CN118266424A - Method, device and equipment for separating flea larvae of macrobrachium rosenbergii - Google Patents
Method, device and equipment for separating flea larvae of macrobrachium rosenbergii Download PDFInfo
- Publication number
- CN118266424A CN118266424A CN202410688306.4A CN202410688306A CN118266424A CN 118266424 A CN118266424 A CN 118266424A CN 202410688306 A CN202410688306 A CN 202410688306A CN 118266424 A CN118266424 A CN 118266424A
- Authority
- CN
- China
- Prior art keywords
- dimensional model
- characteristic
- flea
- feature points
- larvae
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 241001327110 Macrobrachium rosenbergii Species 0.000 title claims abstract description 32
- 238000010586 diagram Methods 0.000 claims abstract description 100
- 238000012545 processing Methods 0.000 claims abstract description 65
- 230000029052 metamorphosis Effects 0.000 claims abstract description 54
- 238000000926 separation method Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 23
- 238000003709 image segmentation Methods 0.000 claims abstract description 15
- 238000013450 outlier detection Methods 0.000 claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims description 19
- 239000000178 monomer Substances 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 238000004040 coloring Methods 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 3
- 238000011534 incubation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000013505 freshwater Substances 0.000 claims 3
- 238000000280 densification Methods 0.000 claims 2
- 241000238557 Decapoda Species 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 description 8
- 238000009395 breeding Methods 0.000 description 3
- 230000001488 breeding effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010612 desalination reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/90—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/50—Culture of aquatic animals of shellfish
- A01K61/59—Culture of aquatic animals of shellfish of crustaceans, e.g. lobsters or shrimps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Zoology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marine Sciences & Fisheries (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biodiversity & Conservation Biology (AREA)
- Animal Husbandry (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of separation of young shrimps, in particular to a method, a device and equipment for separating flea larvae of macrobrachium rosenbergii. Collecting an area image of the target flea larvae, and carrying out image segmentation processing on the area image based on an area growth algorithm; performing feature extraction processing on a single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points; and identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool, so that the metamorphosis flea larvae which are successful and the metamorphosis flea larvae which are not successful can be accurately identified and distinguished, and the automatic separation process is realized.
Description
Technical Field
The invention relates to the technical field of separation of young shrimps, in particular to a method, a device and equipment for separating flea larvae of macrobrachium rosenbergii.
Background
In the breeding process of the macrobrachium rosenbergii fries, flea larvae just hatched cannot normally swim and can only move irregularly by water flow. Flea larvae can be completely transformed after about 20 days, and can swim normally like shrimps, but the transformation time of each shrimp is asynchronous. During the breeding process, it is necessary to separate the metamorphosed flea larvae from the non-metamorphosed larvae (which are not very different in weight). After flea larvae which are deformed successfully are separated, desalination treatment is performed in time, and normal cultivation can be performed in a pond, so that a large amount of resources can be saved, and economic benefit is improved. Therefore, the method has important significance for separating and screening flea larvae in the breeding process and has decisive effect for the subsequent growth and development of the macrobrachium rosenbergii. At present, many separation processes rely on manual identification, which is not only inefficient, but also susceptible to factors such as operator fatigue, inattention, etc., and cannot accurately distinguish flea larvae at different stages of development.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method, a device and equipment for separating flea larvae of macrobrachium rosenbergii.
The technical scheme adopted by the invention for achieving the purpose is as follows:
The first aspect of the invention discloses a method for separating macrobrachium rosenbergii flea larvae, comprising the steps of:
collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
Performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
And identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
Further, in a preferred embodiment of the present invention, an area image of the target flea larvae is collected, and image segmentation processing is performed on the area image based on an area growth algorithm, so as to obtain a monomer image of the target flea larvae after removing the background, which specifically includes:
Collecting an area image of a target flea larva, introducing an area growth algorithm, and presetting a plurality of seed points in the area image;
defining a plurality of seed point preset range areas as sub-growth areas, and acquiring pixel points in each sub-growth area; for each sub-growth area, calculating cosine similarity between each pixel point and each seed point based on a cosine similarity algorithm to obtain cosine similarity between each seed point and each pixel point in each sub-growth area;
for each sub-growth area, comparing the cosine similarity between the seed point and each pixel point with a preset similarity threshold; reserving pixels with cosine similarity larger than a preset similarity threshold, and removing pixels with cosine similarity not larger than the preset similarity threshold to obtain a new sub-growth area;
The new sub-growing areas are combined to obtain a monomer image of the target flea larvae after removal of the background.
Further, in a preferred embodiment of the present invention, feature extraction processing is performed on the monomer image of the target flea-shaped larva to obtain a plurality of feature points, and outlier detection and dense processing are performed on the feature points to obtain dense feature points, and an actual three-dimensional model diagram of the target flea-shaped larva is constructed based on the dense feature points, which specifically includes:
Performing feature extraction processing on the single image of the target flea larvae to obtain a plurality of feature points; introducing an isolated forest algorithm, constructing a plurality of binary trees, generating a plurality of feature segmentation points according to the feature points, segmenting each binary tree based on the feature segmentation points, and segmenting each binary tree to obtain a plurality of leaf nodes;
After each segmentation, counting the number of characteristic points in each leaf node in each binary tree, and stopping the segmentation of the binary tree if repeated characteristic points do not exist in each leaf node in a certain binary tree, so as to obtain a binary tree with segmented structure;
Repeating the steps until all binary trees are segmented, and obtaining binary trees with all segmented binary trees; calculating Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree to obtain Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree;
Summing the Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, and then taking an average value to obtain the average Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, so as to obtain the outlier score of each characteristic point;
Screening out feature points with outlier scores larger than a preset outlier score to obtain evacuation feature points, and performing dense processing on the evacuation feature points to obtain dense feature points; acquiring point cloud data of the densely distributed feature points, and constructing a point cloud model according to the point cloud data of the densely distributed feature points; and performing gridding treatment on the point cloud model to obtain an actual three-dimensional model diagram of the target flea larvae.
Further, in a preferred embodiment of the present invention, the dense processing is performed on the evacuation feature points to obtain dense feature points, which specifically includes:
constructing a three-dimensional coordinate system, and mapping the evacuation feature points into the three-dimensional coordinate system; acquiring three-dimensional coordinate values of each evacuation characteristic point in the three-dimensional coordinate system;
for any one evacuation feature point, calculating the mahalanobis distance between the evacuation feature point and each other evacuation feature point, and constructing a distance matrix according to the calculated mahalanobis distance; repeating the steps until all the evacuation feature points are calculated, and obtaining a plurality of distance matrixes;
Screening out the shortest Mahalanobis distance from each distance matrix, and obtaining evacuation characteristic point pairs corresponding to the shortest Mahalanobis distance to obtain a plurality of pairs of evacuation characteristic point pairs;
calculating the median coordinate point of each pair of evacuation feature points according to the three-dimensional coordinate values of each evacuation feature point to obtain a plurality of median coordinate points, and converging each median coordinate point with the evacuation feature points to obtain a plurality of densely distributed feature points.
Further, in a preferred embodiment of the present invention, the degree of overlap between the actual three-dimensional model map and the characteristic three-dimensional model map is calculated, specifically:
Acquiring an actual three-dimensional model image of the target flea larvae, and acquiring a characteristic three-dimensional model image of the metamorphosis flea larvae in the knowledge graph;
Importing the actual three-dimensional model image and the characteristic three-dimensional model image into coloring software to perform coloring treatment to obtain a colored actual three-dimensional model image and a characteristic three-dimensional model image; wherein, the actual three-dimensional model graph after coloring is different from the model color of the characteristic three-dimensional model graph;
Constructing a virtual space, inputting the colored actual three-dimensional model image and the characteristic three-dimensional model image into the virtual space, and carrying out alignment treatment on the colored actual three-dimensional model image and the characteristic three-dimensional model image based on an iterative nearest point algorithm to obtain a fused three-dimensional model image;
Analyzing the fusion three-dimensional model diagram in the virtual space, calculating the volume value of a model region with two model colors in the fusion three-dimensional model diagram, and defining the volume value as a first volume value; calculating the volume value of a model region with only one model color in the fusion three-dimensional model graph, and defining the volume value as a second volume value;
And carrying out ratio processing on the second volume value and the first volume value to obtain the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram.
Further, in a preferred embodiment of the present invention, the target flea-shaped larvae are identified according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is an metamorphosis-successful flea-shaped larvae, the separating device is controlled to separate the metamorphosis-successful flea-shaped larvae in the cultivation pool, specifically:
Presetting an overlapping degree threshold value, and comparing the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram with the preset overlapping degree threshold value;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is larger than a preset overlapping degree threshold value, marking the target flea larvae as metamorphosis success flea larvae;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is not greater than a preset overlapping degree threshold, marking the target flea larvae as unsuccessful flea larvae;
If the target flea larvae are metamorphosis-successful flea larvae, the separating device is controlled to separate metamorphosis-successful flea larvae in the incubation pool.
In a second aspect the invention discloses a device for separating giant freshwater prawn flea larvae, the device comprising a memory and a processor, the memory storing a method program for separating giant freshwater prawn flea larvae, the method program for separating giant freshwater prawn flea larvae, when executed by the processor, effecting the steps of:
collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
Performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
And identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
In a third aspect, the invention discloses an apparatus for separating giant freshwater prawn flea larvae comprising:
and the camera module: collecting an area image of the target flea larvae;
A first processing module: image segmentation processing is carried out on the regional image based on a regional growth algorithm, so that a monomer image of the target flea larvae with the background removed is obtained;
And a second processing module: performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
And a storage module: acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
and an identification module: identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram;
And a separation module: if the identification result is metamorphosis flea larvae, the separation device is controlled to separate metamorphosis flea larvae in the cultivation pool.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: collecting an area image of the target flea larvae, and carrying out image segmentation processing on the area image based on an area growth algorithm; performing feature extraction processing on a single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points; and identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool. By utilizing image processing and feature recognition technology, flea larvae which are successful and unsuccessful in metamorphosis are accurately identified and distinguished, so that an automatic separation process is realized, the efficiency of separating the flea larvae of the macrobrachium rosenbergii can be greatly improved, the time and labor cost of manual operation are reduced, the cultivation benefit of the macrobrachium rosenbergii is improved, and the economic benefit is increased.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a first process flow diagram of a method for separating Macrobrachium rosenbergii flea larvae;
FIG. 2 is a second process flow diagram of a method for separating macrobrachium rosenbergii flea larvae;
FIG. 3 is a third process flow diagram of a method for separating Macrobrachium rosenbergii flea larvae.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, a first aspect of the present invention discloses a method for separating macrobrachium rosenbergii flea larvae, comprising the steps of:
s102: collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
s104: performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
s106: acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
S108: and identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
Further, in a preferred embodiment of the present invention, an area image of the target flea larvae is collected, and image segmentation processing is performed on the area image based on an area growth algorithm, so as to obtain a monomer image of the target flea larvae after removing the background, which specifically includes:
Collecting an area image of a target flea larva, introducing an area growth algorithm, and presetting a plurality of seed points in the area image;
defining a plurality of seed point preset range areas as sub-growth areas, and acquiring pixel points in each sub-growth area; for each sub-growth area, calculating cosine similarity between each pixel point and each seed point based on a cosine similarity algorithm to obtain cosine similarity between each seed point and each pixel point in each sub-growth area;
for each sub-growth area, comparing the cosine similarity between the seed point and each pixel point with a preset similarity threshold; reserving pixels with cosine similarity larger than a preset similarity threshold, and removing pixels with cosine similarity not larger than the preset similarity threshold to obtain a new sub-growth area;
The new sub-growing areas are combined to obtain a monomer image of the target flea larvae after removal of the background.
It is noted that first, one or more seed points need to be selected, which are located in the flea-like juvenile body or in the background. The selection of seed points may be manual or automatic, such as by thresholding or other image segmentation techniques. And defining a plurality of seed point preset range areas as sub-growth areas, calculating cosine similarity between each pixel point and the seed point, reserving the pixel points with the cosine similarity being larger than a preset similarity threshold in the corresponding sub-growth areas, removing the pixel points with the cosine similarity being not larger than the preset similarity threshold in the corresponding sub-growth areas to obtain new sub-growth areas, and merging the new sub-growth areas to obtain the monomer image of the target flea larvae with the background removed. Compared with global threshold segmentation, the method has the advantages that global analysis is not needed for the whole image, so that the method has lower calculation complexity, the image processing efficiency can be effectively improved, and the separation efficiency is improved; in addition, the method considers local information among pixels, can keep the detail characteristics of flea larvae, and can improve the follow-up modeling accuracy.
As shown in fig. 2, in a further preferred embodiment of the present invention, feature extraction processing is performed on the monomer image of the target flea-shaped larva to obtain a plurality of feature points, and outlier detection and dense processing are performed on the feature points to obtain dense feature points, and an actual three-dimensional model diagram of the target flea-shaped larva is constructed based on the dense feature points, specifically:
S202: performing feature extraction processing on the single image of the target flea larvae to obtain a plurality of feature points; introducing an isolated forest algorithm, constructing a plurality of binary trees, generating a plurality of feature segmentation points according to the feature points, segmenting each binary tree based on the feature segmentation points, and segmenting each binary tree to obtain a plurality of leaf nodes;
s204: after each segmentation, counting the number of characteristic points in each leaf node in each binary tree, and stopping the segmentation of the binary tree if repeated characteristic points do not exist in each leaf node in a certain binary tree, so as to obtain a binary tree with segmented structure;
S206: repeating the steps until all binary trees are segmented, and obtaining binary trees with all segmented binary trees; calculating Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree to obtain Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree;
S208: summing the Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, and then taking an average value to obtain the average Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, so as to obtain the outlier score of each characteristic point;
s210: screening out feature points with outlier scores larger than a preset outlier score to obtain evacuation feature points, and performing dense processing on the evacuation feature points to obtain dense feature points; acquiring point cloud data of the densely distributed feature points, and constructing a point cloud model according to the point cloud data of the densely distributed feature points; and performing gridding treatment on the point cloud model to obtain an actual three-dimensional model diagram of the target flea larvae.
The feature extraction processing can be performed on the single image of the target flea larva according to feature extraction algorithms such as ORB and SIFT to obtain a plurality of feature points. However, due to the defect of the feature extraction algorithm, when feature points in the image are extracted by the feature extraction algorithm, some feature point features are offset or redundant, which is an outlier, for example, noise or interference may exist in the image, and these non-target information is erroneously identified as feature points, thereby becoming the outlier; as another example, feature extraction algorithms are typically designed to be invariant to scale and rotation, but in practical applications, variations in scale and rotation may cause anomalies in the distribution of feature points, thereby creating outliers; therefore, after extracting the characteristic points, further screening out outlier characteristic points through an isolated forest algorithm to obtain evacuation characteristic points, then carrying out dense treatment on the evacuation characteristic points to obtain densely distributed characteristic points, and then constructing an actual three-dimensional model diagram of the target flea larvae by utilizing a point cloud reconstruction mode. The method can obtain the characteristic points with high reliability, so that a high-precision model diagram is reconstructed, and the characteristic form of the target flea larvae can be truly reduced.
As shown in fig. 3, in a further preferred embodiment of the present invention, the evacuating feature points are densely processed to obtain densely distributed feature points, which is specifically:
s302: constructing a three-dimensional coordinate system, and mapping the evacuation feature points into the three-dimensional coordinate system; acquiring three-dimensional coordinate values of each evacuation characteristic point in the three-dimensional coordinate system;
S304: for any one evacuation feature point, calculating the mahalanobis distance between the evacuation feature point and each other evacuation feature point, and constructing a distance matrix according to the calculated mahalanobis distance; repeating the steps until all the evacuation feature points are calculated, and obtaining a plurality of distance matrixes;
S306: screening out the shortest Mahalanobis distance from each distance matrix, and obtaining evacuation characteristic point pairs corresponding to the shortest Mahalanobis distance to obtain a plurality of pairs of evacuation characteristic point pairs;
S308: calculating the median coordinate point of each pair of evacuation feature points according to the three-dimensional coordinate values of each evacuation feature point to obtain a plurality of median coordinate points, and converging each median coordinate point with the evacuation feature points to obtain a plurality of densely distributed feature points.
It should be noted that, because the number of feature points extracted by the feature extraction algorithm is limited, and a part of feature points are outliers, when a three-dimensional model diagram is constructed, the geometric structure of the three-dimensional model is incomplete due to the insufficient number of feature points, details are lacking, the shape of an actual object cannot be accurately reflected, the detailed information on the surface of the three-dimensional model is lost, such as texture, concave-convex, and the like, the sense of reality and visual effect of the model are reduced, and therefore dense processing is required to be performed on the sparse feature points, so that more feature points are obtained.
Further, in a preferred embodiment of the present invention, the degree of overlap between the actual three-dimensional model map and the characteristic three-dimensional model map is calculated, specifically:
Acquiring an actual three-dimensional model image of the target flea larvae, and acquiring a characteristic three-dimensional model image of the metamorphosis flea larvae in the knowledge graph;
Importing the actual three-dimensional model image and the characteristic three-dimensional model image into coloring software to perform coloring treatment to obtain a colored actual three-dimensional model image and a characteristic three-dimensional model image; wherein, the actual three-dimensional model graph after coloring is different from the model color of the characteristic three-dimensional model graph;
Constructing a virtual space, inputting the colored actual three-dimensional model image and the characteristic three-dimensional model image into the virtual space, and carrying out alignment treatment on the colored actual three-dimensional model image and the characteristic three-dimensional model image based on an iterative nearest point algorithm to obtain a fused three-dimensional model image;
Analyzing the fusion three-dimensional model diagram in the virtual space, calculating the volume value of a model region with two model colors in the fusion three-dimensional model diagram, and defining the volume value as a first volume value; calculating the volume value of a model region with only one model color in the fusion three-dimensional model graph, and defining the volume value as a second volume value;
And carrying out ratio processing on the second volume value and the first volume value to obtain the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram.
The characteristic three-dimensional model map characterizes the characteristic morphology of the metamorphosis-successful flea larvae. The actual three-dimensional model diagram and the characteristic three-dimensional model diagram can be subjected to coloring treatment through coloring software such as SolidWorks, so that the colored actual three-dimensional model diagram and the characteristic three-dimensional model diagram are obtained, the colored actual three-dimensional model diagram is different from the characteristic three-dimensional model diagram in model color, the colored actual three-dimensional model diagram can be red, and the colored characteristic three-dimensional model diagram is green. In the virtual space, the fused three-dimensional model diagram can be analyzed by combining a triangle splitting method and the like to obtain a first volume value and a second volume value, and the ratio processing is carried out on the second volume value and the first volume value to obtain the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram. The method can rapidly calculate the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, the algorithm is simple and easy to realize, and the recognition efficiency can be effectively improved.
Further, in a preferred embodiment of the present invention, the target flea-shaped larvae are identified according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is an metamorphosis-successful flea-shaped larvae, the separating device is controlled to separate the metamorphosis-successful flea-shaped larvae in the cultivation pool, specifically:
Presetting an overlapping degree threshold value, and comparing the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram with the preset overlapping degree threshold value;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is larger than a preset overlapping degree threshold value, marking the target flea larvae as metamorphosis success flea larvae;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is not greater than a preset overlapping degree threshold, marking the target flea larvae as unsuccessful flea larvae;
If the target flea larvae are metamorphosis-successful flea larvae, the separating device is controlled to separate metamorphosis-successful flea larvae in the incubation pool.
It should be noted that the separation device may be a device such as a manipulator or a grid, and the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram is analyzed, so as to determine whether the target flea larvae are metamorphosis success flea larvae, if the target flea larvae are metamorphosis success flea larvae, the separation device is controlled to timely separate the metamorphosis success flea larvae in the cultivation pool, desalination is timely performed, and normal cultivation is performed in the pond, so that a large amount of resources can be saved, and economic benefit is improved.
In summary, by using the image processing and feature recognition technology, flea larvae which are successful and not successful are accurately recognized and distinguished, so that an automatic separation process is realized, the separation efficiency of the flea larvae of the macrobrachium rosenbergii can be greatly improved, the time and labor cost of manual operation are reduced, the cultivation benefit of the macrobrachium rosenbergii is improved, and the economic benefit is increased.
In a second aspect the invention discloses a device for separating giant freshwater prawn flea larvae, the device comprising a memory and a processor, the memory storing a method program for separating giant freshwater prawn flea larvae, the method program for separating giant freshwater prawn flea larvae, when executed by the processor, effecting the steps of:
collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
Performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
And identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
In a third aspect, the invention discloses an apparatus for separating giant freshwater prawn flea larvae comprising:
and the camera module: collecting an area image of the target flea larvae;
A first processing module: image segmentation processing is carried out on the regional image based on a regional growth algorithm, so that a monomer image of the target flea larvae with the background removed is obtained;
And a second processing module: performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
And a storage module: acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
and an identification module: identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram;
And a separation module: if the identification result is metamorphosis flea larvae, the separation device is controlled to separate metamorphosis flea larvae in the cultivation pool.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. A method for separating macrobrachium rosenbergii flea larvae comprising the steps of:
collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
Performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
And identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
2. The method for separating flea larvae of macrobrachium rosenbergii according to claim 1, wherein the method comprises the steps of collecting regional images of the target flea larvae, and performing image segmentation processing on the regional images based on a regional growth algorithm to obtain monomer images of the target flea larvae after background removal, wherein the method comprises the steps of:
Collecting an area image of a target flea larva, introducing an area growth algorithm, and presetting a plurality of seed points in the area image;
defining a plurality of seed point preset range areas as sub-growth areas, and acquiring pixel points in each sub-growth area; for each sub-growth area, calculating cosine similarity between each pixel point and each seed point based on a cosine similarity algorithm to obtain cosine similarity between each seed point and each pixel point in each sub-growth area;
for each sub-growth area, comparing the cosine similarity between the seed point and each pixel point with a preset similarity threshold; reserving pixels with cosine similarity larger than a preset similarity threshold, and removing pixels with cosine similarity not larger than the preset similarity threshold to obtain a new sub-growth area;
The new sub-growing areas are combined to obtain a monomer image of the target flea larvae after removal of the background.
3. The method for separating flea larvae of macrobrachium rosenbergii according to claim 1, wherein the feature extraction processing is performed on the single image of the target flea larvae to obtain a plurality of feature points, the outlier detection and the densification processing are performed on the feature points to obtain densely distributed feature points, and an actual three-dimensional model diagram of the target flea larvae is constructed based on the densely distributed feature points, specifically:
Performing feature extraction processing on the single image of the target flea larvae to obtain a plurality of feature points; introducing an isolated forest algorithm, constructing a plurality of binary trees, generating a plurality of feature segmentation points according to the feature points, segmenting each binary tree based on the feature segmentation points, and segmenting each binary tree to obtain a plurality of leaf nodes;
After each segmentation, counting the number of characteristic points in each leaf node in each binary tree, and stopping the segmentation of the binary tree if repeated characteristic points do not exist in each leaf node in a certain binary tree, so as to obtain a binary tree with segmented structure;
Repeating the steps until all binary trees are segmented, and obtaining binary trees with all segmented binary trees; calculating Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree to obtain Euclidean distance between each characteristic point and the characteristic cutting point in each cut binary tree;
Summing the Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, and then taking an average value to obtain the average Euclidean distance between each characteristic point and the characteristic segmentation point in each segmented binary tree, so as to obtain the outlier score of each characteristic point;
Screening out feature points with outlier scores larger than a preset outlier score to obtain evacuation feature points, and performing dense processing on the evacuation feature points to obtain dense feature points; acquiring point cloud data of the densely distributed feature points, and constructing a point cloud model according to the point cloud data of the densely distributed feature points; and performing gridding treatment on the point cloud model to obtain an actual three-dimensional model diagram of the target flea larvae.
4. A method for separating giant freshwater prawn flea larvae according to claim 3, characterized in that the evacuating characteristic points are subjected to a densification process to obtain densely packed characteristic points, in particular:
constructing a three-dimensional coordinate system, and mapping the evacuation feature points into the three-dimensional coordinate system; acquiring three-dimensional coordinate values of each evacuation characteristic point in the three-dimensional coordinate system;
for any one evacuation feature point, calculating the mahalanobis distance between the evacuation feature point and each other evacuation feature point, and constructing a distance matrix according to the calculated mahalanobis distance; repeating the steps until all the evacuation feature points are calculated, and obtaining a plurality of distance matrixes;
Screening out the shortest Mahalanobis distance from each distance matrix, and obtaining evacuation characteristic point pairs corresponding to the shortest Mahalanobis distance to obtain a plurality of pairs of evacuation characteristic point pairs;
calculating the median coordinate point of each pair of evacuation feature points according to the three-dimensional coordinate values of each evacuation feature point to obtain a plurality of median coordinate points, and converging each median coordinate point with the evacuation feature points to obtain a plurality of densely distributed feature points.
5. A method for separating giant freshwater prawn flea larvae according to claim 1, characterized in that the degree of overlap between the actual three-dimensional model map and the characteristic three-dimensional model map is calculated, in particular:
Acquiring an actual three-dimensional model image of the target flea larvae, and acquiring a characteristic three-dimensional model image of the metamorphosis flea larvae in the knowledge graph;
Importing the actual three-dimensional model image and the characteristic three-dimensional model image into coloring software to perform coloring treatment to obtain a colored actual three-dimensional model image and a characteristic three-dimensional model image; wherein, the actual three-dimensional model graph after coloring is different from the model color of the characteristic three-dimensional model graph;
Constructing a virtual space, inputting the colored actual three-dimensional model image and the characteristic three-dimensional model image into the virtual space, and carrying out alignment treatment on the colored actual three-dimensional model image and the characteristic three-dimensional model image based on an iterative nearest point algorithm to obtain a fused three-dimensional model image;
Analyzing the fusion three-dimensional model diagram in the virtual space, calculating the volume value of a model region with two model colors in the fusion three-dimensional model diagram, and defining the volume value as a first volume value; calculating the volume value of a model region with only one model color in the fusion three-dimensional model graph, and defining the volume value as a second volume value;
And carrying out ratio processing on the second volume value and the first volume value to obtain the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram.
6. The method for separating flea larvae of macrobrachium rosenbergii according to claim 1, wherein the target flea larvae are identified according to the degree of overlap between the actual three-dimensional model image and the characteristic three-dimensional model image, and if the identification result is an metamorphosis success flea larvae, the separating device is controlled to separate the metamorphosis success flea larvae in the cultivation pond, specifically:
Presetting an overlapping degree threshold value, and comparing the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram with the preset overlapping degree threshold value;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is larger than a preset overlapping degree threshold value, marking the target flea larvae as metamorphosis success flea larvae;
If the overlapping degree between the actual three-dimensional model image and the characteristic three-dimensional model image is not greater than a preset overlapping degree threshold, marking the target flea larvae as unsuccessful flea larvae;
If the target flea larvae are metamorphosis-successful flea larvae, the separating device is controlled to separate metamorphosis-successful flea larvae in the incubation pool.
7. An apparatus for separating giant freshwater fleas larvae, the apparatus comprising a memory and a processor, the memory having stored therein a method program for separating giant freshwater fleas larvae, the method program for separating giant freshwater fleas larvae, when executed by the processor, effecting the steps of:
collecting an area image of the target flea-shaped larva, and performing image segmentation processing on the area image based on an area growth algorithm to obtain a single image of the target flea-shaped larva after the background is removed;
Performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
And identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram, and if the identification result is the metamorphosis flea larvae, controlling the separation equipment to separate the metamorphosis flea larvae in the cultivation pool.
8. An apparatus for separating giant freshwater prawn fleas larvae, the apparatus for separating giant freshwater prawn fleas comprising:
and the camera module: collecting an area image of the target flea larvae;
A first processing module: image segmentation processing is carried out on the regional image based on a regional growth algorithm, so that a monomer image of the target flea larvae with the background removed is obtained;
And a second processing module: performing feature extraction processing on the single image of the target flea-shaped larva to obtain a plurality of feature points, performing outlier detection and dense processing on the feature points to obtain densely distributed feature points, and constructing an actual three-dimensional model diagram of the target flea-shaped larva based on the densely distributed feature points;
And a storage module: acquiring a characteristic three-dimensional model diagram of the metamorphosis success flea larvae based on a big data network, constructing a knowledge graph, and importing the characteristic three-dimensional model diagram of the metamorphosis success flea larvae into the knowledge graph;
and an identification module: identifying the target flea larvae according to the overlapping degree between the actual three-dimensional model diagram and the characteristic three-dimensional model diagram;
And a separation module: if the identification result is metamorphosis flea larvae, the separation device is controlled to separate metamorphosis flea larvae in the cultivation pool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410688306.4A CN118266424B (en) | 2024-05-30 | 2024-05-30 | Method, device and equipment for separating flea larvae of macrobrachium rosenbergii |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410688306.4A CN118266424B (en) | 2024-05-30 | 2024-05-30 | Method, device and equipment for separating flea larvae of macrobrachium rosenbergii |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118266424A true CN118266424A (en) | 2024-07-02 |
| CN118266424B CN118266424B (en) | 2024-08-13 |
Family
ID=91640390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410688306.4A Active CN118266424B (en) | 2024-05-30 | 2024-05-30 | Method, device and equipment for separating flea larvae of macrobrachium rosenbergii |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118266424B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118566083A (en) * | 2024-08-05 | 2024-08-30 | 广东省农业科学院蚕业与农产品加工研究所 | Mulberry threshing effect and threshing granularity detection method, device and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109258531A (en) * | 2018-09-10 | 2019-01-25 | 戴大喜 | A kind of screening technique of Luo pond crayfish fries |
| CN110633711A (en) * | 2019-09-09 | 2019-12-31 | 长沙理工大学 | Computer device and method for training feature point detector and feature point detection method |
| CN111080685A (en) * | 2019-12-17 | 2020-04-28 | 北京工业大学 | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision |
| CN111540049A (en) * | 2020-04-28 | 2020-08-14 | 华北科技学院 | Geological information identification and extraction system and method |
| CN112258390A (en) * | 2020-09-10 | 2021-01-22 | 华中师范大学 | High-precision microscopic virtual learning resource generation method |
-
2024
- 2024-05-30 CN CN202410688306.4A patent/CN118266424B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109258531A (en) * | 2018-09-10 | 2019-01-25 | 戴大喜 | A kind of screening technique of Luo pond crayfish fries |
| CN110633711A (en) * | 2019-09-09 | 2019-12-31 | 长沙理工大学 | Computer device and method for training feature point detector and feature point detection method |
| CN111080685A (en) * | 2019-12-17 | 2020-04-28 | 北京工业大学 | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision |
| CN111540049A (en) * | 2020-04-28 | 2020-08-14 | 华北科技学院 | Geological information identification and extraction system and method |
| CN112258390A (en) * | 2020-09-10 | 2021-01-22 | 华中师范大学 | High-precision microscopic virtual learning resource generation method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118566083A (en) * | 2024-08-05 | 2024-08-30 | 广东省农业科学院蚕业与农产品加工研究所 | Mulberry threshing effect and threshing granularity detection method, device and equipment |
| CN118566083B (en) * | 2024-08-05 | 2024-10-29 | 广东省农业科学院蚕业与农产品加工研究所 | Mulberry threshing effect and threshing granularity detection method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118266424B (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166145B (en) | Fruit tree leaf growth parameter extraction method and system based on cluster segmentation | |
| CN108960011B (en) | Partially-shielded citrus fruit image identification method | |
| CN104239420B (en) | A kind of video Similarity Match Method based on video finger print | |
| CN118266424B (en) | Method, device and equipment for separating flea larvae of macrobrachium rosenbergii | |
| CN112990103B (en) | String mining secondary positioning method based on machine vision | |
| Buayai et al. | End-to-end automatic berry counting for table grape thinning | |
| CN115797350B (en) | Bridge disease detection method, device, computer equipment and storage medium | |
| CN114092487A (en) | Target fruit instance segmentation method and system | |
| CN111353385A (en) | Pedestrian re-identification method and device based on mask alignment and attention mechanism | |
| CN111161090A (en) | Method, device and system for determining containment column information and storage medium | |
| Armalivia et al. | Automatic counting shrimp larvae based you only look once (YOLO) | |
| CN104573701B (en) | A kind of automatic testing method of Tassel of Corn | |
| CN115098717A (en) | Three-dimensional model retrieval method and device, electronic equipment and storage medium | |
| CN114445691A (en) | Model training method and device, electronic equipment and storage medium | |
| Bailey et al. | Image analysis of weaverbird nests reveals signature weave textures | |
| CN108109125A (en) | Information extracting method and device based on remote sensing images | |
| Lin et al. | A multilevel slicing based coding method for tree detection | |
| CN117635938A (en) | Pepper point cloud segmentation method, equipment, medium and system | |
| CN113516193B (en) | Image processing-based red date defect identification and classification method and device | |
| CN116863390A (en) | Method and system for identifying harmful weeds under complex background of forage grass | |
| CN117095275A (en) | Asset inventory method, system, device and storage medium for data center | |
| CN116071653A (en) | Automatic extraction method for multi-stage branch structure of tree based on natural image | |
| CN114187659A (en) | Posture recognition method for recognizing posture of pig and related product thereof | |
| Lin et al. | Fusion and Inpainting: A Novel Salient Object Detection Network | |
| CN111079792A (en) | Power equipment identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |