CN115272760A

CN115272760A - Small sample smoke image fine classification method suitable for forest fire smoke detection

Info

Publication number: CN115272760A
Application number: CN202210885015.5A
Authority: CN
Inventors: 程朋乐; 孙冰剑; 娄黎明
Original assignee: Beijing Forestry University
Current assignee: Beijing Forestry University
Priority date: 2022-07-26
Filing date: 2022-07-26
Publication date: 2022-11-01

Abstract

The embodiment of the disclosure discloses a small sample smoke image fine classification method, a small sample smoke image fine classification device, electronic equipment and a computer readable medium, which are suitable for forest fire smoke detection. One embodiment of the method comprises: inputting each image supporting each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category; calculating the average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; inputting the target smoke image into a feature extraction network to obtain a target feature vector; calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set; and determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set. The method can reduce the false alarm problem in the forest fire smoke detection task by further distinguishing the subdivision types of the smoke. And, the difficulty of the scarcity of smoke samples is overcome by using distance metric learning.

Description

Small sample smoke image fine classification method suitable for forest fire smoke detection

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a small sample smoke image fine classification method suitable for forest fire smoke detection.

Background

The existing smoke detection methods, including the traditional method and the deep learning method, do not have the capability of further distinguishing the specific types of smoke, while in a forest fire smoke detection scene, the occurrence of smoke does not necessarily mean the occurrence of a fire, and because smoke generated by cooking smoke, factory smoke and the like is not caused by the fire, the conventional smoke detection work faces the problem of non-dangerous smoke false alarm. In addition, the detection of smoke, especially fire smoke, faces the challenge of data scarcity.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a small sample smoke image fine classification method suitable for forest fire smoke detection to solve the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method for finely classifying a small sample smoke image suitable for smoke detection in a forest fire, the method comprising: inputting each image supporting each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category; calculating the average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; inputting the target smoke image into a feature extraction network to obtain a target feature vector; calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set; and determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

In a second aspect, some embodiments of the present disclosure provide a small sample smoke image fine classification apparatus suitable for forest fire smoke detection, the apparatus comprising: the first input unit is configured to input each image supporting each category in the smoke image set into the feature extraction network respectively to obtain a feature vector set of each category; the first calculation unit is configured to calculate an average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; the second input unit is configured to input the target smoke image into the feature extraction network to obtain a target feature vector; the second calculation unit is configured to calculate the distance between the target feature vector and the feature vector of each category to obtain a distance set; and the determining unit is configured to determine the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.

One of the above-described various embodiments of the present disclosure has the following advantageous effects: by further distinguishing the subdivision types of the smoke, the false alarm problem in the smoke detection task of the forest fire can be reduced. And, the difficulty of smoke sample scarcity is overcome by using distance metric learning.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

Fig. 1 is a schematic diagram of one application scenario of some embodiments of the disclosed small sample smoke image sub-classification method suitable for forest fire smoke detection;

FIG. 2 is a flow diagram of some embodiments of a small sample smoke image sub-classification method suitable for forest fire smoke detection according to the present disclosure;

FIG. 3 is a flow diagram of further embodiments of a small sample smoke image sub-classification method suitable for forest fire smoke detection according to the present disclosure;

fig. 4 is a schematic structural view of some embodiments of a small sample smoke image sub-classification apparatus suitable for forest fire smoke detection according to the present disclosure;

FIG. 5 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 shows a schematic diagram of one application scenario to which some embodiments of the disclosed small sample smoke image fine classification method suitable for forest fire smoke detection may be applied.

In the application scenario shown in fig. 1, the computing device 101 first inputs each image of each category in the smoke-image-support set 102 into the feature extraction network 103, in this embodiment, the smoke-image-support set includes three categories of smoke images, which are a cooking smoke image, a factory smoke image, and a fire smoke image, respectively, the network outputs the feature vector sets of each category, in this embodiment, the feature vector set 104 corresponding to the cooking smoke image is { (1, 4), (1, 3), (2, 5) }, the feature vector set 105 corresponding to the factory smoke image is { (2, 2), (2, 3), (3, 3) }, and the feature vector set 106 corresponding to the fire smoke image is { (6, 2), (5, 1), (4, 1) }, and then calculates an average value of feature vectors in each category, obtaining a feature vector of each category, in this embodiment, a feature vector 107 corresponding to a cooking smoke image is (1.33, 4.00), a feature vector 108 corresponding to a factory smoke image is (2.33, 2.67), and a feature vector 109 corresponding to a fire smoke image is (5.00, 1.33), then inputting a target smoke image 110 into the feature extraction network 103 to obtain a target feature vector 111, in this embodiment, the target feature vector 111 is (1, 5), then calculating distances between the target feature vector 111 and the

feature vectors

107, 108, and 109 of each category to obtain a distance set 112, in this embodiment, the distance set 112 is {1.05,2.68,5.43}, and finally determining the category of the target smoke image as a category 113 corresponding to the minimum distance in the distance set 112, in the present embodiment, the minimum distance in the distance set 112 is 1.05, and the corresponding category is "smoke".

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or electronic devices, or may be implemented as a single server or a single electronic device. When the computing device is embodied as software, it may be implemented as multiple pieces of software or software modules, for example, to provide distributed services, or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices 101 in FIG. 1 is merely illustrative. There may be any number of computing devices 101, as desired for implementation.

With continued reference to fig. 2, a flow 200 of some embodiments of a small sample smoke image sub-classification method suitable for forest fire smoke detection in accordance with the present disclosure is shown. The small sample smoke image fine classification method suitable for forest fire smoke detection comprises the following steps:

step 201, inputting each image supporting each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category.

In some optional implementations of some embodiments, the set of supported smoke images input to the smoke sub-classification method execution body may include images exhibiting different classes of smoke that participate in the above-described feature extraction network training.

In some embodiments, the set of smoke-supporting images may further include images exhibiting different classes of smoke that are not involved in the training of the feature extraction network.

In alternative embodiments of some embodiments, the different types of smoke may include fire smoke, factory smoke, and cooking smoke.

In some embodiments, the different types of smoke may also include fire smoke, cooking smoke, and weather-induced fog.

Step 202, calculating an average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category.

And 203, inputting the target smoke image into a feature extraction network to obtain a target feature vector.

And 204, calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set.

In some optional implementations of some embodiments, the executing entity may calculate euclidean distances between the target feature vector and the feature vectors of each category, to obtain a distance set.

In some embodiments, the executing subject may further calculate mahalanobis distances between the target feature vector and the feature vectors of each category, resulting in a distance set.

Step 205, determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

The method provided by some embodiments of the present disclosure can reduce the false alarm problem in the forest fire smoke detection task by further distinguishing the subdivision types of smoke. And, the difficulty of smoke sample scarcity is overcome by using distance metric learning.

With further reference to fig. 3, a flow 300 of further embodiments of a small sample smoke image sub-classification method suitable for forest fire smoke detection is shown. The flow 300 of the small sample smoke image fine classification method suitable for forest fire smoke detection comprises the following steps:

step 301, inputting each image of each category in a smoke-supporting image set into a feature extraction network respectively to obtain a feature vector set of each category, wherein the smoke-supporting image set comprises images participating in training of the feature extraction network and showing different categories of smoke, and the different categories of smoke comprise fire smoke, factory smoke and cooking smoke.

Step 302, calculating an average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category.

And step 303, inputting the target smoke image into the feature extraction network to obtain a target feature vector.

In some embodiments, the specific implementation of steps 302 to 303 and the technical effect thereof may refer to steps 202 to 203 in the embodiment corresponding to fig. 2, which are not described herein again.

Step 304, calculating the Euclidean distance between the target feature vector and the feature vector of each category to obtain a distance set.

Step 305, determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

In some embodiments, the specific implementation of step 305 and the technical effect thereof may refer to step 205 in the embodiment corresponding to fig. 2, which is not described herein again.

As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the flow 300 of the small sample smoke image sub-classification method for forest fire smoke detection in some embodiments corresponding to fig. 3 embodies the use of smoke images participating in network training as the smoke image supporting set, so that the method in this embodiment can obtain a more stable class feature vector. In addition, the Euclidean distance is used, so that the calculation is simple and convenient, and the gradient is favorably obtained. And different types of smoke including fire smoke, factory smoke and cooking smoke better accord with the results of the existing smoke detection work and the scene of forest fire smoke detection.

With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a small sample smoke image fine classification apparatus suitable for forest fire smoke detection, which correspond to those method embodiments shown in fig. 2, and which may be applied in various electronic devices in particular.

As shown in fig. 4, the smoke sub-classification apparatus 400 of some embodiments comprises: a first input unit 401, a first calculation unit 402, a second input unit 403, a second calculation unit 404, and a determination unit 405. Wherein, according to one or more embodiments of this disclosure, provide a small sample smog fine classification device suitable for forest fire smog detects, include: a first input unit 401 configured to input each image supporting each category in the smoke image set into a feature extraction network, respectively, to obtain a feature vector set of each category; a first calculating unit 402, configured to calculate an average value of feature vectors in the feature vector set of each category, resulting in a feature vector of each category; a second input unit 403, configured to input the target smoke image into the feature extraction network, resulting in a target feature vector; a second calculating unit 404 configured to calculate a distance between the target feature vector and the feature vector of each category, resulting in a distance set; a determining unit 405 configured to determine the category of the target smoke image as a category corresponding to a minimum distance in the distance set.

In an alternative implementation of some embodiments, the set of smoke-enabled images in the first input unit 401 includes images showing different categories of smoke that participate in the above-described training of the feature extraction network.

In an optional implementation of some embodiments, the second computing unit 404 is further configured to: and calculating the Euclidean distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set.

In an alternative implementation of some embodiments, the different categories of smoke in the first input unit 401 include fire smoke, factory smoke and cooking smoke.

It will be understood that the units described in the apparatus 400 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.

Referring now to fig. 5, a schematic diagram of an electronic device (e.g., the server or terminal device of fig. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device in some embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may be separate and not incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: inputting each image of each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category; calculating the average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; inputting the target smoke image into a feature extraction network to obtain a target feature vector; calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set; and determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, which may be described as: a processor includes a first input unit, a first calculation unit, a second input unit, a second calculation unit, and a determination unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, a determination unit may also be described as a "unit that determines a category".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.

According to one or more embodiments of the present disclosure, there is provided a small sample smoke image fine classification method suitable for forest fire smoke detection, including: inputting each image supporting each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category; calculating the average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; inputting the target smoke image into a feature extraction network to obtain a target feature vector; calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set; and determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

According to one or more embodiments of the present disclosure, the smoke-supporting image set includes images exhibiting different classes of smoke, which participate in the training of the feature extraction network.

According to one or more embodiments of the present disclosure, calculating a distance between the target feature vector and the feature vector of each of the categories includes: and calculating the Euclidean distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set.

According to one or more embodiments of the present disclosure, the different types of smoke include fire smoke, factory smoke, and cooking smoke.

According to one or more embodiments of the present disclosure, there is provided a fine smoke classification apparatus including: the first input unit is configured to input each image supporting each category in the smog image set into the feature extraction network respectively to obtain a feature vector set of each category; the first calculation unit is configured to calculate an average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; the second input unit is configured to input the target smoke image into the feature extraction network to obtain a target feature vector; the second calculation unit is configured to calculate the distance between the target feature vector and the feature vector of each category to obtain a distance set; and the determining unit is configured to determine the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

According to one or more embodiments of the present disclosure, the set of smoke-enabled images in the first input unit includes images exhibiting different classes of smoke that participate in the above-described feature extraction network training.

According to one or more embodiments of the present disclosure, the second computing unit is further configured to: and calculating the Euclidean distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set.

According to one or more embodiments of the present disclosure, the different kinds of smoke in the first input unit include fire smoke, factory smoke, and cooking smoke.

According to one or more embodiments of the present disclosure, there is provided an electronic device including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement a method as in any above.

According to one or more embodiments of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method as any one of the above.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A small sample smoke image fine classification method suitable for forest fire smoke detection comprises the following steps: inputting each image supporting each category in the smoke image set into a feature extraction network respectively to obtain a feature vector set of each category; calculating the average value of the feature vectors in the feature vector set of each category to obtain the feature vector of each category; inputting the target smoke image into the feature extraction network to obtain a target feature vector; calculating the distance between the target characteristic vector and the characteristic vector of each category to obtain a distance set; and determining the category of the target smoke image as the category corresponding to the minimum distance in the distance set.

2. The method of claim 1, wherein the set of supporting smoke images comprises images exhibiting different categories of smoke that participate in training of the feature extraction network.

3. The method of claim 1, wherein said calculating a distance between said target feature vector and said each class of feature vectors comprises: and calculating Euclidean distance between the target feature vector and the feature vector of each category.

4. The method of claim 2, wherein the different categories of smoke include fire smoke, factory smoke, and cooking smoke.

5. Small sample smoke image fine classification equipment suitable for forest fire smoke detection comprises:

the first input unit is configured to input each image supporting each category in the smoke image set into the feature extraction network respectively to obtain a feature vector set of each category;

a first calculating unit, configured to calculate an average value of feature vectors in the feature vector set of each category, resulting in a feature vector of each category;

the second input unit is configured to input a target smoke image into the feature extraction network to obtain a target feature vector;

a second calculating unit configured to calculate a distance between the target feature vector and the feature vector of each category, resulting in a distance set;

a determining unit configured to determine a category of the target smoke image as a category corresponding to a minimum distance in the distance set.

6. An electronic device, comprising: one or more processors; storage means having one or more programs stored thereon which, when executed by the one or more processors, cause the one or more processors to implement the method as claimed in claims 1-4.

7. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method as claimed in claims 1-4.