) where the observation light is tangent to the trunk on the chest height plane, as shown in fig. 4, the true breast diameter of the standing tree is further calculated:
wherein α represents the angle between OA and OB, SABRepresenting the distance between A, B points in the world coordinate system, r is the radius of the tree under ideal conditions;
calculating the real breast diameter data D of the standing tree according to the following formula:
sin2α+cos2α＝1
D＝2r。
other steps and parameters are the same as in one of the first to fourth embodiments.
Claims (5)
1. A standing tree measuring method based on binocular vision is characterized by comprising the following steps:
firstly, calibrating a binocular camera to obtain internal and external parameters of the binocular camera;
correcting the binocular camera, acquiring a disparity map, and measuring binocular distance;
step three, identifying tree species;
and step four, measuring and calculating the real breast diameter data.
2. The binocular vision based stumpage measurement method according to claim 1, wherein in the first step, a binocular camera is calibrated to obtain internal and external parameters of the binocular camera; the specific process is as follows:
fixing a left camera and a right camera as a rigid body, wherein the distance between the left camera and the right camera is 10cm, and obtaining internal and external parameters of the cameras through camera calibration, wherein the internal parameters K of the cameras comprise a focal length f, a center distance T between the two cameras, a position of a principal point p and a size ratio of a pixel to a real environment; the camera extrinsic parameters comprise a rotation matrix R and a translation vector t; capturing more than 20 views, and changing the angle and the distance between the plane of the calibration plate and the imaging plane every time when the complete chessboard angular point is successfully detected;
xc1＝R1xw+t1
xσ2＝R2xw+t2
wherein x isσ1Presentation Camera C1Non-homogeneous coordinates in a coordinate system, xc2Presentation Camera C2Non-homogeneous coordinates in a coordinate system, xwRepresenting the non-homogeneous coordinate of any point Q in space in a world coordinate system, and a rotation matrix R1And a translation vector t1Is a camera C1External parameter of relative position to world coordinate system, rotation matrix R2And a translation vector t2Is a camera C2External parameters of relative position to the world coordinate system; r represents a stereo calibration rotation matrix, and t represents a stereo calibration translation vector.
3. The binocular vision based stumpage determination method according to claim 2, wherein the steps of binocular camera correction, obtaining a disparity map, binocular distance measurement; the specific process is as follows:
correcting the binocular camera:
(1) acquiring left and right views; (2) eliminating distortion for left and right views; (3) binocular parallel correction; (4) image cutting;
and (3) stereo matching calculation disparity map:
(1) and (3) calculating matching cost: carrying out gray level similarity measurement under different parallaxes by adopting a gray level difference square method;
(2) matching cost superposition: the method is mean square error;
(3) parallax acquisition: selecting a point with the optimal superposition matching cost, namely, taking a point with the minimum mean square error as a corresponding matching point;
(4) parallax refinement
And (5) binocular distance measurement.
4. The binocular vision based stumpage measurement method according to claim 3, wherein the steps of three tree species identification; the specific process is as follows:
after the image is obtained, trunk information in the image is extracted by using a target detection technology based on a depth convolution neural network, the category of the tree is obtained, the height of a camera is adjusted to be 1.3 m, the optical axis of the camera is parallel to the ground, 3-5 frames of images are extracted from a video of one tree for subsequent processing, a model for target detection can predict the trunk in each picture and fit the position, and parameters of the reliability and the position are averaged and output.
5. The binocular vision-based stumpage measurement method according to claim 4, wherein the true breast diameter data is measured in the fourth step; the specific process is as follows:
three-dimensional information is obtained by a trigonometry principle, a binocular camera observes the same object from two points to obtain images under different visual angles, the three-dimensional information of the object is obtained by calculating the offset between pixels according to the pixel matching relation between the images and the triangulation principle to obtain the depth of field information of the object, graying is carried out in a trunk frame extracted by a target detection algorithm, edge detection is carried out by using a canny operator, and two-point coordinates (x coordinate) for measuring the breast diameter of the tree in an image coordinate system are obtainedA,yA) And (x)B,yB)：
Wherein, XARepresenting (x) in the image coordinate systemA,yA) Abscissa, X, of the world coordinate system corresponding to the pointBRepresenting (x) in the image coordinate systemB,yB) The abscissa of the world coordinate system corresponding to the point, Z represents the vertical distance from the target point P to the center distance, f represents the focal length of the camera, u represents the focal length of the camera0Representing the offset, v, of the image plane coordinate system to the x-axis of the image coordinate system0Indicating the offset, Y, of the image plane coordinate system to the Y-axis of the image coordinate systemARepresenting (x) in the image coordinate systemA，yA) Ordinate, Y, of the world coordinate system corresponding to the pointBRepresenting (x) in the image coordinate systemB，yB) The vertical coordinate of the corresponding world coordinate system;
assuming that the trunk is a cylinder, further calculating to obtain the true breast diameter of the standing tree:
wherein α represents the angle between OA and OB, SABRepresenting the distance between A, B points in the world coordinate system, r is the radius of the tree under ideal conditions;
calculating the real breast diameter data D of the standing tree according to the following formula:
stn2α+cos2α＝1
D＝2r。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911385049.2A CN111179335A (en) | 2019-12-28 | 2019-12-28 | Standing tree measuring method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911385049.2A CN111179335A (en) | 2019-12-28 | 2019-12-28 | Standing tree measuring method based on binocular vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179335A true CN111179335A (en) | 2020-05-19 |
Family
ID=70654172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911385049.2A Pending CN111179335A (en) | 2019-12-28 | 2019-12-28 | Standing tree measuring method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179335A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815703A (en) * | 2020-07-16 | 2020-10-23 | 中国农业机械化科学研究院 | Handheld grain heap measuring device and grain heap measuring method based on binocular camera |
| CN113587895A (en) * | 2021-07-30 | 2021-11-02 | 杭州三坛医疗科技有限公司 | Binocular distance measuring method and device |
| CN113888641A (en) * | 2021-09-16 | 2022-01-04 | 广西大学 | A method for measuring diameter at breast height of standing trees based on machine vision and deep learning |
| CN114067002A (en) * | 2022-01-17 | 2022-02-18 | 江苏中云筑智慧运维研究院有限公司 | Binocular camera external parameter determination method and system |
| CN115294562A (en) * | 2022-07-19 | 2022-11-04 | 广西大学 | Intelligent sensing method for operation environment of plant protection robot |
| CN115439526A (en) * | 2022-08-23 | 2022-12-06 | 中国农业大学 | Tree diameter measurement method based on halcon binocular stereo vision |
| CN115797459A (en) * | 2022-08-29 | 2023-03-14 | 南京航空航天大学 | Binocular vision system distance measurement method with arbitrary focal length combination |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052914A (en) * | 2017-12-21 | 2018-05-18 | 中国科学院遥感与数字地球研究所 | A kind of forest forest resource investigation method identified based on SLAM and image |
| CN108827245A (en) * | 2018-05-17 | 2018-11-16 | 北京林业大学 | A kind of twin-lens portable forestry investigation apparatus |
| CN109522924A (en) * | 2018-09-28 | 2019-03-26 | 浙江农林大学 | A kind of broad-leaf forest wood recognition method based on single photo |
| CN109544613A (en) * | 2018-11-23 | 2019-03-29 | 南昌航空大学 | A kind of binocular solid matching process and system based on the study of dense network depth |
| CN109829372A (en) * | 2018-12-26 | 2019-05-31 | 北京木业邦科技有限公司 | Trees intermediate cutting method, apparatus, electronic equipment and computer readable storage medium |
| CN110070571A (en) * | 2019-04-28 | 2019-07-30 | 安徽农业大学 | A detection method of bamboo morphological parameters based on depth camera |
| CN110097060A (en) * | 2019-03-28 | 2019-08-06 | 浙江工业大学 | A kind of opener recognition methods towards trunk image |
-
2019
- 2019-12-28 CN CN201911385049.2A patent/CN111179335A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052914A (en) * | 2017-12-21 | 2018-05-18 | 中国科学院遥感与数字地球研究所 | A kind of forest forest resource investigation method identified based on SLAM and image |
| CN108827245A (en) * | 2018-05-17 | 2018-11-16 | 北京林业大学 | A kind of twin-lens portable forestry investigation apparatus |
| CN109522924A (en) * | 2018-09-28 | 2019-03-26 | 浙江农林大学 | A kind of broad-leaf forest wood recognition method based on single photo |
| CN109544613A (en) * | 2018-11-23 | 2019-03-29 | 南昌航空大学 | A kind of binocular solid matching process and system based on the study of dense network depth |
| CN109829372A (en) * | 2018-12-26 | 2019-05-31 | 北京木业邦科技有限公司 | Trees intermediate cutting method, apparatus, electronic equipment and computer readable storage medium |
| CN110097060A (en) * | 2019-03-28 | 2019-08-06 | 浙江工业大学 | A kind of opener recognition methods towards trunk image |
| CN110070571A (en) * | 2019-04-28 | 2019-07-30 | 安徽农业大学 | A detection method of bamboo morphological parameters based on depth camera |
Non-Patent Citations (5)
| Title |
|---|
| 张海明等: "《光电物理类专业实验教程》", 31 August 2018 * |
| 李亚东等: "USB摄像头双目视觉胸径测量实证研究", 《中南林业科技大学学报》 * |
| 杨力铭: "《时空域脉搏信号检测方法研究》", 31 December 2017 * |
| 樊仲谋: "摄影测树原理与技术方法研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
| 赵亚凤: "基于双目视觉的原木材积检测方法研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815703A (en) * | 2020-07-16 | 2020-10-23 | 中国农业机械化科学研究院 | Handheld grain heap measuring device and grain heap measuring method based on binocular camera |
| CN111815703B (en) * | 2020-07-16 | 2024-05-03 | 中国农业机械化科学研究院 | Handheld grain pile measuring device and grain pile measuring method based on binocular camera |
| CN113587895A (en) * | 2021-07-30 | 2021-11-02 | 杭州三坛医疗科技有限公司 | Binocular distance measuring method and device |
| CN113587895B (en) * | 2021-07-30 | 2023-06-30 | 杭州三坛医疗科技有限公司 | Binocular distance measuring method and device |
| CN113888641A (en) * | 2021-09-16 | 2022-01-04 | 广西大学 | A method for measuring diameter at breast height of standing trees based on machine vision and deep learning |
| CN113888641B (en) * | 2021-09-16 | 2025-03-21 | 广西大学 | A method for measuring standing tree diameter at breast height based on machine vision and deep learning |
| CN114067002A (en) * | 2022-01-17 | 2022-02-18 | 江苏中云筑智慧运维研究院有限公司 | Binocular camera external parameter determination method and system |
| CN115294562A (en) * | 2022-07-19 | 2022-11-04 | 广西大学 | Intelligent sensing method for operation environment of plant protection robot |
| CN115439526A (en) * | 2022-08-23 | 2022-12-06 | 中国农业大学 | Tree diameter measurement method based on halcon binocular stereo vision |
| CN115439526B (en) * | 2022-08-23 | 2025-02-07 | 中国农业大学 | Tree breast diameter measurement method based on halcon binocular stereo vision |
| CN115797459A (en) * | 2022-08-29 | 2023-03-14 | 南京航空航天大学 | Binocular vision system distance measurement method with arbitrary focal length combination |
| CN115797459B (en) * | 2022-08-29 | 2024-02-13 | 南京航空航天大学 | Binocular vision system ranging method with arbitrary focal length combination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179335A (en) | Standing tree measuring method based on binocular vision | |
| CN109269430B (en) | Passive measurement method of diameter at breast height of multiple standing trees based on depth extraction model | |
| CN101839692B (en) | Method for measuring three-dimensional position and stance of object with single camera | |
| CN109285145B (en) | A smartphone-based method for measuring the height of multiple standing trees | |
| CN109708578B (en) | Device, method and system for measuring plant phenotype parameters | |
| CN113137920B (en) | A kind of underwater measurement equipment and underwater measurement method | |
| Wu et al. | Passive measurement method of tree diameter at breast height using a smartphone | |
| CN109410256A (en) | Based on mutual information cloud and image automatic, high precision method for registering | |
| CN112825190B (en) | Precision evaluation method, system, electronic equipment and storage medium | |
| CN108416791A (en) | A Binocular Vision-Based Pose Monitoring and Tracking Method for Parallel Mechanism Maneuvering Platform | |
| CN110223355B (en) | Feature mark point matching method based on dual epipolar constraint | |
| CN104224212A (en) | CT system, CT system scanning positioning method and CT system calibration method | |
| CN107869954B (en) | A binocular vision volume weight measurement system and its realization method | |
| CN109341668B (en) | A Multi-Camera Measurement Method Based on Refraction Projection Model and Beam Tracing Method | |
| CN105066877A (en) | Tree measuring method based on intelligent terminal lens | |
| CN109448043A (en) | Standing tree height extracting method under plane restriction | |
| CN105286871A (en) | Video processing-based body height measurement method | |
| CN115375842A (en) | Plant three-dimensional reconstruction method, terminal and storage medium | |
| CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
| CN110966956A (en) | Binocular vision-based three-dimensional detection device and method | |
| CN113008158B (en) | Multi-line laser tire pattern depth measuring method | |
| CN106871900A (en) | Image matching positioning method in ship magnetic field dynamic detection | |
| CN116883480A (en) | Corn plant height detection method based on binocular image and ground-based radar fusion point cloud | |
| CN111524193B (en) | Method and device for measuring two-dimensional size of an object | |
| CN115511878A (en) | Method, device, medium and equipment for monitoring surface displacement of slope |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200519 |
|
| WD01 | Invention patent application deemed withdrawn after publication |