CN114359673B - Small sample smoke detection method, device and equipment based on metric learning - Google Patents

Abstract

Embodiments of the present disclosure disclose a method, apparatus, electronic device, and computer-readable medium for small sample smoke detection based on metric learning. One embodiment of the method comprises the following steps: acquiring a first frame and a current frame of a target video; dividing the first frame and the current frame into corresponding sub-image blocks, and executing the following steps on each pair of sub-image blocks: inputting the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; responding to the fact that the first distance is larger than a first threshold value, inputting a superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance; and determining the current frame sub-image block as a smoke image block in response to the second distance meeting a preset condition. The method reduces the need for smoke training data by using metric learning.

Description

Small sample smoke detection method, device and equipment based on metric learning

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and in particular to a small sample smoke detection method, apparatus, device, and computer-readable medium based on metric learning.

Background technique

In existing deep learning-based smoke detection technology, a large amount of training data is often required to ensure the reliability of detection results. Due to the limited smoke scenes and irregular smoke shapes, the acquisition and labeling of these training data requires a lot of manpower, which brings challenges to smoke detection based on deep learning.

Summary of the invention

The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

Some embodiments of the present disclosure propose a small sample smoke detection method, apparatus, device and computer-readable medium based on metric learning to solve the technical problems mentioned in the above background technology section.

In a first aspect, some embodiments of the present disclosure provide a small sample smoke detection method based on metric learning, the method comprising: acquiring a first frame and a current frame of a target video; dividing the first frame and the current frame into corresponding sub-image blocks, and performing the following steps for each pair of sub-image blocks: inputting the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; in response to the first distance being greater than a first threshold, inputting the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance; in response to the second distance satisfying a preset condition, determining the current frame sub-image block as a smoke image block.

In a second aspect, some embodiments of the present disclosure provide a small sample smoke detection device based on metric learning, the device comprising: an acquisition unit, configured to acquire a first frame and a current frame of a target video; a division unit, configured to divide the first frame and the current frame into corresponding sub-image blocks, and perform the following steps for each pair of sub-image blocks: a first input unit, configured to input the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; a second input unit, configured to input the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance in response to the first distance being greater than a first threshold; and a determination unit, configured to determine the current frame sub-image block as a smoke image block in response to the second distance satisfying a preset condition.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: by using metric learning, the demand for smoke training data is reduced, so that the smoke detection technology based on deep learning can be applied in scenarios where data is scarce.

BRIEF DESCRIPTION OF THE DRAWINGS

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

FIG1 is a schematic diagram of an application scenario of a small sample smoke detection method based on metric learning according to some embodiments of the present disclosure;

FIG2 is a flow chart of some embodiments of a small sample smoke detection method based on metric learning according to the present disclosure;

FIG3 is a flow chart of other embodiments of a small sample smoke detection method based on metric learning according to the present disclosure;

FIG4 is a schematic diagram of the structure of some embodiments of the smoke detection device according to the present disclosure;

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

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

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

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

FIG1 is a schematic diagram showing an application scenario of a small sample smoke detection method based on metric learning to which some embodiments of the present disclosure can be applied.

In the application scenario shown in FIG1 , the computing device 101 first obtains the first frame 103 and the current frame 104 of the target video 102, and then divides the first frame 103 and the current frame 104 into corresponding sub-image blocks. In this embodiment, the computing device 101 divides the first frame 103 and the current frame 104 into four sub-image blocks, and performs the following steps for each pair of sub-image blocks: the first frame sub-image block 108 and the corresponding current frame sub-image block 111 are input into the first metric network 105 to obtain a first distance 106. In this embodiment, the first distance 106 is 2.45. In response to the first distance 106 being greater than the first threshold 107, in this embodiment, the first threshold 107 is 1, and the first distance 106 satisfies the condition of being greater than the first threshold, the superposition result 110 of the first frame sub-image block 108 and the smoke template image 109 and the current frame sub-image block 111 are input into the second metric network 112 to obtain a second distance 113. In this embodiment, the second distance 113 is 0.16. In response to the second distance 113 satisfying the preset condition 114, the current frame sub-image block 111 is determined as a smoke image block. In this embodiment, the second distance 113 satisfies the preset condition "<0.5", so the computing device 101 determines the current frame sub-image block as a smoke image block.

It should be noted that the computing device 101 can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or electronic devices, or as a single server or a single electronic device. When the computing device is embodied as software, it can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

It should be understood that the number of computing devices 101 in FIG1 is merely illustrative and any number of computing devices 101 may be provided according to implementation requirements.

2, a process 200 of some embodiments of a small sample smoke detection method based on metric learning according to the present disclosure is shown. The small sample smoke detection method based on metric learning includes the following steps:

Step 201, obtaining the first frame and the current frame of the target video.

In some embodiments, the execution subject of the small sample smoke detection method based on metric learning (eg, the computing device shown in FIG. 1 ) can obtain the first frame and the current frame of the target video in an offline manner.

In some embodiments, the execution subject may also obtain the first frame and the current frame of the target video by wireless communication.

Step 202: divide the first frame and the current frame into corresponding sub-image blocks, and perform the following steps on each pair of sub-image blocks.

In some embodiments, the execution entity may divide the first frame and the current frame into corresponding non-overlapping sub-image blocks, for example, dividing the sub-image blocks into 100*100 blocks every 100 columns and 100 rows.

In some embodiments, the execution entity may further divide the first frame and the current frame into corresponding sub-image blocks with overlapping areas, for example, dividing the sub-image blocks into 100*100 blocks every 50 columns and 50 rows.

Step 203: input the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance.

In some embodiments, the first metric network may be a network trained using a smoke dataset.

In some optional implementations of some embodiments, the first metric network may be a metric network trained using a non-smoke dataset.

In some optional implementations of some embodiments, the first metric network may be a metric network trained using a non-smoke dataset and fine-tuned using a smoke dataset.

Step 204: In response to the first distance being greater than the first threshold, the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block are input into a second metric network to obtain a second distance.

In some embodiments, the second metric network may be a network trained using a smoke dataset.

In some optional implementations of some embodiments, the second metric network may be a metric network trained using a non-smoke dataset.

In some optional implementations of some embodiments, the second metric network may be a metric network trained using a non-smoke dataset and fine-tuned using a smoke dataset.

Step 205: In response to the second distance satisfying a preset condition, the sub-image block of the current frame is determined as a smoke image block.

In some embodiments, the execution entity may determine the sub-image block of the current frame as a smoke image block in response to the second distance being smaller than the first distance.

In some optional implementations of some embodiments, the execution entity may determine the sub-image block of the current frame as a smoke image block in response to the second distance being smaller than a second threshold.

In some optional implementations of some embodiments, the above-mentioned execution entity may first acquire a target image set, and then input each image in the target image set and the current frame sub-image block into a second metric network in turn to obtain a third distance set, and finally, in response to the second distance being less than each third distance in the third distance set, determine the current frame sub-image block as a smoke image block.

The methods provided by some embodiments of the present disclosure can better cope with noise in the form of clouds and fog in the detection scene.

Further referring to FIG3 , it shows a process 300 of another embodiment of a small sample smoke detection method based on metric learning. The process 300 of the forest fire smoke detection method based on gray value increasing number sequence comprises the following steps:

Step 301, obtaining the first frame and the current frame of the target video.

Step 302: Divide the first frame and the current frame into corresponding sub-image blocks, and perform the following steps on each pair of sub-image blocks.

Step 303: input the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance.

Step 304: In response to the first distance being greater than the first threshold, the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block are input into a second metric network to obtain a second distance.

In some embodiments, the specific implementation of steps 301-304 and the technical effects brought about by them can refer to steps 201-204 in the embodiment corresponding to Figure 2, and will not be repeated here.

Step 305: Acquire a target image set.

In some embodiments, the execution subject of the small sample smoke detection method based on metric learning (eg, the computing device shown in FIG. 1 ) can obtain the first frame and the current frame of the target video in an offline manner.

In some embodiments, the execution subject may also obtain the first frame and the current frame of the target video by wireless communication.

Step 306: Input each image in the target image set and the sub-image block of the current frame into the second metric network in sequence to obtain a third distance set.

Step 307: In response to the second distance being smaller than each third distance in the third distance set, determining the sub-image block of the current frame as a smoke image block.

It can be seen from Figure 3 that, compared with the description of some embodiments corresponding to Figure 2, the process 300 of the small sample smoke detection method based on metric learning in some embodiments corresponding to Figure 3 embodies the step of measuring each image in the target image set with the sub-image block of the current frame. Through this step, the method can effectively exclude interfering objects contained in the target image set, such as cars, pedestrians, etc., thereby being more robust to noise in the scene.

Further referring to FIG. 4 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a smoke detection device, which correspond to the method embodiments shown in FIG. 2 , and the device can be specifically applied to various electronic devices.

As shown in FIG4 , a smoke detection device 400 of some embodiments includes: an acquisition unit 401, a division unit 402, a first input unit 403, a second input unit 404, and a determination unit 405. According to one or more embodiments of the present disclosure, a smoke detection device is provided, including: an acquisition unit 401, configured to acquire a first frame and a current frame of a target video; a division unit 402, configured to divide the first frame and the current frame into corresponding sub-image blocks, and perform the following steps for each pair of sub-image blocks: a first input unit 403, configured to input the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; a second input unit 404, configured to input the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network in response to the first distance being greater than a first threshold value, and obtaining a second distance; a determination unit 405, configured to determine the current frame sub-image block as a smoke image block in response to the second distance satisfying a preset condition.

In an optional implementation of some embodiments, the determination unit 405 is further configured to: in response to the second distance being smaller than the second threshold, determine the sub-image block of the current frame as a smoke image block.

In an optional implementation of some embodiments, the device 400 also includes: an acquisition unit, configured to: acquire a target image set; a third input unit, configured to: input each image in the target image set and the current frame sub-image block into the second metric network in turn to obtain a third distance set.

In an optional implementation of some embodiments, the determination unit 405 is further configured to: in response to the second distance being smaller than each third distance in the third distance set, determine the sub-image block of the current frame as a smoke image block.

In an optional implementation of some embodiments, the first metric network and the second metric network include metric networks trained using a non-smoke dataset.

In an optional implementation of some embodiments, the first metric network and the second metric network include metric networks trained using a non-smoke dataset and fine-tuned using a smoke dataset.

It is understandable that the units recorded in the device 400 correspond to the steps in the method described with reference to Figure 2. Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 400 and the units contained therein, and will not be repeated here.

Referring to FIG5 below, it shows a schematic diagram of the structure of an electronic device (e.g., the server or terminal device in FIG1 ) 500 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG5 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG5 , the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to the bus 504.

Typically, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although FIG. 5 shows an electronic device 500 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively. Each box shown in FIG. 5 may represent one device, or may represent multiple devices as needed.

In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

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 above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the first frame and the current frame of the target video; divides the first frame and the current frame into corresponding sub-image blocks, and performs the following steps for each pair of sub-image blocks: inputs the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; in response to the first distance being greater than a first threshold, inputs the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance; in response to the second distance satisfying a preset condition, determines the current frame sub-image block as a smoke image block. This method reduces the demand for smoke training data by using metric learning.

Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a division unit, a first input unit, a second input unit, and a determination unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the determination unit may also be described as a "unit for determining a smoke image block".

The functions described above herein 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), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

According to one or more embodiments of the present disclosure, a small sample smoke detection method based on metric learning is provided, comprising: acquiring a first frame and a current frame of a target video; dividing the first frame and the current frame into corresponding sub-image blocks, and performing the following steps for each pair of sub-image blocks: inputting the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; in response to the first distance being greater than a first threshold, inputting the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance; in response to the second distance satisfying a preset condition, determining the current frame sub-image block as a smoke image block.

According to one or more embodiments of the present disclosure, in response to the second distance satisfying a preset condition, determining the current frame sub-image block as a smoke image block includes: in response to the second distance being less than a second threshold, determining the current frame sub-image block as a smoke image block.

According to one or more embodiments of the present disclosure, in response to the first distance being greater than a first threshold, the superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block are input into a second metric network to obtain a second distance, and the method further includes: acquiring a target image set; inputting each image in the target image set and the current frame sub-image block into the second metric network in turn to obtain a third distance set.

According to one or more embodiments of the present disclosure, in response to the second distance satisfying a preset condition, determining the current frame sub-image block as a smoke image block includes: in response to the second distance being less than each third distance in a third distance set, determining the current frame sub-image block as a smoke image block.

According to one or more embodiments of the present disclosure, the first metric network and the second metric network include metric networks trained using a non-smoke dataset.

According to one or more embodiments of the present disclosure, the first metric network and the second metric network include metric networks trained using a non-smoke dataset and fine-tuned using a smoke dataset.

According to one or more embodiments of the present disclosure, a smoke detection device is provided, comprising: an acquisition unit, configured to acquire a first frame and a current frame of a target video; a division unit, configured to divide the first frame and the current frame into corresponding sub-image blocks, and perform the following steps for each pair of sub-image blocks: a first input unit, configured to input the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance; a second input unit, configured to, in response to the first distance being greater than a first threshold, input a superposition result of the first frame sub-image block and a smoke template image and the current frame sub-image block into a second metric network to obtain a second distance; and a determination unit, configured to, in response to the second distance satisfying a preset condition, determine the current frame sub-image block as a smoke image block.

According to one or more embodiments of the present disclosure, the determination unit is further configured to: in response to the second distance being smaller than a second threshold, determine the sub-image block of the current frame as a smoke image block.

According to one or more embodiments of the present disclosure, the device also includes: an acquisition unit, configured to: acquire a target image set; a third input unit, configured to: input each image in the target image set and the current frame sub-image block into the second metric network in sequence to obtain a third distance set.

According to one or more embodiments of the present disclosure, the determination unit is further configured to: in response to the second distance being smaller than each third distance in the third distance set, determine the current frame sub-image block as a smoke image block.

According to one or more embodiments of the present disclosure, the first metric network and the second metric network include metric networks trained using a non-smoke dataset.

According to one or more embodiments of the present disclosure, the first metric network and the second metric network include metric networks trained using a non-smoke dataset and fine-tuned using a smoke dataset.

According to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above methods.

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

The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims (9)

1. A method for detecting smoke in a small sample based on metric learning, comprising:

acquiring a first frame and a current frame of a target video;

dividing the first frame and the current frame into corresponding sub-image blocks, and executing the following steps on each pair of sub-image blocks:

inputting the first frame sub-image block and the corresponding current frame sub-image block into a first metric network to obtain a first distance;

responding to the first distance being larger than a first threshold value, inputting a superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance;

and determining the current frame sub-image block as a smoke image block in response to the second distance meeting a preset condition.

2. The method of claim 1, wherein the determining the current frame sub-image block as a smoke image block in response to the second distance satisfying a preset condition comprises:

and determining the current frame sub-image block as a smoke image block in response to the second distance being less than a second threshold.

3. The method of claim 1, wherein after said superimposing the first frame sub-image block with the smoke template image and the current frame sub-image block are input to a second metric network in response to the first distance being greater than a first threshold, the method further comprises:

acquiring a target image set;

and inputting each image in the target image set and the current frame sub-image block into the second metric network in sequence to obtain a third distance set.

4. A method according to claim 3, wherein said determining the current frame sub-image block as a smoke image block in response to the second distance meeting a preset condition comprises:

in response to the second distance being less than each third distance in the third set of distances, the current frame sub-image block is determined to be a smoke image block.

5. The method of claim 1, wherein the first metric network, the second metric network comprise a metric network trained using a non-smoke dataset.

6. The method of claim 1, wherein the first and second metric networks comprise metric networks trained using non-smoke data sets and trimmed using smoke data sets.

7. A small sample smoke detection apparatus based on metric learning, comprising:

an acquisition unit configured to acquire a first frame and a current frame of a target video;

a dividing unit configured to divide the first frame and the current frame into corresponding sub-image blocks, the steps being performed on each pair of sub-image blocks:

the first input unit is configured to input the first frame sub-image block and the corresponding second frame sub-image block into a first metric network to obtain a first distance;

the second input unit is configured to respond to the fact that the first distance is larger than a first threshold value, and input a superposition result of the first frame sub-image block and the smoke template image and the current frame sub-image block into a second metric network to obtain a second distance;

and a determining unit configured to determine the current frame sub-image block as a smoke image block in response to the second distance satisfying a preset condition.

8. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, causes the one or more processors to implement the method recited in any one of claims 1-6.

9. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method as claimed in any of claims 1-6.