CN115861309B

CN115861309B - MPCM acceleration method, device, terminal and medium for infrared weak and small target detection

Info

Publication number: CN115861309B
Application number: CN202310146710.4A
Authority: CN
Inventors: 侯小叶; 赵成功; 杜怡厂; 胡传坤
Original assignee: Hopewell Optoelectronics Co ltd
Current assignee: Hopewell Optoelectronics Co ltd
Priority date: 2023-02-22
Filing date: 2023-02-22
Publication date: 2023-06-16
Anticipated expiration: 2043-02-22
Also published as: CN115861309A

Abstract

The invention relates to the field of target detection, and particularly discloses an acceleration method, a device, a terminal and a medium for detecting an MPCM (multi-point code) by using an infrared weak and small target, wherein a current frame image is obtained, converted into a gray level image, and subjected to mean value filtering to obtain an image M; calculating PCM for the image M; pyramid downsampling the image M by n1 times, n2 times and … … nh times; respectively calculating PCM (pulse code modulation) for the images subjected to downsampling of each pyramid; up-sampling the contrast diagram corresponding to the down-sampled calculated PCM by n1 times, n2 times and … … nh times respectively; calculating MPCM based on each contrast map PCM; and binarizing the MPCM according to the threshold value to obtain the target position. The invention processes the image through downsampling, calculates PCM for the downsampled image, and then carries out upsampling processing, thereby improving the processing speed of MPCM algorithm and meeting the requirement of real-time processing.

Description

MPCM acceleration method, device, terminal and medium for infrared weak and small target detection

Technical Field

The invention relates to the field of target detection, in particular to the field of infrared target detection, and specifically relates to an MPCM acceleration method, device, terminal and medium for infrared weak and small target detection.

Background

Infrared dim target detection is one of the most important technologies in passive defense systems. On the one hand, small objects are often submerged in background clutter due to noise interference; on the other hand, small objects are very challenging to detect because they do not have obvious shape features and useful texture information.

The current infrared weak and small target detection algorithm is mainly divided into multi-frame detection and single-frame detection, wherein the multi-frame detection realizes infrared small target detection by utilizing the continuity and the relativity of moving targets in multi-frame images, the single-frame detection mainly utilizes single-frame images to extract the characteristics of gradient, gray scale, contrast and the like of the small targets in the infrared images, and the weak and small target detection is realized by means of target enhancement or background suppression and the like. However, many schemes of single frame detection focus on the mechanism of enhancing contrast, i.e. highlighting the enhancement target and suppressing the background area, but these algorithms based on human visual contrast mechanisms still have some drawbacks, some schemes cannot well suppress the background, some can only enhance the highlight target, and some can smooth the target.

The MPCM (Multiscale patch-based contrastmeasure) algorithm can well calculate the contrast ratio of a target and a background, and has a good detection effect no matter whether the target is high-brightness or darker than the background, but the multi-scale calculation of the original algorithm is slower in speed, and the real-time processing of an image with slightly larger resolution is not achieved.

Disclosure of Invention

In order to solve the problems, the invention provides an acceleration method, an acceleration device, an acceleration terminal and an acceleration medium for detecting an MPCM (multi-point code) by using an infrared weak and small target, which are characterized in that an image is processed through downsampling, a PCM (pulse code modulation) is calculated on the downsampled image, and then the downsampled image is processed, so that the processing speed of an MPCM algorithm can be improved, and the requirement of real-time processing is met.

In a first aspect, the present invention provides a method for accelerating detection of MPCM by infrared weak and small targets, including the following steps:

acquiring a current frame image, converting the current frame image into a gray level image, and performing mean value filtering to obtain an image M;

calculating PCM for the image M, noted as first PCM;

pyramid downsampling the image M by n1 times, n2 times and … … nh times;

respectively calculating PCM (pulse code modulation) for the images subjected to downsampling of each pyramid to obtain n1 th PCM, n2 nd PCM and … … th nhPCM;

up-sampling the comparison graphs corresponding to the n1 th PCM, the n2 nd PCM and the … … th nhPCM by n1 times, n2 times and … … nh times respectively;

calculating MPCM based on the first PCM and each up-sampled contrast map PCM;

and binarizing the MPCM according to the threshold value to obtain the target position.

Further, the method specifically comprises the following steps:

convolution operation is carried out on the check image M by means of mean convolution to obtain a scale image C ₃ ；

Performing convolution operation on the image downsampled by each pyramid and the mean convolution kernel to respectively obtain a scale image C _n1 、C _n2 、……、C _nh ；

Image C of single scale _k Marked as C, corresponding to C calculated%i，j) Contrast value D of a dot _{i j（，）} Obtaining each PCM; wherein the method comprises the steps ofk=3、n1、h2……nh。

Further, the method specifically includes calculating MPCM by the following formula:

wherein,

h is the height of the image and W is the width of the image.

Further, when the MPCM is binarized, the threshold value is

The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>

,/>

Is->

Is used for the average value of (a),

is->

Standard deviation of (2).

Further, the method specifically comprises the following steps:

and adopting a 3*3 mean filter to perform mean filtering on the gray scale image.

In a second aspect, the present invention provides an acceleration device for detecting an MPCM of a weak infrared target, including,

an image preprocessing module: acquiring a current frame image, converting the current frame image into a gray level image, and performing mean value filtering to obtain an image M;

and a downsampling module: pyramid downsampling the image M by n1 times, n2 times and … … nh times;

PCM calculation module: calculating PCM for the image M, noted as first PCM; respectively calculating PCM (pulse code modulation) for the images subjected to downsampling of each pyramid to obtain n1 th PCM, n2 nd PCM and … … th nhPCM;

up-sampling module: up-sampling the comparison graphs corresponding to the n1 th PCM, the n2 nd PCM and the … … th nhPCM by n1 times, n2 times and … … nh times respectively;

MPCM calculation module: calculating MPCM based on the first PCM and each up-sampled contrast map PCM;

a target position determining module: and binarizing the MPCM according to the threshold value to obtain the target position.

Further, the PCM calculation module performs PCM calculation by:

Further, the MPCM calculation module calculates the MPCM by the following formula:

wherein,

h is the height of the image, and W is the width of the image;

when the target position determining module binarizes the MPCM, the threshold value is

,/>

Is->

Mean value of->

Is->

Standard deviation of (2).

In a third aspect, a technical solution of the present invention provides a terminal, including:

the memory is used for storing an infrared weak and small target detection MPCM acceleration program;

and the processor is used for realizing the steps of the method for detecting the infrared small target according to any one of the above steps when executing the MPCM acceleration program.

In a fourth aspect, the present invention provides a computer readable storage medium, where an infrared small-size object detection MPCM acceleration program is stored, where the infrared small-size object detection MPCM acceleration program, when executed by a processor, implements the steps of the infrared small-size object detection MPCM acceleration method according to any one of the above.

The method, the device, the terminal and the medium for accelerating the detection of the MPCM by the infrared weak and small target have the following beneficial effects compared with the prior art: after preprocessing the acquired image, in addition to directly calculating the PCM for the preprocessed image, downsampling the image, calculating the PCM for the downsampled image again, and finally determining the target based on each PCM calculation MPCM. The invention processes the image through downsampling, calculates PCM for the downsampled image, then carries out upsampling processing, and finally calculates MPCM, thereby improving the processing speed of MPCM algorithm and meeting the requirement of real-time processing.

Drawings

For a clearer description of embodiments of the present application or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description that follow are only some embodiments of the present application, and that other drawings may be obtained from these drawings by a person of ordinary skill in the art without inventive effort.

Fig. 1 is a schematic flow chart of an acceleration method for detecting an MPCM of an infrared weak and small target according to an embodiment of the invention.

Fig. 2 is a flowchart of an embodiment of an acceleration method for detecting MPCM of infrared dim targets according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of a 3*3 mean filter template.

Fig. 4 is a schematic view of a sliding window structure.

Fig. 5 is a schematic diagram of a detection result of an embodiment of an acceleration method for detecting MPCM of an infrared weak target according to an embodiment of the present invention.

Fig. 6 is a schematic block diagram of an infrared weak small target detection MPCM acceleration device according to an embodiment of the invention.

Fig. 7 is a schematic structural diagram of a terminal according to an embodiment of the present invention.

Detailed Description

Some terms related to the present invention are explained below.

PCM: pathc-based contrast measure, contrast measurement of the target at a certain scale.

MPCM: multiscale patch-based contrast measure, multiscale block contrast method.

In order to provide a better understanding of the present application, those skilled in the art will now make further details of the present application with reference to the drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

Fig. 1 is a schematic flow chart of an acceleration method for detecting MPCM of infrared dim targets according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps.

S1, acquiring a current frame image, converting the current frame image into a gray level image, and performing mean value filtering to obtain an image M.

And acquiring a current frame image from the video streaming, and performing target detection based on the current frame image. Firstly, gray processing is carried out on an image, and then, filtering is carried out on a gray image to filter noise interference. The user selects the mean filter as desired.

S2, calculating the PCM for the image M, and recording the PCM as a first PCM.

And preprocessing the image obtained by the pull stream, and then directly performing PCM (pulse code modulation) calculation.

And S3, performing pyramid downsampling on the image M by n1 times, n2 times and … … nh times.

The image obtained by the pulling flow is preprocessed and then subjected to pyramid downsampling, and of course, downsampling is performed by several times, a user can select according to needs, for example, pyramid downsampling is performed on the image M by 2 times and 4 times, and subsequent processing is performed on the image based on the pyramid downsampling by 2 times and 4 times.

S4, respectively calculating PCM for the images subjected to downsampling of the pyramids to obtain nth 1PCM, nth 2PCM and … … nth hPCM.

The PCM is calculated on the downsampled image, obtaining a plurality of PCMs.

S5, up-sampling the comparison graphs corresponding to the n1 th PCM, the n2 nd PCM and the … … th nhPCM by n1 times, n2 times and … … nh times respectively.

Of course, after the PCM is calculated from the downsampled image, the upsampling process is performed, and the MPCM is calculated after the upsampling process.

S6, calculating MPCM based on the first PCM and each up-sampled contrast map PCM.

And S7, binarizing the MPCM according to a threshold value to obtain a target position.

According to the method for accelerating the detection of the MPCM by the infrared weak and small targets, the images are processed through downsampling, PCM is calculated on the downsampled images, the downsampled images are processed and the MPCM is finally calculated, so that the processing speed of an MPCM algorithm can be improved, and the requirement of real-time processing is met.

For further understanding of the present invention, a detailed description of the present invention is provided below, and fig. 2 is a schematic flow chart of the detailed embodiment, and as shown in fig. 2, the detailed embodiment includes the following steps.

S1, pulling and obtaining a current frame image I.

S2, converting the image I into a gray image G.

And S3, carrying out mean value filtering on the gray level image G to obtain an image M.

Averaging is performed to filter out noise interference, for example, a 3*3 averaging filter may be selected, and fig. 3 is a 3*3 averaging filter template.

The algorithm principle of the 3*3 mean filter is as follows:

。

s4, carrying out convolution operation on the image M by using a 3*3 mean convolution kernel to obtain

Pyramid downsampling is respectively carried out on the image M by 2 times and 4 times, convolution operation is carried out on the image M and the average convolution kernel to obtain +.>

。

S5, after convolution operation, single-scale image

(wherein k can be set to 3,5,7, etc.) denoted C, the contrast value of the (i, j) point is calculated corresponding to C +.>

The calculation formula is as follows:

，/>

；

the sliding window structure is shown in fig. 4, where T is a target area and B is a background area.

T,

The mean value of (2) can be obtained from the coordinate value of C, wherein the mean value of T is +.>

,/>

Is +.>

,

Is +.>

,/>

Is +.>

,/>

Is +.>

,/>

Mean value of (1)

,/>

Is +.>

,/>

Is +.>

,/>

Is +.>

Ksize=3 is the scale of convolution, +.>

H, W are the image's aspect ratio, as are the contrast maps of other pyramid downsampled images.

S6, after the contrast map is calculated on the pyramid downsampled image, upsampling the corresponding contrast map.

S7, calculating MPCM of the original resolution size according to the following formula:

，/>

。

s8, according to the threshold value TH pair

Binarization is carried out to obtain the position of the target.

Wherein,

is an empirical value; />

Is->

Mean value of->

Is->

Standard deviation of (2).

Through testing, a plurality of pyramid downsampling scales are synthesized, 3 scales are used, the downsampling of the original image and the original image is 2 times, the downsampling of the original image is 4 times, the processing speed of the image of 640 x 640 on a Hai Si chip can reach 29.5 frames/second, the speed of the calculated MPCM is improved by 2.4 times compared with that of the original algorithm, and the real-time detection requirement can be completely met. As shown in fig. 5, the detection results in fig. 5 (a) are original images, (b) are original PCM, (c) are PCM of 2 times of original downsampling, (d) are PCM of 4 times of original image downsampling, and (e) are results of target calibration.

The embodiment of the method for detecting the MPCM by the infrared small target is described in detail above, and the method for detecting the MPCM by the infrared small target is based on the description of the embodiment.

Fig. 6 is a schematic block diagram of an infrared weak and small target detection MPCM acceleration device according to an embodiment of the invention, where, as shown in fig. 6, the device includes: an image preprocessing module 101, a downsampling module 102, a PCM calculation module 103, an upsampling module 104, an MPCM calculation module 105, and a target position determination module 106.

The image preprocessing module 101: and acquiring a current frame image, converting the current frame image into a gray level image, and performing mean value filtering to obtain an image M.

The downsampling module 102: the image M was pyramid downsampled n1 times, n2 times, … … nh times.

PCM calculation module 103: calculating PCM for the image M, noted as first PCM; PCM is calculated for each pyramid downsampled image to obtain nth 1PCM, nth 2PCM, … … nth hpcm.

Specifically, the module performs PCM calculations by: convolution operation is carried out on the check image M by means of mean convolution to obtain a scale image C ₃ The method comprises the steps of carrying out a first treatment on the surface of the Performing convolution operation on the image downsampled by each pyramid and the mean convolution kernel to respectively obtain a scale image C _n1 、C _n2 、……、C _nh The method comprises the steps of carrying out a first treatment on the surface of the Image C of single scale _k Marked as C, corresponding to C calculated%i，j) Contrast value D of a dot _{i j（，）} Obtaining each PCM; wherein the method comprises the steps ofk=3、n1、h2……nh。

Up-sampling module 104: up-sampling is carried out on the comparison graphs corresponding to the n1 th PCM, the n2 nd PCM and the … … th nhPCM by n1 times, n2 times and … … nh times respectively.

MPCM calculation module 105: MPCM is calculated based on the first PCM, each up-sampled contrast map PCM.

MPCM is calculated by the following formula:

H is the height of the image and W is the width of the image.

The target location determination module 106: and binarizing the MPCM according to the threshold value to obtain the target position.

Wherein the threshold value

，/>

,/>

Is->

Mean value of->

Is->

Standard deviation of (2).

The infrared small target detection MPCM acceleration device of this embodiment is used to implement the foregoing infrared small target detection MPCM acceleration method, so that the specific embodiment of the device can be seen from the foregoing example part of the infrared small target detection MPCM acceleration method, so that the specific embodiment thereof may refer to the description of the corresponding examples of each part, and will not be further described herein.

In addition, since the device for accelerating the detection of the MPCM for the weak infrared target according to the present embodiment is used for implementing the method for accelerating the detection of the MPCM for the weak infrared target, the functions thereof correspond to those of the method described above, and will not be described herein.

Fig. 7 is a schematic structural diagram of a terminal 700 according to an embodiment of the present invention, including: processor 710, memory 720, and communication unit 730. The processor 710 is configured to implement the following steps when implementing the MPCM acceleration program for detecting an infrared small target stored in the memory 720:

calculating PCM for the image M, noted as first PCM;

pyramid downsampling the image M by n1 times, n2 times and … … nh times;

calculating MPCM based on the first PCM and each up-sampled contrast map PCM;

The invention processes the image through downsampling, calculates PCM for the downsampled image, then carries out upsampling processing, and finally calculates MPCM, thereby improving the processing speed of MPCM algorithm and meeting the requirement of real-time processing.

The terminal 700 includes a processor 710, a memory 720, and a communication unit 730. The components may communicate via one or more buses, and it will be appreciated by those skilled in the art that the configuration of the server as shown in the drawings is not limiting of the invention, as it may be a bus-like structure, a star-like structure, or include more or fewer components than shown, or may be a combination of certain components or a different arrangement of components.

The memory 720 may be used to store instructions for execution by the processor 710, and the memory 720 may be implemented by any type of volatile or non-volatile memory terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. The execution of the instructions in memory 720, when executed by processor 710, enables terminal 700 to perform some or all of the steps in the method embodiments described below.

The processor 710 is a control center of the memory terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by running or executing software programs and/or modules stored in the memory 720, and invoking data stored in the memory. The processor may be comprised of an integrated circuit (Integrated Circuit, simply referred to as an IC), for example, a single packaged IC, or may be comprised of a plurality of packaged ICs connected to the same function or different functions. For example, the processor 710 may include only a central processing unit (Central Processing Unit, simply CPU). In the embodiment of the invention, the CPU can be a single operation core or can comprise multiple operation cores.

And a communication unit 730 for establishing a communication channel so that the storage terminal can communicate with other terminals. Receiving user data sent by other terminals or sending the user data to other terminals.

The invention also provides a computer storage medium, which can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (randomaccess memory, RAM) and the like.

The computer storage medium stores an infrared small target detection MPCM acceleration program, and the infrared small target detection MPCM acceleration program realizes the following steps when being executed by a processor:

calculating PCM for the image M, noted as first PCM;

pyramid downsampling the image M by n1 times, n2 times and … … nh times;

calculating MPCM based on the first PCM and each up-sampled contrast map PCM;

It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solution in the embodiments of the present invention may be embodied essentially or what contributes to the prior art in the form of a software product stored in a storage medium such as a U-disc, a mobile hard disk, a Read-only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk or an optical disk, etc. various media capable of storing program codes, including several instructions for causing a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention.

In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The foregoing disclosure is merely illustrative of the preferred embodiments of the invention and the invention is not limited thereto, since modifications and variations may be made by those skilled in the art without departing from the principles of the invention.

Claims

1. An acceleration method for detecting an MPCM by an infrared weak and small target is characterized by comprising the following steps:

calculating PCM for the image M, noted as first PCM; PCM refers to a contrast measurement mode of a target under a certain scale;

pyramid downsampling the image M by n1 times, n2 times and … … nh times;

calculating MPCM based on the first PCM and each up-sampled contrast map PCM;

binarizing the MPCM according to a threshold value to obtain a target position;

the method specifically comprises the following steps:

Image C of single scale _k Marked as C, corresponding to C calculated%i，j) Contrast value D of a dot _（i，j） Obtaining each PCM; wherein the method comprises the steps ofk=3、n1、h2……nh；

The method specifically includes calculating MPCM by the following formula:

wherein,

h is the height of the image and W is the width of the image.

2. The method for accelerating detection of MPCM of small infrared target according to claim 1, wherein the threshold value is

,/>

Is->

Mean value of->

Is->

Standard deviation of (2).

3. The method for detecting MPCM acceleration according to claim 2, wherein the method specifically comprises:

4. An infrared weak and small target detection MPCM accelerating device is characterized by comprising,

PCM calculation module: calculating PCM for the image M, noted as first PCM; respectively calculating PCM (pulse code modulation) for the images subjected to downsampling of each pyramid to obtain n1 th PCM, n2 nd PCM and … … th nhPCM; PCM refers to a contrast measurement mode of a target under a certain scale;

a target position determining module: binarizing the MPCM according to a threshold value to obtain a target position;

the PCM calculation module performs PCM calculation through the following steps:

The MPCM calculation module calculates MPCM by the following formula:

wherein,

h is the height of the image, and W is the width of the image;

,/>

Is that

Mean value of->

Is->

Standard deviation of (2).

5. A terminal, comprising:

a processor for implementing the steps of the method for detecting small infrared targets according to any one of claims 1-3 when executing the small infrared targets detection MPCM acceleration program.

6. A computer readable storage medium, wherein an infrared small object detection MPCM acceleration program is stored on the readable storage medium, and the infrared small object detection MPCM acceleration program, when executed by a processor, implements the steps of the infrared small object detection MPCM acceleration method according to any of claims 1-3.