CN115294482B - Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image - Google Patents
Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image Download PDFInfo
- Publication number
- CN115294482B CN115294482B CN202211170765.0A CN202211170765A CN115294482B CN 115294482 B CN115294482 B CN 115294482B CN 202211170765 A CN202211170765 A CN 202211170765A CN 115294482 B CN115294482 B CN 115294482B
- Authority
- CN
- China
- Prior art keywords
- image
- triangle
- connected domain
- domain
- sub
- 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.)
- Active
Links
- 241000233866 Fungi Species 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims description 46
- 238000005303 weighing Methods 0.000 claims description 4
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 8
- 150000001875 compounds Chemical class 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 240000000599 Lentinula edodes Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000001497 healthy food Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection 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
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/16—Image acquisition using multiple overlapping images; Image stitching
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Mining & Mineral Resources (AREA)
- Human Resources & Organizations (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an edible fungus yield estimation method based on unmanned aerial vehicle remote sensing images, and belongs to the technical field of image data processing; the method comprises the following steps: sequentially collecting top views of a plurality of edible fungi planted in the field along a preset air route by an unmanned aerial vehicle, and obtaining a plurality of third communicating areas with the shape similar to that of the first communicating area; obtaining a plurality of triangles III similar to the triangles I in shape; sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field; and obtaining the total weight of the edible fungi in the planting field. The invention can realize the quick seamless splicing of the images; and estimating the yield of the edible fungi according to the area of the fungus cover of the edible fungi.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an edible fungus yield estimation method based on unmanned aerial vehicle remote sensing images.
Background
The edible fungi is a large fungus which can be eaten as a dish or used as a medicine to treat diseases, has the characteristics of rich nutrition, unique flavor, higher medicinal value and the like, is deeply favored by people, is gradually integrated into the ranks of natural healthy foods in the current society, is planted outdoors in a large range artificially, and needs to be subjected to yield estimation to provide data support for subsequent picking, processing and selling. The method for estimating the crop yield by using the remote sensing technology becomes a mainstream method, and the remote sensing method for estimating the crop yield is timely and efficient in data acquisition, low in cost and wide in monitoring range. However, high-precision yield estimation is difficult to realize by satellite remote sensing, so that the unmanned aerial vehicle platform with the advantages of low cost, strong maneuverability, simplicity in operation, large observation range and the like is developed rapidly, a suitable image with high precision can be provided, and a new way is provided for farmland information acquisition and yield estimation.
However, in order to obtain a complete edible fungus planting field, each image acquired by the unmanned aerial vehicle must have an overlapping part, and in order to make yield estimation more accurate, the acquired continuous images need to be accurately spliced. The traditional image mosaic algorithm, such as an image mosaic technology based on an SIFT algorithm and an image mosaic technology based on an SURF algorithm, has low operation efficiency in the mosaic process, needs to perform operations of extracting and matching feature points for each image for multiple times in the mosaic mode, consumes a large amount of time, and has low robustness. Especially, when the scale transformation, the visual angle transformation and the illumination change exist in the images, the matching precision between two continuous images is poor, and splicing gaps and ghost misplacement phenomena are easy to occur.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides an edible fungus yield estimation method based on an unmanned aerial vehicle remote sensing image, the method performs binarization operation on the image, and performs image splicing by using the characteristics of edible fungi in the binary image according to the acquisition sequence of the image, so that the matching precision can be ensured, the matching speed is greatly improved, the splicing ghost image dislocation phenomenon can be effectively eliminated, and the rapid seamless splicing of the image can be realized; and estimating the yield of the edible fungi according to the area of the fungus cover of the edible fungi.
The invention aims to provide an edible fungus yield estimation method based on an unmanned aerial vehicle remote sensing image, which comprises the following steps:
sequentially collecting a plurality of top views of edible fungi planted in the field along a preset air route by an unmanned aerial vehicle, wherein partial areas of two adjacent top views are overlapped; carrying out binarization processing on each top view to obtain a binary image; marking two adjacent binary images as a first image and a second image;
acquiring a first communication domain of each pileus in a first image; simultaneously acquiring a second connected domain of each pileus in a second image;
acquiring a plurality of third connected domains with similar shapes to the first connected domains from all the second connected domains according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
connecting every two first connected domains with the centers of two adjacent first connected domains, wherein the centers of the two first connected domains are not on the same straight line, so as to form a triangle I; according to any third connected domain with the shape similar to that of the first connected domain, two central points which are adjacent to the third connected domain and have central points which are not on the same straight line and comprise the second connected domain and/or the third connected domain are connected pairwise to form a triangle II, and a plurality of triangles II are obtained in sequence; acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the side length in the triangle I and the side length of each triangle II;
acquiring a triangle III overlapped with the triangle I by using the number of pixel points of the three connected domains corresponding to the triangle I and the number of pixel points of the non-overlapped region when the pixel points of the three connected domains corresponding to the triangle I are overlapped with the three connected domains corresponding to each triangle III; splicing the first image and the second image based on a triangle positioning mode according to the triangle I and a triangle III superposed with the triangle I; sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field;
obtaining a plurality of pileus with different overlooking areas, weighing the pileus, measuring the overlooking area of the pileus, and then performing smooth curve fitting according to the overlooking areas of the pileus and corresponding weight data to obtain an area and weight function;
and (4) overlooking the area of each pileus in the complete image of the edible fungi in the planting field, and obtaining the total weight of the edible fungi in the planting field through an area and weight function.
In one embodiment, a plurality of third connected components with similar shapes to the first connected component are obtained according to the following steps:
acquiring a first probability that the shape of each first connected domain is similar to that of each second connected domain according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
and acquiring a plurality of third connected domains with similar shapes to the first connected domain from all the second connected domains according to the first probability that the first connected domain is similar to each second connected domain in shape.
In one embodiment, the first probability that the first connected component and each second connected component are similar in shape is obtained according to the following steps:
acquiring first communication domains of a plurality of pileus in a first image; obtaining a first area and a first perimeter of a first communication domain of each pileus;
obtaining a first circularity of each pileus according to the first area and the first perimeter of each first connected domain;
similarly, a second area, a second perimeter and a second circularity of each pileus of a second connected domain of each pileus in the second image are obtained;
and acquiring a first probability that the shapes of the first connected domain and each second connected domain are similar according to the first area, the first circumference and the first circularity of any first connected domain and the second area, the second circumference and the second circularity of each second connected domain.
In one embodiment, a plurality of triangles III similar in shape to the triangle I are obtained by the following steps:
acquiring two nearest and next nearest first communication domains of the first communication domain and the first communication domain which are adjacent to the first communication domain and have different central points on the same straight line; connecting the first connected domain with the central points of two adjacent first connected domains to form a triangle I;
acquiring any third connected domain with a shape similar to that of the first connected domain, and acquiring two nearest and second nearest second connected domains and/or third connected domains, which are adjacent to the third connected domain and have different central points on the same straight line; connecting the third connected domain with the central points of two adjacent second connected domains and/or third connected domains to form a triangle II; sequentially obtaining a plurality of triangles II;
acquiring a second probability that the shape of the triangle I is similar to that of each triangle II according to the side length in the triangle I and the side length of each triangle II; and acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the second probability that the triangle I is similar to the shape of each triangle II.
In one embodiment, the first image and the second image are stitched according to the following steps:
forming a first sub-image by using the minimum circumscribed rectangle of the three connected domains corresponding to the triangle I; forming a second sub-image by using the minimum external rectangles of the three connected domains corresponding to any one triangle III, and sequentially acquiring a plurality of second sub-images;
acquiring a second sub-image superposed with the first sub-image according to the number of pixels in three connected domains in the first sub-image when the number of pixels in the three connected domains is superposed with each second sub-image;
and splicing the first image and the second image based on a triangle positioning mode according to a triangle III corresponding to a second sub-image superposed with the first sub-image and a triangle I corresponding to the first sub-image.
In an embodiment, the second sub-image coinciding with the first sub-image is obtained by:
acquiring the coincidence probability of the first sub-image and each second sub-image according to the number of the pixel points in the three connected domains in the first sub-image and the number of the pixel points in the non-coincident connected domains when the number of the pixel points in the three connected domains in the first sub-image is overlapped with each second sub-image;
and acquiring second sub-images coincident with the first sub-images according to the coincidence probability of the first sub-images and each second sub-image.
The beneficial effects of the invention are: the invention provides an edible fungus yield estimation method based on unmanned aerial vehicle remote sensing images, which comprises the steps of extracting characteristics of the acquired remote sensing images according to HSV color characteristics of edible fungi to obtain a connected domain of each pileus; in order to reduce the calculated amount in the algorithm and improve the running speed of the algorithm, the image is subjected to binarization operation; according to the image acquisition sequence, the optimal selected target connected domain is screened out by acquiring the two adjacent binary image similar connected domains for preliminary matching, and the workload of subsequent matching is reduced; then, triangles in two adjacent images are respectively constructed based on similar connected domains, each connected domain is regarded as a point, accurate matching is carried out in a triangular positioning mode, the accuracy of splicing the two adjacent images is effectively improved, the adjacent images are spliced, the matching speed is greatly improved while the matching accuracy is ensured, the splicing ghost image dislocation phenomenon is effectively eliminated, and rapid seamless splicing of the images can be realized; and estimating the yield of the edible fungi according to the area of the fungus cover of the edible fungi.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart showing the general steps of an embodiment of the method for estimating the yield of edible fungi based on the unmanned aerial vehicle remote sensing image.
FIG. 2 is an HSV image of shiitake mushrooms in an edible fungus.
FIG. 3 is a non-uniform quantization histogram corresponding to HSV images of mushrooms in edible fungi.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method mainly estimates the yield of the edible fungi planted outdoors, but for the edible fungi with larger planting areas, the overall yield of the edible fungi is difficult to estimate by visual inspection or aerial photography; because the height of aerial photography is high when an integral image is acquired, the pileus area of each edible fungus in the photographed image is difficult to estimate. Therefore, multiple remote sensing edible fungus planting field images are shot through low-flight aerial photography, and the collected remote sensing images need to be accurately spliced for edible fungus yield estimation; the existing image splicing method has long time and low matching precision, and splicing gaps and ghost misplacement phenomena are easy to occur.
It should be noted that the invention is mainly aimed at the yield estimation of outdoor mushroom planting, the production of mushrooms is almost independent growth, and the pileus of each mushroom is clearly displayed in the collected image.
According to the method, the collected remote sensing image is processed, extraction and identification are carried out according to HSV color characteristics of the edible fungi, then binaryzation operation is carried out on the image, and image splicing is carried out according to the collection sequence of the image by utilizing the characteristics of the edible fungi in the binary image, so that the matching precision can be ensured, the matching speed is greatly improved, the splicing ghost image dislocation phenomenon can be effectively eliminated, and the quick seamless splicing of the image can be realized; and further estimating the yield of the edible fungi according to the area of the pileus of the edible fungi.
The invention provides an edible fungus yield estimation method based on an unmanned aerial vehicle remote sensing image, which is shown in figure 1 and comprises the following steps:
s1, sequentially collecting a plurality of top views of edible fungi planted in a field along a preset air route by an unmanned aerial vehicle, wherein partial areas of two adjacent top views are overlapped; carrying out binarization processing on each top view to obtain a binary image; recording two adjacent binary images as a first image and a second image;
in this embodiment, when the top view of the edible fungi is collected, in order to avoid the influence of the irradiation intensity of the solar rays, the top view of the edible fungi planted in the field is selected to be shot by flying by using an unmanned aerial vehicle in the early morning or evening without dazzling, and the top view of the edible fungi is obtained; wherein the top view of the edible fungi contains the edible fungi cap. Be equipped with laser range finding sensor on the unmanned aerial vehicle, can acquire its height apart from ground in real time, the camera is adjusted the height and is made the image can clearly show domestic fungus information when shooing, and carries out the altitude mark that corresponds to every high accuracy remote sensing image of gathering.
It should be noted that, when the images are acquired, the flying heights of the unmanned aerial vehicles are different, so that the scene and the actual proportion in the shot images are different, and the images are adjusted by using geometric transformation. And then carrying out binarization operation on the image, and further carrying out image splicing according to the shape and position relation of the edible fungi. Therefore, in the process of acquiring the top views, the size proportion of each top view acquired by the acquisition equipment is equal according to the height of the acquisition equipment from the planting field.
In this embodiment, the image size of collection is unanimous, however because the difference of unmanned aerial vehicle flying height can lead to scenery and actual proportion in each image different, need adjust and make it unified, specifically as follows:
acquiring the size of each image according to the imaging parameters of the camera on the unmanned aerial vehicle and the mark height of each acquired imageAnd sequentially acquiring a proportion set according to the image acquisition sequence and the proportion of the corresponding actual size
Wherein
Is the number of images acquired. Get the set
Mean value of
The standard proportion parameter is used to make the proportion of the size of the scenery object in each image and the actual size of the scenery uniform, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
in order to set the standard ratio parameter,
is as follows
The ratio of the image of the web to the actual size,
is a first
Scaling factor of the image. According to the scaling factor of each image
The image is geometrically transformed and adjusted so that the ratio of the image size to the corresponding actual size is uniform
(ii) a It should be noted that the scaling factor is obtained according to the imaging parameters of the camera on the unmanned aerial vehicle and the mark height of each acquired image; therefore, the zoomed image is obtained, namely the top view of the edible fungi.
In this embodiment, when binarization processing is performed on each top view, binarization processing is performed on the scaled image, where a pixel point in a pileus region of the edible fungus is 1, and a pixel point in a background region is 0.
S2, acquiring a plurality of third connected domains similar to the first connected domain in shape; the method comprises the following specific steps:
acquiring a first communication domain of each pileus in a first image; simultaneously acquiring a second connected domain of each pileus in the second image;
acquiring a plurality of third connected domains with similar shapes to the first connected domains from all the second connected domains according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
it should be noted that the color can be used for most intuitively distinguishing different types of things, the calculation amount of color feature extraction is small, and the color of the mushroom cap surface of the edible mushroom is greatly different from the surrounding environment. In this embodiment, the histogram equalization algorithm is used to enhance the image acquired by the unmanned aerial vehicle, improve the visual effect of the image, and then the bilateral filtering is used to perform denoising processing on the image. The image is then converted from the RGB color space to the HSV color space, as shown in fig. 2 and 3, this embodiment uses 16:4:4, obtaining the HSV image in fig. 2 and the non-uniform quantization histogram corresponding to the HSV image in fig. 2 in fig. 3.
Through counting the color component characteristics of the mushrooms in the current planting field, setting a threshold range according to the color component characteristic values, and judging that the color non-uniform component characteristic values of the pixels are in the edible mushroom area within the threshold range. And finally, acquiring the connected domain of each pileus by using morphological opening operation and filling operation. Therefore, a first communication domain corresponding to each pileus is obtained from the first image; and acquiring a second connected domain of each pileus from the second image.
In this embodiment, the first connected component in the first image is marked in the following way:
taking the upper left corner of the collected first image as a starting point, and traversing pixel points at the edge of the image in a clockwise direction; taking a first communication domain of a pileus of the edible fungi with the closest initial traversal pixel point, and marking the first communication domain
Taking the first connected domain of the edible fungus with the shortest traversal pixel point distance, and if the connected domain is still the same
Then, the first connected domain of the edible fungus with the shortest traversal pixel point distance is taken down again until a new first connected domain of the edible fungus is obtained and marked as
Thereby obtaining a first set of pileus communication domains at the edge of the first image near the second image
Wherein, in the process,
number of first communication domains for the labeled pileus.
In this embodiment, a plurality of third connected components with similar shapes to the first connected component are obtained according to the following steps:
acquiring a first probability that the shape of each first connected domain is similar to that of each second connected domain according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
and acquiring a plurality of third connected domains with similar shapes to the first connected domain from all the second connected domains according to the first probability that the first connected domain is similar to each second connected domain in shape.
The first probability that the shape of the first connected domain is similar to that of each second connected domain is obtained according to the following steps:
acquiring first communication domains of a plurality of pileus in a first image; and obtaining a first area and a first perimeter of a first connected domain of each pileus;
obtaining a first circularity of each pileus according to the first area and the first perimeter of each first connected domain;
similarly, a second area, a second perimeter and a second circularity of each pileus of a second connected domain of each pileus in the second image are obtained;
and according to the first area, the first perimeter and the first circularity of any first connected domain and the second area, the second perimeter and the second circularity of each second connected domain, obtaining a first probability that the shapes of the first connected domain and each second connected domain are similar.
Note that, in the present embodiment, statistics are collected
First pileus first communication domain
S and perimeter L, the first circularity E is therefore calculated as:
in the formula (I), the compound is shown in the specification,
representing a first connected domain
A first circularity of (a);
representing a first connected domain
The area of (a) is greater than (b),
representing a first connected domain
Perimeter. Wherein the first connected domain
And first connected domain
The perimeter is according to the first communication domain
The number of inner pixels and the number of edge pixels. Since most of the pileus communication domains of the edible fungi are circular, the degree of each pileus is expressed by the circularity. Sequentially calculate a set
The circularity of each first communication domain; similarly, a second area, a second perimeter and a second circularity of each pileus of a second connected domain of each pileus in the second image are obtained.
First connected domain
The first probability of similarity in shape to each second connected component is calculated as follows:
in the formula (I), the compound is shown in the specification,
representing a first connected domain
And any one ofThe second connected domain has a first probability of being similar in shape;
Sequentially calculating each second connected domain and each first connected domain
A first probability that the shapes of (a) are similar; set the first probability threshold of 99%, if
If not, the two pileus connected domains are judged to be similar, otherwise, the two pileus connected domains are judged to be irrelevant. Sequentially acquiring the first communication domain in the second image
The number of similar second connected domains is marked as C;
if C is 0, then determine the first communication domain
Not in the overlapped region of the two images, and returning the collection
First connected domain of middle and next pileus
Calculating the first communication domain
Similar connected domains; if the number of the similar connected domains still obtained is 0, the calculation is carried out until the first connected domain is calculated
Similar connected domains; wherein the content of the first and second substances,
number of first communication domains for the labeled pileus;
if C is greater than 0, thenConnecting domains with the number C, namely the connecting domains with the first connecting domain
A similar plurality of third connected domains; at least three points which are not on a straight line are needed for image splicing to be positioned, so that splicing malposition ghosting is prevented; a next determination is made to determine the most similar connected domain from the third connected domains. It should be noted that the purpose of setting the first probability threshold to 99% is to obtain the most similar connected components and avoid larger errors in subsequent triangulation.
S3, obtaining a plurality of triangles III similar to the triangle I in shape; the method comprises the following specific steps:
connecting every two first connected domains with the center points of two adjacent first connected domains, wherein the center points of the two first connected domains are not on the same straight line, so as to form a triangle I; according to any third connected domain with the shape similar to that of the first connected domain, two central points which are adjacent to the third connected domain and have central points which are not on the same straight line and comprise the second connected domain and/or the third connected domain are connected in pairs to form a triangle II, and a plurality of triangles II are sequentially obtained; acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the side length in the triangle I and the side length of each triangle II;
wherein, a plurality of triangles III similar to the shape of the triangle I are obtained according to the following steps:
acquiring two first communication domains which are adjacent to the first communication domain and have central points which are not nearest and next nearest on the same straight line; connecting the central points of the first communication domains and two adjacent first communication domains to form a triangle I;
any third connected domain with the shape similar to that of the first connected domain is obtained, and the two nearest and next nearest connected domains with central points not on the same straight line are obtained and comprise the second connected domain and/or the third connected domain; connecting the third connected domain and the central points of two adjacent connected domains including the second connected domain and/or the third connected domain to form a triangle II; sequentially obtaining a plurality of triangles II;
acquiring a second probability that the shape of the triangle I is similar to that of each triangle II according to the side length in the triangle I and the side length of each triangle II; and acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the second probability that the triangle I is similar to the shape of each triangle II.
In the present embodiment, in order to obtain a plurality of triangles iii similar to the shape of the triangle i, the following are specific:
taking a first connected domain away from the pileus in the first image
Counting central points of the three first communication domains, and if the three central points are positioned on a straight line, taking the distance between the remaining first communication domains and the first communication domain
The nearest one replaces the relatively distant one of the two first communication domains until the three center points, which form a triangle i, do not lie on a straight line. Connecting the first communication domain
Is set as the connecting edge of the center point of the first connecting domain closest to the center point of the first connecting domain
Having a length of
Connecting the first communication domain
The connecting edge of the center point of the first connecting domain with the next closest center point is set as
Having a length of
Setting the connecting edge between the central point of the nearest first connected domain and the central point of the next nearest first connected domain as
Having a length of
。
In the same way, with the first connection domain
The third connected domain is obtained, the two nearest and next nearest connected domains with the central points not on the same straight line comprise the second connected domain and/or the third connected domain; connecting the third connected domain and the central points of two adjacent connected domains including the second connected domain and/or the third connected domain to form a triangle II; sequentially obtaining a plurality of triangles II; the connecting edge of the third connected domain and the nearest one including the center point of the second connected domain or the third connected domain is set as
Having a length of
(ii) a The third connected domain and the next nearest connected edge including the center point of the second connected domain or the third connected domain are set as
Having a length of
(ii) a Setting the connecting edge of the nearest central point including the second connected domain or the third connected domain and the next nearest central point including the second connected domain or the third connected domain as
Length of whichIs composed of
；
Acquiring a second probability that the shape of the triangle I is similar to that of each triangle II according to the side length in the triangle I and the side length of each triangle II; the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
representing a second probability that the shape of the triangle I is similar to that of any one of the triangles II;
Similarly, in the second image, the first communication domain is acquired
All triangles II formed by each similar third connected domain and the connected domains of the neighborhoods and the center points of which are not on the same straight line; calculating second probabilities that the shapes of the triangles II and the triangles I are similar one by one;
set the second probability threshold of 99%, if
Then judge the triangle II and triangle I pairThe side lengths are similar, and the corresponding included angles are similar; otherwise it is judged not relevant. Obtaining the first communication domain from C third communication domains in the second image
The number of third connected domains corresponding to a triangle II similar to the triangle I is marked as D;
if D is 0, all triangles II and first connected domains formed by C third connected domains in the second image are judged
The formed triangles I are dissimilar and return to the collection
First connected domain of middle and next pileus
Then sequentially calculating the first connection domain
Similar connected domains, and computing the first connected domain
The number of third connected domains corresponding to the triangles II forming the triangles similar to the triangle I is calculated to the first connected domain in sequence if the number of the third connected domains corresponding to the triangle II still obtained is 0
；
If D is larger than 0, obtaining triangles similar to the triangle I from all the triangles II, and marking the triangles similar to the triangle I as a plurality of triangles III; then the next step of judgment is carried out, and the triangle which is the most coincident with the triangle I is selected from the plurality of triangles III.
It should be noted that the purpose of setting the second probability threshold to 99% is to obtain the most similar triangles and avoid larger errors in subsequent triangulation.
S4, sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field; the method comprises the following specific steps:
acquiring a triangle III overlapped with the triangle I by using the number of pixel points of the three connected domains corresponding to the triangle I and the number of pixel points of the non-overlapped region when the pixel points of the three connected domains corresponding to the triangle I are overlapped with the three connected domains corresponding to each triangle III; splicing the first image and the second image based on a triangle positioning mode according to the triangle I and a triangle III superposed with the triangle I; sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field;
the first image and the second image are spliced according to the following steps:
forming a first sub-image by using the minimum external rectangle of the three connected domains corresponding to the triangle I; forming a second sub-image by using the minimum external rectangles of the three connected domains corresponding to any one triangle III, and sequentially acquiring a plurality of second sub-images;
acquiring a second subimage superposed with the first subimage according to the quantity of the pixels in three connected domains in the first subimage when the quantity of the pixels in the three connected domains is superposed with each second subimage;
and splicing the first image and the second image based on a triangle positioning mode according to a triangle III corresponding to a second sub-image superposed with the first sub-image and a triangle I corresponding to the first sub-image.
It should be noted that, the second sub-image coinciding with the first sub-image is obtained according to the following steps:
acquiring the coincidence probability of the first sub-image and each second sub-image according to the number of the pixel points in the three connected domains in the first sub-image and the number of the pixel points in the non-coincident connected domains when the number of the pixel points in the three connected domains in the first sub-image is overlapped with each second sub-image;
and acquiring second sub-images coincident with the first sub-images according to the coincidence probability of the first sub-images and each second sub-image.
In this embodiment, the first sub-image formed by the minimum bounding rectangle of the three connected components corresponding to the triangle I is recorded as
(ii) a Taking the minimum circumscribed rectangle of three connected domains corresponding to any one triangle III to form a second sub-image
；
Let the first connection region in triangle I
And the central point of (3) and the first communication area in the triangle III
The central points of the corresponding connected domains are overlapped, and the image is rotated by taking the point as the center
Make the connecting side of the triangle I and the triangle III
And with
Angle and connecting edge of
And with
The sum of the included angles is minimum;
counting the number of pixel points of which the first sub-image and the second sub-image are non-overlapped regions at the moment
Then, the number of pixel points in the three connected domains selected in the first image is calculated
Obtaining the similarity probability of the two sub-images
Is as follows; the calculation formula of the coincidence probability of the first sub-image and each second sub-image is as follows:
in the formula (I), the compound is shown in the specification,
representing the coincidence probability of the first sub-image and each second sub-image;
representing the number of pixel points of a non-overlapped connected domain when the first sub-image is overlapped with the second sub-image;
and expressing the number of pixel points in three connected domains in the first subimage. The number of pixels in which two sub-images are non-overlapped regions
The larger the more, the similar probability thereof
The smaller.
Calculating a second sub-image formed by three connected domains corresponding to each triangle III in the second image and a first sub-image formed by three connected domains corresponding to the triangle I in the first image one by one, and rotating the coincidence probability
Setting a coincidence probability threshold of 99%, if
If the two sub-images are similar, otherwise, the two sub-images are not related. It should be noted that the threshold value of the coincidence probability is set to 99% mainly to avoid the occurrence of the localization ghost.
And sequentially acquiring the number of all second sub-images formed in the second image and all overlapped second sub-images of the first sub-images in the first image after rotation, and recording as R.
If R is 0, judging that all the second sub-images are not coincident with the first sub-image, and returning to the collection
First connected domain of middle and next pileus
Then sequentially calculating the first connection domain
Similar connected domain, computing the first connected domain
The number of third connected domains corresponding to a triangle II similar to the triangle I is formed, the number of all second sub-images which are overlapped with the first sub-image in the first image after rotation is calculated, and if all the second sub-images which are obtained are not overlapped with the first sub-image, the number of the third connected domains is calculated from the first connected domain to the first connected domain in sequence
；
If R is larger than 0, judging that all second sub-images have second sub-images coincident with the first sub-images, and taking coincidence probability in the number of all second sub-images
A triangle III corresponding to the second sub-image at the maximum is used as a triangle superposed with the triangle I;
will be connected with a triangleThe central points of three connected domains corresponding to the overlapped triangles III are used as positioning points, and the first connected domain of the pileus in the first image is enabled to be positioned based on a triangle positioning mode
And the central point of (2) and the first communication area in the second image
The center points of the corresponding connected domains are overlapped, and then the second image is rotated to ensure that the triangle I and the connecting edge corresponding to the overlapped triangle III are connected
And with
Angle and connecting edge of
And
the sum of the included angles is minimum, the superposition is regarded as successful, and the pixel value of the corresponding pixel point of the overlapping part of the first image and the second image is set as 1; the splicing of the first image and the second image is completed; and sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field.
The image splicing process is performed by using binary images, the values of pixel points are only 0 and 1, the calculated amount in the algorithm is greatly reduced, the running speed of the algorithm is improved, then preliminary matching is performed according to the shape characteristics of the pileus connected domain, then accurate matching is performed by using a triangular positioning mode according to the connected domain position, and the splicing ghost image dislocation phenomenon can be effectively prevented.
S5, obtaining the total weight of edible fungi in the planting field; the method comprises the following specific steps:
obtaining a plurality of pileus with different overlooking areas, weighing the pileus, measuring the overlooking areas of the pileus, and then performing smooth curve fitting according to the overlooking areas of the pileus and corresponding weight data to obtain an area and weight function;
overlooking the area of each mushroom cap in the complete image of the edible mushrooms in the planting field, and obtaining the total weight of the edible mushrooms in the planting field through an area and weight function.
In this embodiment, a complete image of the current planting field and a pileus connected domain of the edible fungi in the image are obtained, the area of the pileus connected domain is counted, and an area set is obtained
Wherein
The number of edible fungi in the current planted field is shown. The corresponding ratio of the image size to the actual size is known as
Then the actual overlook area of each pileus is collected
Comprises the following steps:
the method comprises the following steps of taking 50 edible fungi with different overlooking area sizes of the fungus covers, weighing the edible fungi and measuring the overlooking area of the fungus covers, and then carrying out smooth curve fitting according to the overlooking area of the 50 groups of fungus covers and corresponding weight data to obtain an area and weight function, wherein the formula is as follows:
wherein y is the weight of the edible fungi, x is the overlooking area of each actual pileus,
as a function of area and weight.
Collecting the actual overlook area of the mushroom cap
Substituting into the area and weight function to obtain corresponding weight set of edible fungi
(ii) a Weight set of edible fungi
The weight calculation formula of each edible fungus is as follows:
in the formula (I), the compound is shown in the specification,
shows the actual plan view area of the cap of the kth edible fungus,
as a function of the area and the weight,
is the weight of the kth edible fungus,
representing the number of edible fungi in the current planting field;
the total weight H of the edible fungi in the current planting field is obtained through the obtained weight calculation of each edible fungus, and the specific calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
the weight of the kth edible fungi is,
representing the number of the edible fungi in the current planting field, and H represents the weight estimation of the edible fungi in the current planting field; thereby calculating the total weight of the edible fungi in the planting field.
In conclusion, according to the method for estimating the yield of the edible fungi based on the unmanned aerial vehicle remote sensing image, the characteristics of the acquired remote sensing image are extracted according to HSV color characteristics of the edible fungi, and the connected domain of each pileus is obtained; in order to reduce the calculated amount in the algorithm and improve the running speed of the algorithm, the image is subjected to binarization operation; according to the image acquisition sequence, the optimal selection target connected domain is screened out by acquiring the similar connected domains of two adjacent binary images for preliminary matching, and the workload of subsequent matching is reduced; then, triangles in two adjacent images are respectively constructed based on similar connected domains, each connected domain is regarded as a point, accurate matching is carried out in a triangular positioning mode, the accuracy of splicing the two adjacent images is effectively improved, the adjacent images are spliced, the matching speed is greatly improved while the matching accuracy is ensured, the splicing ghost image dislocation phenomenon is effectively eliminated, and rapid seamless splicing of the images can be realized; and estimating the yield of the edible fungi according to the area of the fungus cover of the edible fungi.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An edible fungus yield estimation method based on unmanned aerial vehicle remote sensing images is characterized by comprising the following steps:
sequentially collecting top views of a plurality of pieces of edible fungi planted in the field along a preset air route by an unmanned aerial vehicle, wherein partial areas of two adjacent top views are overlapped; carrying out binarization processing on each top view to obtain a binary image; marking two adjacent binary images as a first image and a second image;
acquiring a first communication domain of each pileus in a first image; simultaneously acquiring a second connected domain of each pileus in a second image;
acquiring a plurality of third connected domains with similar shapes to the first connected domains from all the second connected domains according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
connecting every two first connected domains with the center points of two adjacent first connected domains, wherein the center points of the two first connected domains are not on the same straight line, so as to form a triangle I; according to any third connected domain with the shape similar to that of the first connected domain, two central points which are adjacent to the third connected domain and have central points which are not on the same straight line and comprise the second connected domain and/or the third connected domain are connected in pairs to form a triangle II, and a plurality of triangles II are sequentially obtained; acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the side length in the triangle I and the side length of each triangle II;
acquiring a triangle III overlapped with the triangle I by utilizing the number of pixel points of three connected domains corresponding to the triangle I and the number of pixel points of an un-overlapped area when the three connected domains corresponding to each triangle III are overlapped; splicing the first image and the second image based on a triangle positioning mode according to the triangle I and a triangle III superposed with the triangle I; sequentially splicing all adjacent two binary images to obtain a complete image of the edible fungi in the planting field;
obtaining a plurality of pileus with different overlooking areas, weighing the pileus, measuring the overlooking area of the pileus, and then performing smooth curve fitting according to the overlooking areas of the pileus and corresponding weight data to obtain an area and weight function;
and (4) overlooking the area of each pileus in the complete image of the edible fungi in the planting field, and obtaining the total weight of the edible fungi in the planting field through an area and weight function.
2. The method for estimating the yield of edible fungi based on the unmanned aerial vehicle remote sensing image according to claim 1, wherein the plurality of third connected domains with similar shapes of the first connected domain are obtained according to the following steps:
acquiring a first probability that the shape of each first connected domain is similar to that of each second connected domain according to the area and the perimeter of any first connected domain and the area and the perimeter of each second connected domain;
and acquiring a plurality of third connected domains with similar shapes to the first connected domain from all the second connected domains according to the first probability that the first connected domain is similar to each second connected domain in shape.
3. The method for estimating the yield of the edible fungi based on the unmanned aerial vehicle remote sensing image as claimed in claim 2, wherein the first probability that the shape of the first connected domain is similar to that of each second connected domain is obtained according to the following steps:
acquiring first communication domains of a plurality of pileus in a first image; obtaining a first area and a first perimeter of a first communication domain of each pileus;
obtaining a first circularity of each pileus according to the first area and the first perimeter of each first connected domain;
similarly, a second area, a second perimeter and a second circularity of each pileus of a second connected domain of each pileus in the second image are obtained;
and acquiring a first probability that the shapes of the first connected domain and each second connected domain are similar according to the first area, the first perimeter and the first circularity of any first connected domain and the second area, the second perimeter and the second circularity of each second connected domain.
4. The method for estimating the yield of the edible fungi based on the unmanned aerial vehicle remote sensing image according to claim 1, wherein a plurality of triangles III similar to the triangle I in shape are obtained according to the following steps:
acquiring two nearest and next nearest first communication domains of the first communication domain and the first communication domain which are adjacent to the first communication domain and have different central points on the same straight line; connecting the central points of the first communication domains and the central points of two adjacent first communication domains to form a triangle I;
acquiring any third connected domain with a shape similar to that of the first connected domain, and acquiring two nearest and second nearest second connected domains and/or third connected domains, which are adjacent to the third connected domain and have different central points on the same straight line; connecting the third connected domain with the central points of two adjacent second connected domains and/or third connected domains to form a triangle II; sequentially obtaining a plurality of triangles II;
acquiring a second probability that the shape of the triangle I is similar to that of each triangle II according to the side length in the triangle I and the side length of each triangle II; and acquiring a plurality of triangles III similar to the shape of the triangle I from all the triangles II according to the second probability that the triangle I is similar to the shape of each triangle II.
5. The method for estimating the yield of edible fungi based on the unmanned aerial vehicle remote sensing image according to claim 1, wherein the first image and the second image are spliced according to the following steps:
forming a first sub-image by using the minimum external rectangle of the three connected domains corresponding to the triangle I; forming a second sub-image by using the minimum external rectangles of the three connected domains corresponding to any one triangle III, and sequentially acquiring a plurality of second sub-images;
acquiring a second sub-image superposed with the first sub-image according to the number of pixels in three connected domains in the first sub-image when the number of pixels in the three connected domains is superposed with each second sub-image;
and splicing the first image and the second image based on a triangle positioning mode according to a triangle III corresponding to the second subimage superposed with the first subimage and a triangle I corresponding to the first subimage.
6. The method for estimating the yield of edible fungi based on the unmanned aerial vehicle remote sensing image according to claim 5, wherein the second sub-image which is coincident with the first sub-image is obtained according to the following steps:
acquiring the coincidence probability of the first sub-image and each second sub-image according to the number of the pixel points in the three connected domains in the first sub-image and the number of the pixel points in the non-coincident connected domains when the number of the pixel points in the three connected domains in the first sub-image is overlapped with each second sub-image;
and acquiring second sub-images coincident with the first sub-images according to the coincidence probability of the first sub-images and each second sub-image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170765.0A CN115294482B (en) | 2022-09-26 | 2022-09-26 | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170765.0A CN115294482B (en) | 2022-09-26 | 2022-09-26 | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115294482A CN115294482A (en) | 2022-11-04 |
| CN115294482B true CN115294482B (en) | 2022-12-20 |
Family
ID=83834629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211170765.0A Active CN115294482B (en) | 2022-09-26 | 2022-09-26 | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115294482B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601670B (en) * | 2022-12-12 | 2023-03-24 | 合肥恒宝天择智能科技有限公司 | Pine wood nematode disease monitoring method based on artificial intelligence and high-resolution remote sensing image |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093456A (en) * | 2012-12-25 | 2013-05-08 | 北京农业信息技术研究中心 | Corn ear character index computing method based on images |
| CN104252705A (en) * | 2014-09-30 | 2014-12-31 | 中安消技术有限公司 | Method and device for splicing images |
| CN106127690A (en) * | 2016-07-06 | 2016-11-16 | 李长春 | A kind of quick joining method of unmanned aerial vehicle remote sensing image |
| CN110569786A (en) * | 2019-09-06 | 2019-12-13 | 中国农业科学院农业资源与农业区划研究所 | fruit tree identification and quantity monitoring method and system based on unmanned aerial vehicle data acquisition |
| CN111815014A (en) * | 2020-05-18 | 2020-10-23 | 浙江大学 | Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information |
| CN113554675A (en) * | 2021-07-19 | 2021-10-26 | 贵州师范大学 | Edible fungus yield estimation method based on unmanned aerial vehicle visible light remote sensing |
| WO2022016563A1 (en) * | 2020-07-23 | 2022-01-27 | 南京科沃信息技术有限公司 | Ground monitoring system for plant-protection unmanned aerial vehicle, and monitoring method for same |
| CN114240758A (en) * | 2021-12-24 | 2022-03-25 | 柳州市侗天湖农业生态旅游投资有限责任公司 | Mountain tea garden low-altitude image splicing method taking quadrilateral plots as reference objects |
| CN114663789A (en) * | 2022-03-29 | 2022-06-24 | 浙江奥脉特智能科技有限公司 | Power transmission line unmanned aerial vehicle aerial image splicing method |
| CN114926332A (en) * | 2022-04-21 | 2022-08-19 | 上海赫千电子科技有限公司 | Unmanned aerial vehicle panoramic image splicing method based on unmanned aerial vehicle mother vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106356757B (en) * | 2016-08-11 | 2018-03-20 | 河海大学常州校区 | A kind of power circuit unmanned plane method for inspecting based on human-eye visual characteristic |
-
2022
- 2022-09-26 CN CN202211170765.0A patent/CN115294482B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093456A (en) * | 2012-12-25 | 2013-05-08 | 北京农业信息技术研究中心 | Corn ear character index computing method based on images |
| CN104252705A (en) * | 2014-09-30 | 2014-12-31 | 中安消技术有限公司 | Method and device for splicing images |
| CN106127690A (en) * | 2016-07-06 | 2016-11-16 | 李长春 | A kind of quick joining method of unmanned aerial vehicle remote sensing image |
| CN110569786A (en) * | 2019-09-06 | 2019-12-13 | 中国农业科学院农业资源与农业区划研究所 | fruit tree identification and quantity monitoring method and system based on unmanned aerial vehicle data acquisition |
| CN111815014A (en) * | 2020-05-18 | 2020-10-23 | 浙江大学 | Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information |
| WO2022016563A1 (en) * | 2020-07-23 | 2022-01-27 | 南京科沃信息技术有限公司 | Ground monitoring system for plant-protection unmanned aerial vehicle, and monitoring method for same |
| CN113554675A (en) * | 2021-07-19 | 2021-10-26 | 贵州师范大学 | Edible fungus yield estimation method based on unmanned aerial vehicle visible light remote sensing |
| CN114240758A (en) * | 2021-12-24 | 2022-03-25 | 柳州市侗天湖农业生态旅游投资有限责任公司 | Mountain tea garden low-altitude image splicing method taking quadrilateral plots as reference objects |
| CN114663789A (en) * | 2022-03-29 | 2022-06-24 | 浙江奥脉特智能科技有限公司 | Power transmission line unmanned aerial vehicle aerial image splicing method |
| CN114926332A (en) * | 2022-04-21 | 2022-08-19 | 上海赫千电子科技有限公司 | Unmanned aerial vehicle panoramic image splicing method based on unmanned aerial vehicle mother vehicle |
Non-Patent Citations (3)
| Title |
|---|
| Melon yield prediction using small unmanned aerial vehicles;Tiebiao Zhao等;《 Proceedings of the SPIE》;20170531;全文 * |
| 基于点特征检测的农业航空遥感图像配准算法;陆健强等;《农业工程学报》;20200208(第03期);全文 * |
| 无人机遥感影像拼接技术的研究;陈小青;《中国硕士学位论文全文数据库》;20220415;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115294482A (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020103026A4 (en) | A Single Tree Crown Segmentation Algorithm Based on Super-pixels and Topological Features in Aerial Images | |
| CN109785379B (en) | Method and system for measuring size and weight of symmetrical object | |
| CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
| CN109584281B (en) | Overlapping particle layering counting method based on color image and depth image | |
| CN106485655A (en) | A kind of taken photo by plane map generation system and method based on quadrotor | |
| CN112131946B (en) | Automatic extraction method for vegetation and water information of optical remote sensing image | |
| CN105335973A (en) | Visual processing method for strip steel processing production line | |
| CN112418188A (en) | Crop growth whole-course digital assessment method based on unmanned aerial vehicle vision | |
| Karkee et al. | A method for three-dimensional reconstruction of apple trees for automated pruning | |
| CN107527328A (en) | A kind of unmanned plane image geometry processing method for taking into account precision and speed | |
| CN109919088B (en) | Automatic extraction method for identifying individual plants of pitaya in karst region | |
| CN115294482B (en) | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image | |
| CN114708208B (en) | Machine vision-based famous tea tender bud identification and picking point positioning method | |
| CN103700110B (en) | Full-automatic image matching method | |
| CN116309670B (en) | Bush coverage measuring method based on unmanned aerial vehicle | |
| CN112395984A (en) | Method for detecting seedling guide line of unmanned agricultural machine | |
| CN111487643A (en) | Building detection method based on laser radar point cloud and near-infrared image | |
| Yin et al. | Individual tree parameters estimation for chinese fir (cunninghamia lanceolate (lamb.) hook) plantations of south china using UAV Oblique Photography: Possibilities and Challenges | |
| CN115760885B (en) | High-closure-degree wetland forest parameter extraction method based on consumer-level unmanned aerial vehicle image | |
| CN116721344A (en) | Vegetation detection method, device and equipment based on aerial photographing equipment | |
| CN114782455B (en) | Cotton row center line image extraction method for agricultural machine embedded equipment | |
| CN114240758B (en) | Mountain tea garden low-altitude image splicing method taking quadrilateral plots as reference objects | |
| CN115035423B (en) | Hybrid rice parent and parent identification extraction method based on unmanned aerial vehicle remote sensing image | |
| CN116385477A (en) | Tower image registration method based on image segmentation | |
| CN115631136A (en) | 3D point cloud image-based method for rapidly measuring phenotypic parameters of schima superba seedlings |
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 |