CN113313692B - Automatic banana young plant identification and counting method based on aerial visible light image - Google Patents
Automatic banana young plant identification and counting method based on aerial visible light image Download PDFInfo
- Publication number
- CN113313692B CN113313692B CN202110619392.XA CN202110619392A CN113313692B CN 113313692 B CN113313692 B CN 113313692B CN 202110619392 A CN202110619392 A CN 202110619392A CN 113313692 B CN113313692 B CN 113313692B
- Authority
- CN
- China
- Prior art keywords
- subgraph
- banana
- image
- images
- young
- 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
- 241000196324 Embryophyta Species 0.000 title claims abstract description 48
- 235000018290 Musa x paradisiaca Nutrition 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 24
- 240000005561 Musa balbisiana Species 0.000 title 1
- 241000234295 Musa Species 0.000 claims abstract description 48
- 240000000905 Nymphoides indica Species 0.000 claims abstract description 25
- 235000017590 Nymphoides indica Nutrition 0.000 claims abstract description 25
- 238000002372 labelling Methods 0.000 claims abstract description 13
- 238000005520 cutting process Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 6
- 244000157072 Hylocereus undatus Species 0.000 description 4
- 235000018481 Hylocereus undatus Nutrition 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 235000012055 fruits and vegetables Nutrition 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- UHPMCKVQTMMPCG-UHFFFAOYSA-N 5,8-dihydroxy-2-methoxy-6-methyl-7-(2-oxopropyl)naphthalene-1,4-dione Chemical compound CC1=C(CC(C)=O)C(O)=C2C(=O)C(OC)=CC(=O)C2=C1O UHPMCKVQTMMPCG-UHFFFAOYSA-N 0.000 description 1
- 244000241257 Cucumis melo Species 0.000 description 1
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 description 1
- 241000223218 Fusarium Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 235000021015 bananas Nutrition 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/68—Analysis of geometric attributes of symmetry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an automatic banana young plant identification and counting method based on aerial visible light images, which comprises the following steps of S1, collecting the visible light images of banana young plants as original images; s2, performing non-overlapping image clipping on the original image; s3, performing image pretreatment on the sub-images, and marking young banana plants; s4, constructing a Faster-RCNN model, and training the Faster-RCNN model based on the labeling subgraph of the young banana plants; s5, cutting the image to be detected into a subgraph, inputting the subgraph into a trained Faster-RCNN model, and obtaining a subgraph identification image; s6, the sub-image recognition images are spliced into complete images again, and duplicate removal treatment is carried out on the boundary banana young plants to finish counting. The invention not only has high robustness under the variation of the variables such as height, light condition and the like, but also is efficient, greatly reduces the manpower input, and has stronger application and popularization potential.
Description
Technical Field
The invention relates to the field of image recognition and counting of banana young plants, in particular to an automatic banana young plant recognition and counting method based on aerial visible light images.
Background
Since banana crops are perennial herbaceous plants, the banana crops grow rapidly and have more and more bud sucking and proliferation in the coming year, and the quantity of banana plants in the next year is controlled by selecting bud sucking. In addition, most bananas are planted in subtropical and tropical areas, the weather is hot and humid, diseases are easy to propagate and spread, several banana diseases (especially fusarium wilt) have caused serious yield loss in the whole production field, and as diseased plants cannot be effectively cured, the diseased plants can only be removed in time and eliminated to slow down the spread of the diseases. The method has guiding significance for quickly investigating the plant number of the banana garden in time, preventing and controlling diseases of the banana garden, predicting the water, fertilizer and medicine input and output of a manager and the like. The deep learning detection framework based on the Faster RCNN has the advantages of high speed and high precision, and is widely applied to the identification and counting of fruit and vegetable crops in recent years.
The fast-RCNN technology is widely applied to the identification and application industries of melons, fruits and vegetables, for example, nisar and the like propose a dragon fruit counting and yield prediction method thereof, an RGB model (R-G channel) and a YCbCr model (Cr channel) are respectively used for dividing an acquired dragon fruit image, morphological processing is used for carrying out size threshold and shape analysis on the image, whether the number of the dragon fruits in the image is single or 2 adhered in the image is judged through the range of roundness rate, and therefore automatic counting of the dragon fruits is achieved. In the aspect of plant identification, li Zhenbo and the like detect the hydroponic vegetable seedlings by using an improved Faster-RCNN detection model, aiming at the characteristic that the image of the hydroponic vegetable seedlings is tiny and dense, HRNet is adopted as a feature extraction network, information loss in the down sampling process is reduced, and information of small target objects is better reserved, so that better semantic information is provided for regression of subsequent candidate frames in classification. However, the identification of the seedlings of the target crops is performed, the used images have the characteristics of short shooting distance and small number of targets, and the counting of the target crops cannot be performed in a large area. Therefore, the invention provides an automatic banana young plant identification and counting method based on aerial visible light images, which aims to solve the defects in the prior art.
Disclosure of Invention
Aiming at the problems, the invention provides an automatic banana young plant identification and counting method based on aerial visible light images, which solves the technical problems in the prior art, can cut an original image into a plurality of subgraphs in a non-overlapping way, and realizes counting of large-area target crops by combining de-duplication treatment.
In order to achieve the above object, the present invention provides the following solutions: the invention provides an automatic banana young plant identification and counting method based on aerial visible light images, which comprises the following steps:
s1, collecting visible light images of young banana plants as original images;
s2, performing non-overlapping image clipping on the original image to obtain a plurality of subgraphs;
s3, performing image preprocessing on the subgraph, and marking the banana young plants to obtain a banana young plant marking subgraph;
s4, constructing a Faster-RCNN model, and training the Faster-RCNN model based on the labeling subgraph of the young banana plant;
s5, cutting the image to be detected into a subgraph, inputting the subgraph into a trained Faster-RCNN model, and obtaining a subgraph identification image;
s6, the sub-image recognition images are spliced into complete images again, and duplicate removal treatment is carried out on the boundary banana young plants to finish counting.
Preferably, the specific step of S2 non-overlapping image cropping is:
s2.1, creating a plurality of uniform grid vertex coordinates according to the size of the original image;
s2.2, creating a five-dimensional tensor, wherein the five-dimensional tensor is used for storing the cut subgraph, and in the five-dimensional tensor, the front two-dimensional represents the coordinate position of the subgraph in the original image, and the rear three-dimensional represents the information of each subgraph;
and S2.3, cutting the original image, and storing the sub-image data determined by the coordinate values of the upper left corner and the lower right corner of each grid into the five-dimensional tensor.
Preferably, the contrast-limited CLAHE algorithm is applied in the S3 preprocessing to equalize the brightness values of the images in the HSV color space.
Preferably, the specific calculation steps of the deduplication process in S6 are:
s6.1, calculating the coordinates of the central point of the subgraph;
s6.2, traversing and calculating the distance between the center point of the square frame marked by each young banana plant and the edge of the subgraph, setting a first preset distance threshold value and a second preset distance threshold value, and screening out the square frame marked by the edge of the subgraph based on the first preset distance threshold value and the second preset distance threshold value;
s6.3, calculating the area of the sub-image edge labeling square frame, setting an area threshold value, and screening out the labeling square frame of the incomplete banana young plant based on the area threshold value;
s6.4, calculating the center point distance of two adjacent boxes in the marked boxes of the incomplete banana young plants, and identifying the repeated detection condition through a third preset distance threshold.
Preferably, the first preset distance threshold and the second preset distance threshold are both variable thresholds.
Preferably, the setting of the variable threshold is specifically set according to the visible light original image of the aerial altitude.
Preferably, the calculation of the variable threshold is:
wherein, threshold0 is the distance of the current aerial photographing height, threshold1 is the distance threshold of the aerial photographing images of the banana young plants to be counted, Δd0 is the distance of every two banana young plants in the current aerial photographing image subgraph, and Δd1 is the distance of every two banana young plants in the subgraph.
The invention discloses the following technical effects:
according to the invention, images of banana young plants in different light conditions and different shooting heights are obtained in the field by an unmanned plane to construct an original image, aiming at the problem that the number of candidate images generated by the Faster-RCNN frame on an input image is limited, the target crops of target images are reduced by using a processing method of image non-overlapping clipping, and then the number of banana young plants is detected in a large area by adopting a mode of splicing back to a large image. In the sub-graph recognition result, the boundary generated by the sub-graph during interception divides a large number of banana plants into two parts, even four parts. The cross-border banana plants are detected in adjacent subgraphs (boundary repeated identification) respectively, so that the statistical quantity is increased, and larger errors are occupied, therefore, a duplication elimination algorithm is designed, different thresholds are respectively set for the candidate graphs of the young banana plants, and screening, removing and duplication elimination correction are carried out on the candidate graphs with edges, too close distances and too small areas of the subgraphs. The counting method for automatically identifying the young banana plants based on the target detection model of Faster-RCNN has high robustness under the change of variables such as height, light conditions and the like, is efficient and portable, greatly reduces manpower input, can provide relevant technical support for users in aspects such as farm management, yield prediction and the like, and has strong application popularization potential.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is an original image of an 80m aerial photograph acquired by an unmanned aerial vehicle in an embodiment of the present invention;
FIG. 3 is a graph showing the contrast of enhancement effect of equalizing the luminance values of subimages in HSV color space by using the CLAHE algorithm, wherein FIG. 3 (a) is an original subimage and FIG. 3 (b) is an enhanced subimage;
FIG. 4 is a graph showing the comparison of labeling effects of the invention using labelling;
FIG. 5 is a graph showing the effect of errors in repeated identification of banana young plants detected by the method;
FIG. 6 is a schematic diagram of the deduplication process of the present invention;
fig. 7 is a flow chart of the deduplication algorithm of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Referring to fig. 1-7, the embodiment provides an automatic banana young plant identification and counting method based on aerial visible light images, which comprises the following steps:
s1, acquiring a visible light image of a field banana young plant in an aerial photography mode of an unmanned aerial vehicle as an original image, wherein the unmanned aerial vehicle adopts a large-area intelligent phantom4, and the visible light image of the large-area banana young plant is shown in a figure 2;
s2, carrying out non-overlapping image clipping on an original image to obtain a plurality of subgraphs, wherein the method specifically comprises the following steps of:
s2.1, creating (m+1) x (n+1) uniform grid vertex coordinates according to the size of an original image, and performing fine adjustment on the pixel level of the original image by adopting an image scaling method so that the length and the width of the original image can be divided by m and n;
s2.2, storing images by adopting a dimension increasing method, creating a five-dimensional tensor, wherein the five-dimensional tensor is used for storing the cut subgraph, the front two dimensions in the five-dimensional tensor represent the coordinate position (such as the blocks of the ith row and the jth column) of the subgraph in the original image, and the rear three dimensions represent the information (such as the length, the width and the channel number) of each subgraph;
s2.3, clipping the original image by adopting a numpy slicing function, and storing sub-pixel data determined by coordinate values of the upper left corner and the lower right corner of each grid into a five-dimensional tensor.
S3, performing image pretreatment on the sub-map, and marking the young banana plants to obtain a marking sub-map of the young banana plants;
the contrast difference between partial subgraphs is obvious, in order to eliminate the difference between subgraphs, image preprocessing is performed, a contrast-limited self-adaptive histogram equalization algorithm (CLAHE) is applied to equalize the brightness value of the image in the HSV color space, so that the image contrast is enhanced and the image difference caused by the change of ambient illumination is reduced, as shown in fig. 3, the enhancement algorithm has the effect of obviously improving the brightness of a dim subgraph, and meanwhile, a highlight subgraph cannot be overexposed. The processed subgraph is manually marked by a marking tool labellImg, incomplete banana plants appear at the edge part of the subgraph due to grid cutting, and the plants with display pictures exceeding half plants are marked mainly during marking, and a data set image is shown in fig. 4.
S4, constructing a Faster-RCNN model, and training the model based on the labeling subgraph of the young banana plants;
dividing the labeling subgraphs of the young banana plants into data sets according to a training set: test set: validation set = 8:1:1, randomly splitting an original data set, and setting parameters of a model as shown in table 1;
table 1 model training parameters
S5, cutting the image to be detected into a subgraph, inputting the subgraph into a fast-RCNN model after training, and detecting to obtain a subgraph identification image;
s6, the sub-image recognition images are spliced into a complete image again, the splicing principle is that an empty original image is firstly created, then corresponding sub-images are filled in corresponding positions, the sub-images containing recognition results are spliced, so that a user can clearly see the complete recognition results, but if the number is simply counted, only the recognized frames are spliced; repeating the frame selection of banana plants which are divided into two or four in one in the cutting process in the large graph; the duplicate recognition phenomenon is shown in fig. 5, the duplicate removal schematic diagram is shown in fig. 6, the duplicate removal schematic diagram is shown in fig. 7, and finally the counting is completed, and the duplicate removal process specifically comprises:
s6.1, calculating center point coordinates (midx 1, midy 1) of the subgraph based on the grid vertex coordinates:
s6.2, traversing and calculating distances d1 and d2 between a box center point marked by each banana young plant and the edge of the subgraph, setting a first preset distance threshold T1 and a second preset distance threshold T2, and screening out the edge marked box of the subgraph based on the first preset distance threshold T1 and the second preset distance threshold T2, wherein the formula is as follows:
d2＝|midx-2m|；
d1＝|midy-h|；
d1＜T1 and d2＜T2；
where m is the width of the subgraph and h is the height of the subgraph.
The first preset distance threshold value and the second preset distance threshold value are both variable threshold values, the variable threshold values are specifically set according to visible light original images of aerial photo heights, the threshold values selected under the aerial photo heights of 80m at present cannot be compatible with other aerial photo images, so the variable threshold values are designed to meet the accuracy of a subgraph guarantee algorithm under different flight heights, the distance threshold value of the aerial photo heights of 80m at present is set to be threshold0, the distance threshold value of the banana aerial photo images to be counted is input to be threshold1, the distance delta d0 of every two banana young plants in the 80m aerial photo image subgraph is calculated, the distance delta d1 of every two banana young plants in the subgraph is input, and a calculation formula of the new threshold value is as follows:
the threshold0 is the distance of the current aerial photographing height, and the threshold1 is the distance threshold of the aerial photographing images of the young banana plants to be counted.
S6.3, calculating the area of the sub-image edge labeling square frame, setting an area threshold, screening the labeling square frame of the incomplete banana young plant based on the area threshold, wherein the area threshold S is as follows:
s＝(x2-x1)(y2-y1)。
s6.4, calculating the center point distance of two adjacent boxes in the marked boxes of the incomplete banana young plant, and identifying the repeated detection condition through a third preset distance threshold value:
the invention has the following technical effects:
according to the invention, images of banana young plants in different light conditions and different shooting heights are obtained in the field by an unmanned plane to construct an original image, aiming at the problem that the number of candidate images generated by the Faster-RCNN frame on an input image is limited, the target crops of target images are reduced by using a processing method of image non-overlapping clipping, and then the number of banana young plants is detected in a large area by adopting a mode of splicing back to a large image. In the sub-graph recognition result, the boundary generated by the sub-graph during interception divides a large number of banana plants into two parts, even four parts. The cross-border banana plants are detected in adjacent subgraphs (boundary repeated identification) respectively, so that the statistical quantity is increased, and larger errors are occupied, therefore, a duplication elimination algorithm is designed, different thresholds are respectively set for the candidate graphs of the young banana plants, and screening, removing and duplication elimination correction are carried out on the candidate graphs with edges, too close distances and too small areas of the subgraphs. The counting method for automatically identifying the young banana plants based on the target detection model of Faster-RCNN has high robustness under the change of variables such as height, light conditions and the like, is efficient and portable, greatly reduces manpower input, can provide relevant technical support for users in aspects such as farm management, yield prediction and the like, and has strong application popularization potential.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present invention pertains are made without departing from the spirit of the present invention, and all modifications and improvements fall within the scope of the present invention as defined in the appended claims.
Claims (3)
1. The automatic banana young plant identification and counting method based on aerial visible light images is characterized by comprising the following steps of:
s1, collecting visible light images of young banana plants as original images;
s2, performing non-overlapping image clipping on the original image to obtain a plurality of subgraphs;
s3, performing image preprocessing on the subgraph, and marking the banana young plants to obtain a banana young plant marking subgraph;
s4, constructing a Faster-RCNN model, and training the Faster-RCNN model based on the labeling subgraph of the young banana plant;
s5, cutting the image to be detected into a subgraph, inputting the subgraph into a trained Faster-RCNN model, and obtaining a subgraph identification image;
s6, the sub-image recognition images are spliced into complete images again, and duplication elimination treatment is carried out on the boundary banana young plants to finish counting;
calculating center point coordinates (midx 1, midy 1) of the subgraph based on the mesh vertex coordinates:
the first preset distance threshold value and the second preset distance threshold value are both variable threshold values, the variable threshold values are specifically set according to visible light original images of aerial photo heights, the threshold values selected under the aerial photo heights of 80m at present cannot be compatible with other aerial photo images, so the variable threshold values are designed to meet the accuracy of a subgraph guarantee algorithm under different flight heights, the distance threshold value of the aerial photo heights of 80m at present is set to be threshold0, the distance threshold value of the banana aerial photo images to be counted is input to be threshold1, the distance delta d0 of every two banana young plants in the 80m aerial photo image subgraph is calculated, the distance delta d1 of every two banana young plants in the subgraph is input, and a calculation formula of the new threshold value is as follows:
the area of the subgraph edge labeling square frame is calculated, an area threshold is set, the labeling square frame of incomplete banana young plants is screened out based on the area threshold, and the area threshold s is expressed as follows:
s=(x2-x1)(y2-y1)
calculating the distance between the central points of two adjacent boxes in the marked boxes of the incomplete banana young plants, and identifying the repeated detection condition through a third preset distance threshold value:
2. the automatic identification and counting method for young banana plants based on aerial visible light images according to claim 1, wherein the specific steps of S2 non-overlapping image cropping are as follows:
s2.1, creating a plurality of uniform grid vertex coordinates according to the size of the original image;
s2.2, creating a five-dimensional tensor, wherein the five-dimensional tensor is used for storing the cut subgraph, and in the five-dimensional tensor, the front two-dimensional represents the coordinate position of the subgraph in the original image, and the rear three-dimensional represents the information of each subgraph;
and S2.3, cutting the original image, and storing the sub-image data determined by the coordinate values of the upper left corner and the lower right corner of each grid into the five-dimensional tensor.
3. The automatic identification and counting method of banana young plants based on aerial visible light images according to claim 1, wherein a contrast-limited CLAHE algorithm is applied in the S3 preprocessing to equalize the brightness values of the images in HSV color space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110619392.XA CN113313692B (en) | 2021-06-03 | 2021-06-03 | Automatic banana young plant identification and counting method based on aerial visible light image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110619392.XA CN113313692B (en) | 2021-06-03 | 2021-06-03 | Automatic banana young plant identification and counting method based on aerial visible light image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113313692A CN113313692A (en) | 2021-08-27 |
| CN113313692B true CN113313692B (en) | 2023-04-25 |
Family
ID=77377275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110619392.XA Active CN113313692B (en) | 2021-06-03 | 2021-06-03 | Automatic banana young plant identification and counting method based on aerial visible light image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313692B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113888397A (en) * | 2021-10-08 | 2022-01-04 | 云南省烟草公司昆明市公司 | Tobacco pond cleaning and plant counting method based on unmanned aerial vehicle remote sensing and image processing technology |
| CN114742822A (en) * | 2022-05-20 | 2022-07-12 | 青岛农业大学 | Construction method and application of strawberry identification and counting model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327426A (en) * | 2016-08-19 | 2017-01-11 | 携程计算机技术（上海）有限公司 | Image replication removing method and image replication removing system |
| CN111537515A (en) * | 2020-03-31 | 2020-08-14 | 国网辽宁省电力有限公司朝阳供电公司 | Iron tower bolt defect display method and system based on three-dimensional live-action model |
| CN111738159A (en) * | 2020-06-23 | 2020-10-02 | 桂林市思奇通信设备有限公司 | Cotton terminal bud positioning method based on vector calibration |
| CN112017231A (en) * | 2020-08-27 | 2020-12-01 | 中国平安财产保险股份有限公司 | Human body weight identification method and device based on monocular camera and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052984B (en) * | 2017-10-30 | 2019-11-08 | 中国科学院计算技术研究所 | Method of counting and device |
| CN109636824B (en) * | 2018-12-20 | 2022-10-11 | 巢湖学院 | Multi-target counting method based on image recognition technology |
| CN114581801A (en) * | 2019-09-06 | 2022-06-03 | 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 based on unmanned aerial vehicle data acquisition |
| CN111080529A (en) * | 2019-12-23 | 2020-04-28 | 大连理工大学 | Unmanned aerial vehicle aerial image splicing method for enhancing robustness |
-
2021
- 2021-06-03 CN CN202110619392.XA patent/CN113313692B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327426A (en) * | 2016-08-19 | 2017-01-11 | 携程计算机技术（上海）有限公司 | Image replication removing method and image replication removing system |
| CN111537515A (en) * | 2020-03-31 | 2020-08-14 | 国网辽宁省电力有限公司朝阳供电公司 | Iron tower bolt defect display method and system based on three-dimensional live-action model |
| CN111738159A (en) * | 2020-06-23 | 2020-10-02 | 桂林市思奇通信设备有限公司 | Cotton terminal bud positioning method based on vector calibration |
| CN112017231A (en) * | 2020-08-27 | 2020-12-01 | 中国平安财产保险股份有限公司 | Human body weight identification method and device based on monocular camera and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王侨等.基于机器视觉的玉米苗期多条作物行线检测算法.《农业机械学报》.2021,第52卷(第4期),208-220. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113313692A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jia et al. | Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot | |
| CN109961049B (en) | Cigarette brand identification method under complex scene | |
| Scharr et al. | Leaf segmentation in plant phenotyping: a collation study | |
| Maldonado Jr et al. | Automatic green fruit counting in orange trees using digital images | |
| US8340420B2 (en) | Method for recognizing objects in images | |
| CN110569786B (en) | Fruit tree identification and quantity monitoring method and system based on unmanned aerial vehicle data acquisition | |
| US9449253B2 (en) | Learning painting styles for painterly rendering | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN113313692B (en) | Automatic banana young plant identification and counting method based on aerial visible light image | |
| CN110619632A (en) | Mango example confrontation segmentation method based on Mask R-CNN | |
| CN112598713A (en) | Offshore submarine fish detection and tracking statistical method based on deep learning | |
| Alkoffash et al. | A survey of digital image processing techniques in character recognition | |
| CN109685045A (en) | A kind of Moving Targets Based on Video Streams tracking and system | |
| CN112990103B (en) | String mining secondary positioning method based on machine vision | |
| CN109242826B (en) | Mobile equipment end stick-shaped object root counting method and system based on target detection | |
| CN107220647B (en) | Crop center point positioning method and system under blade crossing condition | |
| Lv et al. | A visual identification method for the apple growth forms in the orchard | |
| CN109977899B (en) | Training, reasoning and new variety adding method and system for article identification | |
| CN109740721A (en) | Wheat head method of counting and device | |
| CN114140665A (en) | Dense small target detection method based on improved YOLOv5 | |
| CN111161295A (en) | Background stripping method for dish image | |
| CN115050020A (en) | Intelligent visual detection method and system based on improved Mask R-CNN strawberry leaf area | |
| CN112200854A (en) | Leaf vegetable three-dimensional phenotype measurement method based on video image | |
| Farella et al. | Handling critical aspects in massive photogrammetric digitization of museum assets | |
| CN111738310B (en) | Material classification method, device, electronic equipment and storage medium |
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 |