CN112651462A - Spider classification method and device and classification model construction method and device - Google Patents
Spider classification method and device and classification model construction method and device Download PDFInfo
- Publication number
- CN112651462A CN112651462A CN202110002891.4A CN202110002891A CN112651462A CN 112651462 A CN112651462 A CN 112651462A CN 202110002891 A CN202110002891 A CN 202110002891A CN 112651462 A CN112651462 A CN 112651462A
- Authority
- CN
- China
- Prior art keywords
- spider
- image
- classification
- classification model
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000239290 Araneae Species 0.000 title claims abstract description 130
- 238000013145 classification model Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000010276 construction Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims description 18
- 230000003993 interaction Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003199 nucleic acid amplification method Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 241000238421 Arthropoda Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a spider classification method and device and a classification model construction method and device. The classification model construction method collects a large number of images containing pattern information on the back of the spider, and realizes the construction of the spider classification model based on deep learning identification. Based on the back pattern information, operations such as amplification and the like are not needed, the complexity of identification operation is simplified, the method is suitable for field operation due to the fact that equipment such as an amplifier and the like is not needed, the type of the spider can be pre-judged directly through intelligent portable equipment such as a mobile phone and the like provided with the amplification software, and the collection efficiency of the spider sample in the field can be improved.
Description
Technical Field
The invention belongs to the technical field of spider classification, and particularly relates to a spider classification method and equipment, and a classification model construction method and equipment.
Background
Spiders belong to the order Aranea of the Arabia of the phylum Arthropoda, and are a large group of animals with many species and large quantity. By now, the total known spider species in the world are classified into 128 families, 4173 genus, 48643 species, and there are still a large number of unknown species in the world that have not been discovered and identified. The present invention relates to a method for identifying spider species by using computer image identification technology, and is characterized by that it mainly adopts manual identification or machine identification, and utilizes the identification of spider limb-contacting device, external female device, abdominal bone piece, quantity and position of spinning device and characteristics of book lung to classify spider, for example, the invented patent with application number of CN 202010807451.1. However, the spider species identification using the above method has the following drawbacks: the spiders are classified according to the limb devices and the external female devices, in the image taking process, the limb devices of the spiders need to be detached, image observation and collection can be achieved under an optical microscope, and the observation and the image collection are very troublesome. If a large number of spiders need to be classified, enormous manpower and time are consumed.
Disclosure of Invention
The invention provides a spider classification method, equipment, a classification model construction method and equipment, aiming at solving the problems that image acquisition is complicated, time-consuming and labor-consuming when the existing spider classification is carried out based on a limb touching device and an external female device.
The invention is realized by the following technical scheme:
a spider classification model construction method comprises the following steps:
collecting a spider image, wherein the image contains spider back pattern information;
preprocessing a spider image;
and training a classification model by adopting the preprocessed image.
The inventor finds that the pattern on the back of the spider also records the type information of the spider in long-term research. The method is suitable for a platform end, and classification of spiders is realized on the basis of deep learning identification by acquiring a large number of images containing pattern information on the backs of the spiders. Based on the back pattern information, operations such as amplification and the like are not needed, the complexity of identification operation is simplified, the method is suitable for field operation due to the fact that an optical microscope is not needed, the type of the spider can be judged in advance directly through intelligent portable equipment with a microspur shooting function, such as a mobile phone and a flat panel, and the collection efficiency of the spider sample in the field can be improved.
A spider classification model construction device comprising:
the data storage module is used for storing image data containing the pattern information on the back of the spider and the classification model;
the first data processing module is used for preprocessing image data so that image key information is positioned at the pattern on the back of the spider;
a training module for training a classification model by utilizing the preprocessed image;
and the first data interaction module is used for realizing data interaction with external equipment.
The storage module of the device stores classification models and a large amount of image data, the first data processing module processes images and positions key information of the images at patterns on the back of the spiders so as to improve accuracy of identification training of the types of the spiders, the training module uses the preprocessed images to train the classification models, and the trained classification modules are used as source models of terminal devices. Similarly, the classification model constructed by the scheme can classify the spiders by identifying the pattern information on the backs of the spiders, is convenient to get images, and does not need to solve limbs of the spiders.
A spider classification method comprising the steps of:
acquiring a spider image, wherein the image comprises spider back pattern information;
preprocessing a spider image;
inputting the preprocessed image into the classification model obtained by the method;
and outputting the spider classification result.
The method is suitable for a terminal device, the classification model of the method is a classification model which is trained by an image containing spider back pattern information, the collected spider back image is preprocessed, key information of the image is positioned at the spider back pattern, and the accuracy of spider type identification is improved. The image data after preprocessing is input into the classification model after training is completed, the classification result of the spiders can be output, the limbs of the spiders do not need to be solved in the whole process, the image taking is convenient, and the operation is simple and fast.
A spider classification device comprising:
an image acquisition module for acquiring image data containing pattern information on the back of the spider,
a second data processing module for preprocessing the image data by using the Attention mechanism,
a classification model module for identifying a spider type from the image data,
and a classification result output module for outputting the classification result.
The image acquisition module of the classification equipment acquires image information of the back of the spider, the second data processing module adopts an Attention mechanism to preprocess the image data to enable key image information to be positioned at patterns on the back of the spider, and the classification model module takes the image information as input and outputs classification results to the classification result output module. This classification equipment is suitable for field usage, need not carry out the acrolysis to the spider in the operation process, and image acquisition module can be directly based on current camera commonly used, and easy operation is swift.
A spider classification device comprises an intelligent terminal, and the intelligent terminal is provided with an application adopting the method.
Compared with the prior art, the invention at least has the following advantages and beneficial effects:
1. according to the method and the device for constructing the classification model, the image data containing the pattern information on the back of the spider is used as a training set of the classification model, the classification model with the spider classification function is constructed, the spider limbs are not needed to be separated in the construction process of the image data, the image is not needed to be collected by an optical microscope, the common camera with the microspur shooting function is sampled, the image sampling is convenient and simple, and time and labor are saved.
2. The classification method and the classification equipment have the advantages that the image data containing the pattern information on the back of the spider serves as an identification source, the image taking is carried out in the identification process, the spider limbs are not required to be separated, an optical microscope is not required, the sampling of a common camera is only carried out, the image sampling is convenient and simple, and time and labor are saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a model building method.
FIG. 2 is a flow chart of a spider classification method.
Fig. 3 is a schematic block diagram of the model building apparatus and the classification apparatus.
FIG. 4 is a flow chart of the model building method of the present invention.
Fig. 5 is a thermodynamic diagram of an image without pre-processing.
Fig. 6 is a thermodynamic diagram of an image after preprocessing.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Specific structural and functional details disclosed herein are merely illustrative of example embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It will be understood that when an element is referred to herein as being "connected," "connected," or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Conversely, if a unit is referred to herein as being "directly connected" or "directly coupled" to another unit, it is intended that no intervening units are present. In addition, other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between … …" versus "directly between … …", "adjacent" versus "directly adjacent", etc.).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative designs, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
Example 1
The spider classification model construction method shown in fig. 1 includes the following steps:
the method comprises the steps of collecting a spider image, wherein the image contains spider back pattern information. The pattern image on the back of the spider is easy to collect, so that the pattern image can be directly collected by the image collecting equipment such as the conventional common camera, mobile phone and the like without the help of equipment such as an amplifier and the like. The spider images are used as a training set, the larger the number of the spider images is, the better the spider images are, the larger the number is, and the higher the recognition accuracy of the trained classification model is.
Preprocessing the spider image, and filtering out useless background parts in the image, so that the key information of the image is positioned at the pattern on the back of the spider, and the influence of the background parts on the spider type judgment is reduced. Specifically, the image can be processed by using digital image processing technology or an Attention mechanism. The digital image processing technology can specifically adopt a method combining technologies such as spider morphological analysis, image binarization, image opening and closing operation and the like to realize the positioning of key information of the spider image. However, the method has low positioning accuracy and is easily interfered by factors such as the background and the photographing angle in the image, so that misjudgment is generated. The Attention mechanism is a solution to the problem proposed by imitating human Attention, and simply speaking, high-value information is quickly screened from a large amount of information. The image is processed by adopting an Attention mechanism, so that the key information of the image can be effectively positioned at the back pattern of the spider, the interference of other factors in the image is avoided, the training accuracy of the classification model is improved, and the accuracy of subsequent spider identification is improved.
And training a classification model by adopting the preprocessed image. Specifically, the classification model may adopt a convolutional neural network model, such as a MobileNetV2 network model, an inclusion network model, an Alexnet network model, or the like. Preferably, a convolutional neural network model such as a MobileNetV2 network model is adopted, the model is a lightweight network model, and after the factors such as recognition accuracy, model size and calculation time are considered, the MobileNetV2 network model is a network model more suitable for being used in the field of intelligent equipment such as mobile phones and tablets, so that the hardware requirement on mobile portable intelligent equipment can be reduced, and the field operation time can be shortened. In some indoor laboratories and other occasions, an inclusion network model and an Alexnet network model can be adopted, which can improve the identification accuracy to a certain extent.
After the classification model is constructed by the method, the terminal device performs spider classification based on the trained classification model, and specifically, as shown in fig. 2, the spider classification method includes the following steps:
and acquiring a spider image, wherein the image contains spider back pattern information. Similarly, the pattern image on the back of the spider is easy to collect, and can be directly completed by the image collecting equipment such as the conventional common camera, mobile phone and the like without the help of equipment such as an amplifier and the like.
The spider image is preprocessed, and similarly, the image can be processed by adopting an Attention mechanism or a method combining technologies such as spider morphological analysis, image binarization, image opening and closing operation and the like.
Inputting the preprocessed image into a classification model obtained by training by adopting the method;
and outputting the spider classification result.
Example 2
Based on the principle of the method in the foregoing embodiment, this embodiment discloses a specific implementation, as shown in fig. 4:
the method comprises the steps of collecting a spider image, wherein the image comprises spider back pattern information and background information, and the background information can interfere with classification model training and needs to be filtered. On the other hand, patterns on the abdomen of the spider head may not be fully recognized by the convolutional neural network, thereby causing the spider species to be misjudged. As shown in fig. 5, if the captured spider image is directly input into the MobileNetV2 network model, the convolutional neural network model will be affected by the region a in fig. 5.
And then preprocessing the collected spider images by an Attention mechanism, wherein the preprocessed spider images are shown in fig. 6, the judgment basis is effectively locked at the pattern on the back of the spider, the accuracy of the classification of the spider is greatly improved, and the thermodynamic diagram is shown in fig. 6 and is locked in a B area in the diagram.
And input into a MobileNet V2 network model to train the MobileNet V2 network model.
The MobileNet V2 network model trained based on the method has the classification accuracy rate of more than 95% for spiders.
Example 3
Based on the principle of the method of the embodiment, the embodiment discloses a system which comprises a spider classification model construction device, namely a platform, and a spider classification device, namely an identification terminal, and particularly, the identification terminal can be used independently.
Specifically, as shown in fig. 3, the spider classification module construction device includes a data storage module, a first data processing module, a training module, and a first data interaction module. The data storage module is used for storing image data containing the pattern information of the back of the spider and a classification model, wherein the classification model can be a MobileNet V2 network model. The first data processing module preprocesses the image data to locate the image key information in the spider back pattern, which can preprocess the image using the Attention mechanism in embodiments 1 and 2. And the training module takes the preprocessed images as a training set, trains an original classification model, and takes the trained classification model as a source model of the recognition terminal. The first data interaction module realizes data interaction with external equipment, namely, information interaction with the identification terminal, so that the identification terminal can conveniently download the trained classification model, and the first data interaction module can adopt a wireless data transceiver module, such as a Bluetooth module, a Lora module, a 4G module, a 5G module, a wifi module and the like; wired data transceiver modules such as USB interface, RS232 interface, RS485 interface, etc. may also be used.
The spider classification device, i.e. the identification terminal, can be implemented in a variety of ways:
first, the application program for classifying spiders is solidified when the smart device leaves a factory, the application adopts the classification method in embodiments 1 and 2, and the smart device may be a portable device such as a smart phone, a tablet, a smart band with a camera, and the like.
Secondly, as shown in fig. 3, the recognition terminal includes an image acquisition module, a second data processing module, a classification model module, a classification result output module, and a second data interaction module. The second data interaction module realizes information interaction with external equipment, specifically, trained classification models can be downloaded from a platform end, and interaction of classification results can also be carried out with remote equipment. The image acquisition module is used for acquiring image data containing pattern information on the back of the spider and can adopt a camera. The second data processing module adopts an Attention mechanism to preprocess the image data so as to position the key information of the image on the back pattern of the spider. The classification model module takes the output data of the second data processing module as input and classifies and outputs the spiders. The classification result output module for outputting the classification result may be a voice device, a display device, such as a display, a speaker, an LED lamp, etc.
By adopting the classification equipment of the embodiment, the image information of the back of the spider is collected based on the common camera, the image data is preprocessed through an Attention mechanism, intelligent machine classification is carried out through a MobileNet V2 network model, and the MobileNet V2 neural network of the Attention mechanism is fused, so that the interference of background noise can be better filtered, and meanwhile, the pattern on the back of the spider can be well distinguished. The operation complexity of spider type judgment is greatly simplified, and simultaneously, other electronic equipment such as a mobile phone and the like can be used for pre-judging the spider type in a field acquisition site, so that the hardware and environmental requirements for type identification are reduced, and the field acquisition efficiency of the spider sample is improved.
The embodiments described above are merely illustrative, and may or may not be physically separate, if referring to units illustrated as separate components; if reference is made to a component displayed as a unit, it may or may not be a physical unit, and may be located in one place or distributed over a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications may be made to the embodiments described above, or equivalents may be substituted for some of the features described. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.
Claims (10)
1. A spider classification model construction method is characterized by comprising the following steps:
collecting a spider image, wherein the image contains spider back pattern information;
preprocessing a spider image;
and training a classification model by adopting the preprocessed image.
2. The method for constructing a spider classification model according to claim 1, wherein an Attention mechanism is used to preprocess the spider image.
3. The method of claim 1, wherein the spider classification model is pre-processed using digital image processing techniques.
4. The method of claim 1, wherein the classification model is a convolutional neural network model.
5. The method for constructing the spider classification model according to claim 1, wherein the classification model is an inclusion network model or an Alexnet network model.
6. A spider classification model construction device, comprising:
the data storage module is used for storing image data containing the pattern information on the back of the spider and the classification model;
the first data processing module is used for preprocessing image data so that image key information is positioned at the pattern on the back of the spider;
a training module for training a classification model by utilizing the preprocessed image;
and the first data interaction module is used for realizing data interaction with external equipment.
7. A spider classification method is characterized by comprising the following steps:
acquiring a spider image, wherein the image comprises spider back pattern information;
preprocessing a spider image;
inputting the preprocessed image into a classification model obtained by the method of any one of claims 1-5;
and outputting the spider classification result.
8. A spider classification device, comprising:
an image acquisition module for acquiring image data containing pattern information on the back of the spider,
a second data processing module for preprocessing the image data,
a classification model module for identifying a spider type from the image data,
and a classification result output module for outputting the classification result.
9. The spider classification device according to claim 8, further comprising a second data interaction module for data interaction with an external device.
10. A spider classification device, comprising an intelligent terminal, on which an application adopting the method of claim 7 is installed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110002891.4A CN112651462A (en) | 2021-01-04 | 2021-01-04 | Spider classification method and device and classification model construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110002891.4A CN112651462A (en) | 2021-01-04 | 2021-01-04 | Spider classification method and device and classification model construction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112651462A true CN112651462A (en) | 2021-04-13 |
Family
ID=75367199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110002891.4A Pending CN112651462A (en) | 2021-01-04 | 2021-01-04 | Spider classification method and device and classification model construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651462A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214298A (en) * | 2011-06-20 | 2011-10-12 | 复旦大学 | Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism |
| CN104850836A (en) * | 2015-05-15 | 2015-08-19 | 浙江大学 | Automatic insect image identification method based on depth convolutional neural network |
| CN109145770A (en) * | 2018-08-01 | 2019-01-04 | 中国科学院合肥物质科学研究院 | A kind of spider automatic counting method combined based on multi-scale feature fusion network with location model |
-
2021
- 2021-01-04 CN CN202110002891.4A patent/CN112651462A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214298A (en) * | 2011-06-20 | 2011-10-12 | 复旦大学 | Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism |
| CN104850836A (en) * | 2015-05-15 | 2015-08-19 | 浙江大学 | Automatic insect image identification method based on depth convolutional neural network |
| CN109145770A (en) * | 2018-08-01 | 2019-01-04 | 中国科学院合肥物质科学研究院 | A kind of spider automatic counting method combined based on multi-scale feature fusion network with location model |
Non-Patent Citations (1)
| Title |
|---|
| YANG JIAN ET AL.: "Automatic Classification of Spider Images in Natural Background", 《2019 IEEE 4TH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056106B (en) | Grassland grazing sheep grazing behavior detection system and detection method thereof | |
| CN104036235B (en) | Plant species recognition methods based on blade HOG features and intelligent terminal platform | |
| CN102915432B (en) | A kind of vehicle-mounted microcomputer image/video data extraction method and device | |
| CN109801265B (en) | Real-time transmission equipment foreign matter detection system based on convolutional neural network | |
| CN103218603A (en) | Face automatic labeling method and system | |
| CN105850930A (en) | Machine vision based pre-warning system and method for pest and disease damage | |
| CN108924483A (en) | A kind of automatic monitoring system and method for the field animal based on depth learning technology | |
| CN104616002A (en) | Facial recognition equipment used for judging age groups | |
| CN115249331B (en) | Mine ecological safety identification method based on convolutional neural network model | |
| CN108881813A (en) | A kind of video data handling procedure and device, monitoring system | |
| CN109377921A (en) | But speech control's automatic intelligent demonstration exhibition room | |
| CN110321908A (en) | Image-recognizing method, terminal device and computer readable storage medium | |
| CN112348003A (en) | Airplane refueling scene recognition method and system based on deep convolutional neural network | |
| CN105825228B (en) | Image-recognizing method and device | |
| CN108174237A (en) | Image combining method and device | |
| CN105825046A (en) | Medical data collecting and processing method and device | |
| CN113516070A (en) | Pig counting method | |
| CN110288623A (en) | The data compression method of unmanned plane marine cage culture inspection image | |
| CN108009491A (en) | A kind of object recognition methods solved in fast background movement and system | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| CN113569971B (en) | Image recognition-based catch target classification detection method and system | |
| CN112651462A (en) | Spider classification method and device and classification model construction method and device | |
| CN107306885B (en) | Giant salamander behavior monitoring method | |
| CN109543584A (en) | A kind of identification of intelligent behavior and analysis system | |
| CN115438691A (en) | Small sample gesture recognition method based on wireless signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210413 |
|
| RJ01 | Rejection of invention patent application after publication |