CN111666858A - Forest remote sensing image registration method and system based on single tree recognition - Google Patents
Forest remote sensing image registration method and system based on single tree recognition Download PDFInfo
- Publication number
- CN111666858A CN111666858A CN202010478151.3A CN202010478151A CN111666858A CN 111666858 A CN111666858 A CN 111666858A CN 202010478151 A CN202010478151 A CN 202010478151A CN 111666858 A CN111666858 A CN 111666858A
- Authority
- CN
- China
- Prior art keywords
- image
- single tree
- registered
- local
- key point
- 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 41
- 239000013598 vector Substances 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000011430 maximum method Methods 0.000 claims abstract description 14
- 239000002023 wood Substances 0.000 claims description 15
- 238000005260 corrosion Methods 0.000 claims description 12
- 230000007797 corrosion Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000000638 solvent extraction Methods 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a forest remote sensing image registration method and system based on single tree recognition, and relates to the technical field of image processing. The method comprises the following steps: respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method; calculating a local descriptor of the ith single tree identified in the reference image, and calculating a local descriptor of the jth single tree identified in the image to be registered; and taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered. The invention realizes the registration of images with higher self-similarity, such as forest images, and the like, and can obtain a registration result with higher reliability.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a forest remote sensing image registration method and system based on single tree recognition.
Background
At present, along with the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle is in the real time monitoring of forestry field wide application in forest. Because the remote sensing data that unmanned aerial vehicle acquireed demand manpower is few, easy operation, with low costs, consequently be used for the forest land investigation of supplementary ground, can carry out real time monitoring to the forest, greatly improved the situation that traditional ground investigation is consuming time hard and a large amount of personnel's input to can realize surveying the research of estimating and can carry out the change detection in forest zone in succession to forest biomass.
However, the forest images acquired by the unmanned aerial vehicle need to be registered firstly, and the traditional images such as buildings, roads and other targets have bright characteristics, so that the implementation is simpler. For forest images, the vegetation areas occupy most of the image areas, the vegetation images belong to natural scene images and have self-similarity, therefore, errors are easy to occur during feature point registration, the traditional registration feature point registration method has no universality on forest region images, and the correctness of the registration point pairs obtained through calculation is low.
Disclosure of Invention
The invention aims to solve the technical problem of the prior art and provides a forest remote sensing image registration method and system based on single tree recognition.
The technical scheme for solving the technical problems is as follows:
a forest remote sensing image registration method based on single tree recognition comprises the following steps:
acquiring a reference image and an image to be registered of a target forest;
respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
calculating a local descriptor of the ith single tree identified in the reference image, and calculating a local descriptor of the jth single tree identified in the image to be registered;
taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered;
wherein I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
The invention has the beneficial effects that: according to the forest remote sensing image registration method provided by the invention, single trees in a forest are positioned and identified by a local maximum method, direction parameters are assigned to each point according to the gradient direction distribution characteristics of neighborhood pixels of single tree position points, operators have rotation invariance, descriptors are generated according to feature description information of the single tree position points, and the Euclidean distance of feature vectors of the single tree position points is used as similarity judgment measurement of key points in two images, so that registration of images with higher self-similarity, such as forest images, is realized, and a registration result with higher reliability can be obtained.
Another technical solution of the present invention for solving the above technical problems is as follows:
a forest remote sensing image registration system based on single wood recognition comprises:
the image acquisition unit is used for acquiring a reference image and an image to be registered of the target forest;
the single-tree identification unit is used for respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
the descriptor calculation unit is used for calculating a local descriptor of the ith single tree identified in the reference image and calculating a local descriptor of the jth single tree identified in the image to be registered;
the similarity judgment unit is used for taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered;
wherein I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a schematic flow chart provided by an embodiment of a forest remote sensing image registration method of the present invention;
FIG. 2 is a schematic diagram of a forest remote sensing image provided by an embodiment of the forest remote sensing image registration method of the present invention;
FIG. 3 is an exemplary local maximum graph provided by an embodiment of the forest remote sensing image registration method of the present invention;
fig. 4 is a schematic diagram of a key point 8 × 8 window provided in the embodiment of the forest remote sensing image registration method of the present invention;
FIG. 5 is a schematic view of a weighted window provided by an embodiment of the forest remote sensing image registration method of the present invention;
FIG. 6 is a structural framework diagram provided by an embodiment of the forest remote sensing image registration system of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth to illustrate, but are not to be construed to limit the scope of the invention.
As shown in fig. 1, a schematic flow chart is provided for an embodiment of a forest remote sensing image registration method of the present invention, and the forest remote sensing image registration method includes:
s1, acquiring a reference image and an image to be registered of the target forest;
it should be noted that the reference image and the image to be registered of the target forest may be collected by an unmanned aerial vehicle, or may be collected by other aircrafts, the image collected by the unmanned aerial vehicle may be a picture, or may be an image, and for the picture, one of the pictures may be directly selected, or for the image, a frame of image with the definition meeting the requirement may be selected from an image sequence.
S2, respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
it should be noted that those skilled in the art can implement the local maximum method according to the specific implementation method.
As shown in fig. 2, an exemplary forest remote sensing image schematic diagram is provided, and is realized by an image processing technology, local maximum processing can be realized by performing reconstruction operation based on opening and closing on an original image, crowns of densely arranged single trees can be seen in the diagram, and due to gaps existing among the crowns, image processing can be performed on a reference image and an image to be registered by a local maximum method, so that each single tree and the position of each single tree can be identified.
For another example, for a scene with a small image or a small number of images, a search area may be set in advance, and the entire image may be facilitated by sliding a window, so as to find a local maximum area and determine the area as a single tree.
For example, as shown in fig. 2, the pixel values of the single trees are different from the background, and assuming that the single-side size of the single tree is usually between 10-15 pixels, the size of the search area may be set to 15 × 15, the average value of all pixels in the search area is used as a basis for comparison, and then the entire image is traversed through a sliding window, so that the search area with the largest pixel value can be identified as the single tree.
S3, calculating the local descriptor of the ith single tree identified in the reference image, and calculating the local descriptor of the jth single tree identified in the image to be registered;
for example, the geometric center point of the single tree may be used as a key point, and a descriptor of the key point may be generated by a SIFT algorithm as a local descriptor of the single tree.
S4, taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered;
where I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
According to the forest remote sensing image registration method provided by the embodiment, single trees in a forest are positioned and identified through a local maximum method, direction parameters are assigned to each point according to the gradient direction distribution characteristics of neighborhood pixels of single tree position points, operators have rotation invariance, descriptors are generated according to feature description information of the single tree position points, and the Euclidean distance of feature vectors of the single tree position points is used as similarity judgment measurement of key points in two images, so that registration of images with high self-similarity, such as forest images, is realized, and registration results with high reliability can be obtained.
Optionally, in some possible embodiments, after the similarity determination is performed on the local descriptor of the jth single tree and the local descriptor of the ith single tree, the method further includes:
and eliminating the result of matching error in the judging process by a least square method and a RANSAC algorithm.
For similarity judgment, the single-tree position points in the image to be registered are matched with the single-tree position points in the reference image, but errors may exist in matching of various factors, so that two matched parameters can be fitted through a least square method, and a matching result which is not expected is eliminated through a RANSAC algorithm, so that a more accurate matching result can be obtained, and the registration accuracy is improved.
Optionally, in some possible embodiments, the identifying and locating the single wood in the reference image and the image to be registered respectively according to a local maximum method specifically includes:
converting the reference image into a gray image, performing reconstruction operation based on opening and closing to obtain a local maximum image, performing corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the reference image, and identifying and positioning the single wood in the reference image;
converting the image to be registered into a gray image, carrying out reconstruction operation based on opening and closing to obtain a local maximum image, carrying out corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the image to be registered, and identifying and positioning the single wood in the image to be registered.
As shown in fig. 3, an exemplary local maximum image is provided, and after the opening and closing based reconstruction operation is performed on the forest remote sensing image provided in fig. 2, the local maximum image shown in fig. 3 is obtained.
Optionally, in some possible embodiments, calculating the local descriptor of the ith single wood identified in the reference image specifically includes:
determining a position point of the ith single tree identified in the reference image, and taking the position point as a key point;
partitioning a preset size area around the key point, and respectively calculating a gradient histogram of each block area;
generating a feature vector of a key point according to the gradient histogram;
and generating a local descriptor of the key point according to the feature vector of the key point, wherein the local descriptor is used as a local descriptor of the ith single tree.
It should be understood that the location point of the singles may be the center point of the singles.
By partitioning the area around the single tree position point and respectively calculating the gradient histogram of each area, a unique vector can be generated, the vector is an abstraction of the image information of the area and has uniqueness, so that the unique vector can be used for uniquely representing the single tree, and the similarity judgment of the single tree between two images can be carried out according to the local descriptor of the single tree.
Optionally, in some possible embodiments, calculating a local descriptor of the jth singleton identified in the image to be registered specifically includes:
determining a position point of the jth single tree identified in the image to be registered, and taking the position point as a key point;
partitioning a preset size area around the key point, and respectively calculating a gradient histogram of each block area;
generating a feature vector of a key point according to the gradient histogram;
and generating a local descriptor of the key point according to the feature vector of the key point, wherein the local descriptor is used as a local descriptor of the jth single wood.
It should be understood that the location point of the singles may be the center point of the singles.
By partitioning the area around the single tree position point and respectively calculating the gradient histogram of each area, a unique vector can be generated, the vector is an abstraction of the image information of the area and has uniqueness, so that the unique vector can be used for uniquely representing the single tree, and the similarity judgment of the single tree between two images can be carried out according to the local descriptor of the single tree.
It should be understood that the method for generating the local descriptor of the single tree in the reference image and the image to be registered is the same, and therefore, the method for generating the local descriptor is described below by taking the reference image as an example.
Firstly, a direction is calculated for key points, the direction is the basis of subsequent calculation, and direction parameters are assigned to each key point by utilizing the gradient direction distribution characteristics of the neighborhood pixels of the key points, so that an operator has rotation invariance.
Specifically, the sampling may be performed within a neighborhood window centered on the keypoint, and the histogram may be used to count the gradient direction of the neighborhood pixels. The gradient histogram is in the range of 0-360 degrees, for example, one bar every 45 degrees, 8 bars in total, or one bar every 10 degrees, 36 bars in total, and the peak of the histogram represents the main direction of the neighborhood gradient at the key point, i.e., the direction of the key point. The histogram can also be smoothed by a gaussian function to reduce the effect of abrupt changes.
The coordinate axes are then rotated to the direction of the key point to ensure rotational invariance. For example, as shown in fig. 4, a 8 × 8 window is selected with a keypoint as a center, fig. 5 is an effect of weighting the keypoint to 8 main directions in fig. 4, the center of the portion of fig. 4 is a position of the current keypoint, each cell represents a pixel in a scale space where the keypoint neighborhood is located, a gradient magnitude and a gradient direction of each pixel are obtained by using a formula, an arrow direction represents a gradient direction of the pixel, an arrow length represents a gradient module value, and then a gaussian window is used to perform weighting operation on the gradient magnitude and the gradient module value, where the range representing a circle gaussian weighting in fig. 4 is larger in information contribution of the gradient direction of the pixel closer to the keypoint. Then, a histogram of gradient directions in 8 directions is calculated for each 4 × 4 patch, and an accumulated value of each gradient direction is plotted, so that a seed point is formed, as shown in fig. 5. In fig. 5, a key point is composed of 4 seed points of 2 × 2, and each seed point has 8 pieces of direction vector information. The thought of neighborhood directivity information combination enhances the anti-noise capability of the algorithm, and simultaneously provides better fault tolerance for the feature matching containing the positioning error.
In each 4 x 4 quadrant of 1/16, a gradient direction histogram is calculated by adding weighted gradient values to one of the 8 direction bins of the histogram. This results in a descriptor of 4 x 8-128 dimensions for each feature, each dimension representing the scale/orientation of one of the 4 x 4 grids, and the illumination effect is further removed after normalization of this vector.
It is understood that some or all of the alternative embodiments described above may be included in some embodiments.
As shown in fig. 6, a structural frame diagram provided for an embodiment of the forest remote sensing image registration system of the present invention includes:
the image acquisition unit 1 is used for acquiring a reference image and an image to be registered of a target forest;
the single-tree identification unit 2 is used for respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
the descriptor calculation unit 3 is configured to calculate a local descriptor of the ith single tree identified in the reference image, and calculate a local descriptor of the jth single tree identified in the image to be registered;
the similarity judgment unit 4 is used for taking the Euclidean distance of the feature vectors of the singlets as a similarity judgment standard, and performing similarity judgment on the local descriptor of the jth singlet and the local descriptor of the ith singlet to obtain a registration result of the image to be registered;
where I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
According to the forest remote sensing image registration system provided by the embodiment, single trees in a forest are positioned and identified through a local maximum method, direction parameters are assigned to each point according to the gradient direction distribution characteristics of neighborhood pixels of single tree position points, operators have rotation invariance, descriptors are generated according to feature description information of the single tree position points, and the Euclidean distance of feature vectors of the single tree position points is used as similarity judgment measurement of key points in two images, so that registration of images with high self-similarity, such as forest images, is realized, and a registration result with high reliability can be obtained.
Optionally, in some possible embodiments, the similarity determination unit 4 is further configured to eliminate a result of matching error in the determination process by a least square method and a RANSAC algorithm.
Optionally, in some possible embodiments, the single-tree identifying unit 2 is specifically configured to convert the reference image into a grayscale image, perform reconstruction operation based on opening and closing to obtain a local maximum image, perform erosion operation processing on the local maximum image, superimpose the local maximum image after the erosion operation processing on the reference image, and identify and locate the single tree in the reference image;
converting the image to be registered into a gray image, carrying out reconstruction operation based on opening and closing to obtain a local maximum image, carrying out corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the image to be registered, and identifying and positioning the single wood in the image to be registered.
Optionally, in some possible embodiments, the descriptor calculating unit 3 is specifically configured to determine a position point of an ith single tree identified in the reference image, use the position point as a key point, block a preset size region around the key point, calculate a gradient histogram of each block region, generate a feature vector of the key point according to the gradient histogram, and generate a local descriptor of the key point according to the feature vector of the key point, where the local descriptor is used as a local descriptor of the ith single tree.
Optionally, in some possible embodiments, the descriptor calculating unit 3 is specifically configured to determine a position point of a jth singletree identified in the image to be registered, use the position point as a key point, block regions of a preset size around the key point, respectively calculate a gradient histogram of each block region, generate a feature vector of the key point according to the gradient histogram, and generate a local descriptor of the key point according to the feature vector of the key point, which is used as the local descriptor of the jth singletree.
It is understood that some or all of the alternative embodiments described above may be included in some embodiments.
It should be noted that the above embodiments are product embodiments corresponding to the previous method embodiments, and for the description of each optional implementation in the product embodiments, reference may be made to corresponding descriptions in the above method embodiments, and details are not described here again.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described method embodiments are merely illustrative, and for example, the division of steps into only one logical functional division may be implemented in practice in another way, for example, multiple steps may be combined or integrated into another step, or some features may be omitted, or not implemented.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A forest remote sensing image registration method based on single tree recognition is characterized by comprising the following steps:
acquiring a reference image and an image to be registered of a target forest;
respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
calculating a local descriptor of the ith single tree identified in the reference image, and calculating a local descriptor of the jth single tree identified in the image to be registered;
taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered;
wherein I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
2. The forest remote sensing image registration method based on single wood recognition according to claim 1, wherein after similarity determination is carried out on the local descriptor of the jth single wood and the local descriptor of the ith single wood, the method further comprises:
and eliminating the result of matching error in the judging process by a least square method and a RANSAC algorithm.
3. The forest remote sensing image registration method based on single tree recognition according to claim 1, wherein the single trees in the reference image and the image to be registered are respectively recognized and positioned according to a local maximum method, and the method specifically comprises the following steps:
converting the reference image into a gray image, performing reconstruction operation based on opening and closing to obtain a local maximum image, performing corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the reference image, and identifying and positioning the single wood in the reference image;
converting the image to be registered into a gray image, performing reconstruction operation based on opening and closing to obtain a local maximum image, performing corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the image to be registered, and identifying and positioning the single wood in the image to be registered.
4. The forest remote sensing image registration method based on single tree recognition according to any one of claims 1 to 3, wherein calculating a local descriptor of the ith single tree recognized in the reference image specifically comprises:
determining a position point of the ith single tree identified in the reference image, and taking the position point as a key point;
partitioning the preset size area around the key point, and respectively calculating the gradient histogram of each block area;
generating a feature vector of the key point according to the gradient histogram;
and generating a local descriptor of the key point according to the feature vector of the key point, wherein the local descriptor is used as a local descriptor of the ith single tree.
5. The forest remote sensing image registration method based on single tree recognition according to any one of claims 1 to 3, wherein calculating a local descriptor of a jth single tree recognized in the image to be registered specifically comprises:
determining a position point of the j-th single tree identified in the image to be registered, and taking the position point as a key point;
partitioning the preset size area around the key point, and respectively calculating the gradient histogram of each block area;
generating a feature vector of the key point according to the gradient histogram;
and generating a local descriptor of the key point according to the feature vector of the key point, wherein the local descriptor is used as a local descriptor of the jth single tree.
6. A forest remote sensing image registration system based on single wood recognition is characterized by comprising:
the image acquisition unit is used for acquiring a reference image and an image to be registered of the target forest;
the single-tree identification unit is used for respectively identifying and positioning the single trees in the reference image and the image to be registered according to a local maximum method;
the descriptor calculation unit is used for calculating a local descriptor of the ith single tree identified in the reference image and calculating a local descriptor of the jth single tree identified in the image to be registered;
the similarity judgment unit is used for taking the Euclidean distance of the feature vector of the single tree as a similarity judgment standard, and carrying out similarity judgment on the local descriptor of the jth single tree and the local descriptor of the ith single tree to obtain a registration result of the image to be registered;
wherein I is 1, 2, … …, I is the number of singles identified in the reference image, and J is 1, 2, … …, J is the number of singles identified in the image to be registered.
7. The forest remote sensing image registration system based on single wood recognition according to claim 6, wherein the similarity judgment unit is further used for eliminating the result of matching error in the judgment process through a least square method and a RANSAC algorithm.
8. The forest remote sensing image registration system based on single tree recognition according to claim 6, wherein the single tree recognition unit is specifically configured to convert the reference image into a gray image, perform reconstruction operation based on opening and closing to obtain a local maximum image, perform erosion operation processing on the local maximum image, superimpose the local maximum image after the erosion operation processing on the reference image, and recognize and position the single tree in the reference image;
and converting the image to be registered into a gray image, performing reconstruction operation based on opening and closing to obtain a local maximum image, performing corrosion operation processing on the local maximum image, superposing the local maximum image subjected to the corrosion operation processing to the image to be registered, and identifying and positioning the single wood in the image to be registered.
9. The forest remote sensing image registration system based on single tree recognition according to any one of claims 6 to 8, wherein the descriptor calculation unit is specifically configured to determine a position point of an ith single tree recognized in the reference image, use the position point as a key point, block regions of a preset size around the key point, respectively calculate a gradient histogram of each region, generate a feature vector of the key point according to the gradient histogram, and generate a local descriptor of the key point according to the feature vector of the key point, which is used as a local descriptor of the ith single tree.
10. The forest remote sensing image registration system based on single tree recognition according to any one of claims 6 to 8, wherein the descriptor calculation unit is specifically configured to determine a position point of a jth single tree recognized in the image to be registered, use the position point as a key point, block regions of a preset size around the key point, respectively calculate a gradient histogram of each region, generate a feature vector of the key point according to the gradient histogram, and generate a local descriptor of the key point according to the feature vector of the key point, as the local descriptor of the jth single tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010478151.3A CN111666858A (en) | 2020-05-29 | 2020-05-29 | Forest remote sensing image registration method and system based on single tree recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010478151.3A CN111666858A (en) | 2020-05-29 | 2020-05-29 | Forest remote sensing image registration method and system based on single tree recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111666858A true CN111666858A (en) | 2020-09-15 |
Family
ID=72385313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010478151.3A Pending CN111666858A (en) | 2020-05-29 | 2020-05-29 | Forest remote sensing image registration method and system based on single tree recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111666858A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102062860A (en) * | 2009-11-18 | 2011-05-18 | 中国科学院遥感应用研究所 | Foundation laser radar data registration method based on single tree position and surface information |
| CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
| CN106355577A (en) * | 2016-09-08 | 2017-01-25 | 武汉科技大学 | Method and system for quickly matching images on basis of feature states and global consistency |
| CN106558072A (en) * | 2016-11-22 | 2017-04-05 | 重庆信科设计有限公司 | A kind of method based on SIFT feature registration on remote sensing images is improved |
| CN110853081A (en) * | 2019-11-18 | 2020-02-28 | 武汉数智云绘技术有限公司 | Ground and airborne LiDAR point cloud registration method based on single-tree segmentation |
| CN111126508A (en) * | 2019-12-31 | 2020-05-08 | 湖南云顶智能科技有限公司 | Hopc-based improved heterogeneous image matching method |
| US20200226413A1 (en) * | 2017-08-31 | 2020-07-16 | Southwest Jiaotong University | Fast and robust multimodal remote sensing images matching method and system |
-
2020
- 2020-05-29 CN CN202010478151.3A patent/CN111666858A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102062860A (en) * | 2009-11-18 | 2011-05-18 | 中国科学院遥感应用研究所 | Foundation laser radar data registration method based on single tree position and surface information |
| CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
| CN106355577A (en) * | 2016-09-08 | 2017-01-25 | 武汉科技大学 | Method and system for quickly matching images on basis of feature states and global consistency |
| CN106558072A (en) * | 2016-11-22 | 2017-04-05 | 重庆信科设计有限公司 | A kind of method based on SIFT feature registration on remote sensing images is improved |
| US20200226413A1 (en) * | 2017-08-31 | 2020-07-16 | Southwest Jiaotong University | Fast and robust multimodal remote sensing images matching method and system |
| CN110853081A (en) * | 2019-11-18 | 2020-02-28 | 武汉数智云绘技术有限公司 | Ground and airborne LiDAR point cloud registration method based on single-tree segmentation |
| CN111126508A (en) * | 2019-12-31 | 2020-05-08 | 湖南云顶智能科技有限公司 | Hopc-based improved heterogeneous image matching method |
Non-Patent Citations (1)
| Title |
|---|
| 刘丽晖: "基于不变量理论的遥感图像特征匹配技术", 知识经济 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gao et al. | Automatic change detection in synthetic aperture radar images based on PCANet | |
| Zamir et al. | Accurate image localization based on google maps street view | |
| CN109544501A (en) | A kind of transmission facility defect inspection method based on unmanned plane multi-source image characteristic matching | |
| CN110414566B (en) | Land coverage type change detection method based on time sequence PolSAR image | |
| Ye et al. | An image-based approach for automatic detecting tasseling stage of maize using spatio-temporal saliency | |
| CN103353941B (en) | Natural marker registration method based on viewpoint classification | |
| CN117274627A (en) | Multi-temporal snow remote sensing image matching method and system based on image conversion | |
| CN116310852A (en) | Double-time-phase remote sensing image unsupervised classification and change detection method and system | |
| CN109544608B (en) | Unmanned aerial vehicle image acquisition characteristic registration method | |
| CN111462310A (en) | Bolt defect space positioning method based on multi-view geometry | |
| CN114494373A (en) | High-precision rail alignment method and system based on target detection and image registration | |
| CN113221805B (en) | Method and device for acquiring image position of power equipment | |
| CN112488022B (en) | Method, device and system for monitoring panoramic view | |
| Huang et al. | Superpixel-based change detection in high resolution sar images using region covariance features | |
| Zheng et al. | Deep learning based target detection method with multi-features in SAR imagery | |
| Han et al. | Accurate and robust vanishing point detection method in unstructured road scenes | |
| Liu et al. | RFM-GAN: Robust feature matching with GAN-based neighborhood representation for agricultural remote sensing image registration | |
| CN111666858A (en) | Forest remote sensing image registration method and system based on single tree recognition | |
| CN115861927A (en) | Image identification method and device for power equipment inspection image and computer equipment | |
| CN113642430A (en) | High-precision visual positioning method and system for underground parking lot based on VGG + NetVLAD | |
| CN113850173A (en) | Method, device and medium for eliminating repeated positioning of faulty photovoltaic module | |
| CN106127224A (en) | Based on the semi-supervised polarization SAR sorting technique quickly auctioning figure | |
| Walter | Object-based classification of integrated multispectral and LIDAR data for change detection and quality control in urban areas | |
| Liu et al. | Identification of Damaged Building Regions from High-Resolution Images Using Superpixel-Based Gradient and Autocorrelation Analysis | |
| Cong | Image stitching technology for police drones using an improved image registration method incorporating ORB algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200915 |