CN112800888B - Target reporting method and device based on image recognition - Google Patents
Target reporting method and device based on image recognition Download PDFInfo
- Publication number
- CN112800888B CN112800888B CN202110059192.3A CN202110059192A CN112800888B CN 112800888 B CN112800888 B CN 112800888B CN 202110059192 A CN202110059192 A CN 202110059192A CN 112800888 B CN112800888 B CN 112800888B
- Authority
- CN
- China
- Prior art keywords
- target
- image
- newly added
- video
- video image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 230000008859 change Effects 0.000 claims abstract description 11
- 238000005286 illumination Methods 0.000 claims abstract description 11
- 241001522301 Apogonichthyoides nigripinnis Species 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008685 targeting Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000834287 Cookeolus japonicus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F41—WEAPONS
- F41J—TARGETS; TARGET RANGES; BULLET CATCHERS
- F41J5/00—Target indicating systems; Target-hit or score detecting systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Abstract
The invention provides a target reporting method and device based on image recognition, wherein the method comprises the following steps: for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image; and determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image. According to the target reporting method and device based on image recognition, provided by the invention, the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stained target surfaces and the like can be effectively avoided by utilizing a multi-frame differential algorithm, the positions of the bullet holes are accurately recognized, false reporting or missing reporting is avoided, and the target reporting is accurate and high in accuracy.
Description
Technical Field
The invention relates to the technical field of shooting training target reporting equipment, in particular to a target reporting method and device based on image recognition.
Background
In the technical field of shooting training target reporting equipment, traditional target reporting modes comprise manual target reporting, ultrasonic positioning target reporting, photoelectric sensing target reporting and the like, and a target reporting system based on image acquisition and analysis is started to appear in recent years.
The efficiency of manual target reporting is low, and the influence of subjective factors is large; the ultrasonic wave positioning target reporting and the photoelectric sensing positioning target reporting respectively need to be provided with an ultrasonic wave sensor or a photoelectric positioning probe in or around the target plate, so that the processing difficulty of the target plate is increased, the daily maintenance is difficult, and the debugging workload is large. The existing target reporting system based on image acquisition and analysis mainly uses the difference between the front frame and the rear frame to judge whether shooting is carried out or not, and false report or missing report is easy to generate for interference conditions such as shaking of a target plate, illumination change, connection hole, stain on the target surface and the like.
Therefore, it is necessary to provide a new target reporting method to solve the problems of low target reporting efficiency, inaccuracy, complex implementation, difficult maintenance, easy interference and the like existing in the existing target reporting method.
Disclosure of Invention
The invention provides a target reporting method and device based on image recognition, which are used for solving the defects of low target reporting efficiency, inaccuracy, complex realization, difficult maintenance and easy interference in the prior art and realizing high-efficiency and accurate target reporting.
The invention provides a target reporting method based on image recognition, which comprises the following steps:
for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image;
and determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
According to the target reporting method based on image recognition provided by the invention, before any frame of video image in the target video is determined whether a newly added bullet hole exists on the video image by a multi-frame difference algorithm, the method further comprises the following steps:
acquiring a target range image, and preprocessing the target range image to obtain a target image;
the method comprises the steps of carrying out initial positioning on a decannular line and a bulls-eye of a target image through a circle detection algorithm to obtain an initial bulls-eye position;
based on the initial target position, performing secondary positioning on the target of the target image by utilizing a multidirectional pixel scanning method to obtain an accurate target position;
calibrating each loop line of the target image based on the accurate target position, and calculating target points corresponding to each pixel on the target image;
the video image and the target range image are images obtained by shooting the same target range.
According to the target reporting method based on image recognition, the target of the target image is secondarily positioned by utilizing a multi-direction pixel scanning method based on the initial target position, so as to obtain an accurate target position, and the target reporting method comprises the following steps:
starting from the initial bulls-eye position, scanning pixels on the target image along multiple directions towards the periphery until black pixels are scanned;
and fine-tuning the initial target position according to the pixel distance of each direction scanning to obtain an accurate target position, so that the distances from the accurate target position to black pixels in each direction are equal, or the difference of the pixel distances of each direction scanning is minimized.
According to the target reporting method based on image recognition provided by the invention, each loop line of the target image is calibrated based on the accurate target position, and the target score corresponding to each pixel on the target image is calculated, and the target reporting method comprises the following steps:
starting from the accurate target position, calibrating all loops of the target image one by one according to the characteristics of the target paper image, and determining target components corresponding to each pixel on the target image in the loop calibration process;
the target paper image is characterized in that white and black areas are spaced outwards from a target center, and pixel distances between different areas are changed according to a preset fixed proportion.
According to the target reporting method based on image recognition provided by the invention, for any frame of video image in a target video, whether a newly added bullet hole exists on the video image or not is determined through a multi-frame difference algorithm, and under the condition that the newly added bullet hole exists on the video image, the position of the newly added bullet hole is obtained, and the method comprises the following steps:
for any frame of video image in the target video, acquiring n frames of images including the current video image, and carrying out differential calculation on each frame of images except the video image in the n frames of images and the video image to obtain n-1 frames of differential images;
carrying out weighted average on the n-1 frame differential image to obtain a calculation result;
if the calculation result is smaller than a preset threshold value, determining that no newly added bullet holes exist on the video image; or,
if the calculated result is greater than or equal to a preset threshold value, determining that a newly added bullet hole exists in the video image, and determining the position of the newly added bullet hole by searching the maximum position of the difference of the n-1 frames of differential images;
wherein n is a natural number greater than 2.
According to the target reporting method based on image recognition, the target range image is preprocessed to obtain the target image, and the target image comprises the following steps:
performing edge extraction, binarization and filtering denoising on the target range image to obtain a target image;
the threshold value of the binarization processing is adaptively determined according to illumination change.
The invention also provides a target reporting device based on image recognition, which comprises:
the system comprises a bullet hole determining unit, a target shooting unit and a target shooting unit, wherein the bullet hole determining unit is used for determining whether a newly added bullet hole exists in any frame of video image in a target shooting video through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists in the video image;
and the target score determining unit is used for determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
According to the target reporting device based on image recognition, the invention further comprises:
the preprocessing unit is used for acquiring a target range image, preprocessing the target range image and acquiring a target image;
the initial positioning unit is used for initially positioning the decannular line and the bulls-eye of the target image through a circle detection algorithm to obtain an initial bulls-eye position;
the accurate positioning unit is used for carrying out secondary positioning on the target of the target image by utilizing a multi-direction pixel scanning method based on the initial target position to obtain an accurate target position;
the loop line calibration unit is used for calibrating each loop line of the target image based on the accurate target position and calculating the target score corresponding to each pixel on the target image;
the video image and the target range image are images obtained by shooting the same target range.
According to the target reporting method and device based on image recognition, provided by the invention, the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stained target surfaces and the like can be effectively avoided by utilizing a multi-frame differential algorithm, the positions of the bullet holes are accurately recognized, false reporting or missing reporting is avoided, and the target reporting is accurate and high in accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a target reporting method based on image recognition according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a target reporting method based on image recognition according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of a multi-directional pixel scanning method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an N-frame video image according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a target reporting device based on image recognition according to an embodiment of the present invention;
fig. 6 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a schematic flow chart of a target reporting method based on image recognition according to an embodiment of the present invention, including step 101 and step 102.
Step 101, for any frame of video image in a target video, determining whether a newly added bullet hole exists in the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists in the video image.
Specifically, the target video is video obtained by shooting a target range. The multi-frame difference algorithm is to acquire multi-frame images including the current frame video image, perform difference calculation on other frames of images in the multi-frame images and the current frame video image to acquire a difference image, and perform weighted average on the acquired difference image.
For any frame of video image in the target video, a calculation result can be obtained by utilizing a multi-frame difference algorithm, and then whether a newly added bullet hole exists on the current frame of video image is judged according to the calculation result. If the newly added bullet holes are judged to be known to exist in the video image of the current frame, the position with the largest difference of the differential images is the position of the newly added bullet holes.
By utilizing a multi-frame differential algorithm, the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stained target surfaces and the like can be effectively avoided, and false reporting or missing reporting is avoided.
Step 102, determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
After the positions of the newly added bullet holes are determined, the pixel positions corresponding to the positions of the newly added bullet holes on the video image can be obtained, and then, according to target scores corresponding to each pixel in a predetermined target image, target scores corresponding to the newly added bullet holes, namely target scores corresponding to the video image, can be obtained.
The target image may be a chest target image, a half target image, or the like, and the present invention does not specifically limit the type of target image.
According to the target reporting method based on image recognition, provided by the embodiment of the invention, the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stained target surfaces and the like can be effectively avoided by utilizing a multi-frame differential algorithm, the positions of the bullet holes are accurately recognized, false reporting or missing reporting is avoided, and the target reporting is accurate and high in accuracy.
Fig. 2 is a schematic flow chart of a target reporting method based on image recognition according to another embodiment of the present invention, based on the content of the foregoing embodiment, before determining, by a multi-frame difference algorithm, whether a newly added bullet hole exists on any video image in the target video, the video image further includes steps 001 to 004.
And 001, acquiring a target range image, and preprocessing the target range image to obtain a target object image.
Specifically, an actual range image is acquired, and then the range image is preprocessed to obtain a target image.
In one embodiment, preprocessing the range image to obtain a target image of interest includes:
performing edge extraction, binarization and filtering denoising on the target range image to obtain a target image;
the threshold value of the binarization processing is adaptively determined according to illumination change.
It will be appreciated that the target image is an image of black and white pixels with edge extraction, binarization, interference and noise removal.
And 002, carrying out initial positioning on the decannular line and the bulls-eye of the target image through a circle detection algorithm to obtain an initial bull-eye position.
Specifically, a circle is detected by a circle detection algorithm, for example, a Hough transformation algorithm or various improved Hough transformation algorithms, and the decade loop line and the bulls-eye of the target image are initially positioned to obtain an initial bulls-eye position.
And 003, based on the initial target position, performing secondary positioning on the target of the target image by utilizing a multi-direction pixel scanning method to obtain an accurate target position.
Specifically, the multi-directional pixel scanning method refers to scanning pixels in a plurality of directions toward the periphery.
Starting from an initial bulls-eye position, fine-tuning the initial bulls-eye position by utilizing a multi-directional pixel scanning method, so that the finally obtained bulls-eye position is positioned at the center of the target image decade area.
And 004, calibrating each loop line of the target image based on the accurate bulls-eye position, and calculating the target score corresponding to each pixel on the target image.
And finally, calibrating each loop line of the target image according to the characteristics of the target paper image corresponding to the target image based on the accurate target position, and determining the target score corresponding to each pixel in the target image in the calibrating process.
After determining the target score corresponding to each pixel on the target image, the positions of the bullet holes are determined, and the target score corresponding to the bullet holes can be easily obtained.
Steps 101 and 102 in fig. 2 are the same as steps 101 and 102 in fig. 1, and are not described here again.
According to the target reporting method based on image recognition, the target reporting accuracy and precision can be effectively improved by combining the mode of preliminary positioning by a circular detection algorithm and the mode of multi-directional pixel scanning accurate positioning, meanwhile, the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stains on the target surface and the like is effectively avoided by utilizing a multi-frame differential algorithm, the positions of the bullet holes are accurately identified, and false reporting or missing reporting is avoided.
Based on the foregoing embodiment, the performing, based on the initial target position, secondary positioning on the target of the target image by using a multi-directional pixel scanning method, to obtain an accurate target position includes:
starting from the initial bulls-eye position, scanning pixels on the target image along multiple directions towards the periphery until black pixels are scanned;
and fine-tuning the initial target position according to the pixel distance of each direction scanning to obtain an accurate target position, so that the distances from the accurate target position to black pixels in each direction are equal, or the difference of the pixel distances of each direction scanning is minimized.
Specifically, in one embodiment, after binarizing a target range image, if it is determined that the position of a loop line is black and the decade area is a whole white area according to the characteristics of a target paper image corresponding to the target image, fig. 3 is a schematic diagram of a multi-directional pixel scanning method provided in the embodiment of the present invention, as shown in fig. 3, pixels on the target image are scanned from an initial target position along multiple directions toward the periphery until the pixels are scanned to black, fine tuning is performed on the initial target position according to the pixel distance scanned in each direction, and when the distances from the target position to the black pixels in each direction are equal, or when the pixel distance difference scanned in each direction is minimized, fine tuning is stopped, so as to obtain an accurate target position.
In embodiments of the present invention, accurate bulls-eye position refers to a bulls-eye position that is more accurate than the initial bulls-eye position.
If the position of the loop line is determined to be white and the decade area is determined to be a whole black area according to the characteristics of the target paper image corresponding to the target image, pixels on the target image are scanned from the initial target position along a plurality of directions to the periphery until white pixels are scanned, fine adjustment is performed on the initial target position according to the pixel distance scanned in each direction, and fine adjustment is stopped when the distances from the target position to the white pixels in each direction are equal or the pixel distance difference scanned in each direction is minimized, so that the accurate target position is obtained.
According to the target reporting method based on image recognition, the target can be accurately positioned by utilizing the multi-directional pixel scanning accurate positioning mode.
Based on the foregoing embodiment, the calibrating each loop line of the target image based on the accurate target position, and calculating the target score corresponding to each pixel on the target image includes:
starting from the accurate target position, calibrating all loops of the target image one by one according to the characteristics of the target paper image, and determining target components corresponding to each pixel on the target image in the loop calibration process;
the target paper image is characterized in that white and black areas are spaced outwards from a target center, and pixel distances between different areas are changed according to a preset fixed proportion.
Specifically, since the target paper image is characterized in that the white and black areas are spaced from the center of the target outwards, and the pixel distances between different areas are changed according to a preset fixed proportion. Therefore, the loop line of the target image can be calibrated according to the characteristics of the target paper image corresponding to the target image, namely, starting from the accurate target position, each loop line of the target image is calibrated one by one according to the characteristics of the target paper image, and in the loop line calibration process, the target score corresponding to each pixel on the target image is determined.
For example, the decade area is generally composed of white pixels, the decade line is black pixels, firstly, the decade line is calibrated from the accurate target position, then, according to the pixel distance from the target to the decade line and the pixel distance between different areas according to the preset fixed proportion, the pixel distance from the decade line to the nine-ring line can be determined, further, the nine-ring line is calibrated, and the pixel distance occupied by the decade line needs to be considered when the pixel distance between the different areas is determined.
Based on the foregoing embodiment, for any frame of video image in the targeted video, determining whether a newly added bullet hole exists on the video image by using a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole when the newly added bullet hole exists on the video image includes:
for any frame of video image in the target video, acquiring n frames of images including the current video image, and carrying out differential calculation on each frame of images except the video image in the n frames of images and the video image to obtain n-1 frames of differential images;
carrying out weighted average on the n-1 frame differential image to obtain a calculation result;
if the calculation result is smaller than a preset threshold value, determining that no newly added bullet holes exist on the video image; or,
if the calculated result is greater than or equal to a preset threshold value, determining that a newly added bullet hole exists in the video image, and determining the position of the newly added bullet hole by searching the maximum position of the difference of the n-1 frames of differential images;
wherein n is a natural number greater than 2.
The n-frame images may be consecutive n-frame images or intermittent n-frame images.
And carrying out differential calculation on each frame of images except the video image in the n frames of images and the video image, namely carrying out differential calculation on each other n-1 frames of images except the video image in the n frames of images and the video image respectively to obtain n-1 frames of differential images.
Fig. 4 is a schematic diagram of an N-frame video image according to an embodiment of the present invention, where N is greater than N. In one embodiment, for each frame in the video image, 5 (i.e., n=5) frames are continuously taken for differencing, for example, for the ith frame in the image, the differences between the (i+1), (i+2), (i+3), (i+4) frames and the ith frame are calculated respectively to obtain 4 differential images, then the 4 differential images are weighted and averaged, and then whether a newly added bullet hole exists or not is determined according to the calculation result, and the position of the newly added bullet hole is determined. And then, according to the calculated bullet hole positions and the corresponding relation between each pixel and the target points on the image, the target shooting results can be determined and displayed as required.
According to the target reporting method based on image recognition, whether the bullet hole exists or not and the position of the bullet hole can be accurately judged by utilizing the multi-frame difference algorithm, so that the target reporting is accurate and high in accuracy.
Fig. 5 is a schematic structural diagram of a target reporting device based on image recognition according to an embodiment of the present invention, including: a bullet hole determining unit 510 and a targeting performance determining unit 520, wherein:
the bullet hole determining unit 510 is configured to determine, according to a multi-frame difference algorithm, whether a newly added bullet hole exists in any frame of video image in the targeted video, and obtain a position of the newly added bullet hole when the newly added bullet hole exists in the video image;
the targeting score determining unit 520 is configured to determine a targeting score corresponding to the video image according to the position of the newly added bullet hole and a target score corresponding to each pixel in the predetermined target image.
The target reporting device based on image recognition provided by the embodiment of the invention can effectively avoid the influence on the target reporting caused by interference conditions such as shaking of a target plate, illumination change, connection holes, stained target surfaces and the like by utilizing a multi-frame differential algorithm, accurately recognizes the positions of the bullet holes, avoids false reporting or missing reporting, and has accurate target reporting and high accuracy.
Based on the content of the foregoing embodiment, the target reporting device based on image recognition further includes:
the preprocessing unit is used for acquiring a target range image, preprocessing the target range image and acquiring a target image;
the initial positioning unit is used for initially positioning the decannular line and the bulls-eye of the target image through a circle detection algorithm to obtain an initial bulls-eye position;
the accurate positioning unit is used for carrying out secondary positioning on the target of the target image by utilizing a multi-direction pixel scanning method based on the initial target position to obtain an accurate target position;
the loop line calibration unit is used for calibrating each loop line of the target image based on the accurate target position and calculating the target score corresponding to each pixel on the target image;
the video image and the target range image are images obtained by shooting the same target range.
Based on the content of the above embodiments, the precise positioning unit is specifically configured to:
starting from the initial bulls-eye position, scanning pixels on the target image along multiple directions towards the periphery until black pixels are scanned;
and fine-tuning the initial target position according to the pixel distance of each direction scanning to obtain an accurate target position, so that the distances from the accurate target position to black pixels in each direction are equal, or the difference of the pixel distances of each direction scanning is minimized.
Based on the content of the above embodiment, the loop calibration unit is specifically configured to:
starting from the accurate target position, calibrating all loops of the target image one by one according to the characteristics of the target paper image, and determining target components corresponding to each pixel on the target image in the loop calibration process;
the target paper image is characterized in that white and black areas are spaced outwards from a target center, and pixel distances between different areas are changed according to a preset fixed proportion.
Based on the foregoing embodiments, the bullet hole determining unit 510 is specifically configured to:
for any frame of video image in the target video, acquiring n frames of images including the current video image, and carrying out differential calculation on each frame of images except the video image in the n frames of images and the video image to obtain n-1 frames of differential images;
carrying out weighted average on the n-1 frame differential image to obtain a calculation result;
if the calculation result is smaller than a preset threshold value, determining that no newly added bullet holes exist on the video image; or,
if the calculated result is greater than or equal to a preset threshold value, determining that a newly added bullet hole exists in the video image, and determining the position of the newly added bullet hole by searching the maximum position of the difference of the n-1 frames of differential images;
wherein n is a natural number greater than 2.
Based on the content of the above embodiment, the preprocessing unit is specifically configured to:
performing edge extraction, binarization and filtering denoising on the target range image to obtain a target image;
the threshold value of the binarization processing is adaptively determined according to illumination change.
It should be noted that, the device provided by the embodiment of the present invention can implement all the method steps implemented by the embodiment of the target reporting method based on image recognition, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the embodiment of the method in the embodiment are omitted.
Fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, where, as shown in fig. 6, the electronic device may include: processor 610, communication interface (Communication Intefface) 620, memory 630, and communication bus 640, wherein processor 610, communication interface 620, and memory 630 communicate with each other via communication bus 640. Processor 610 may invoke logic instructions in memory 630 to perform an image recognition based targeting method comprising: for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image; and determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
Further, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-ONly Memory (ROM), a RaNdom Access Memory (RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention further provide a computer program product, including a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions which, when executed by a computer, enable the computer to perform the image recognition-based target method provided by the above method embodiments, the method including: for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image; and determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
In yet another aspect, embodiments of the present invention further provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the image recognition-based target method provided in the above embodiments, the method including: for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image; and determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A target reporting method based on image recognition, comprising:
for any frame of video image in the target video, determining whether a newly added bullet hole exists on the video image through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists on the video image;
determining a target score corresponding to the video image according to the position of the newly added bullet hole and a target score corresponding to each pixel in a predetermined target image;
before determining whether a newly added bullet hole exists on any frame of video image in the targeted video through a multi-frame difference algorithm, the method further comprises the following steps:
acquiring a target range image, and preprocessing the target range image to obtain a target image;
the method comprises the steps of carrying out initial positioning on a decannular line and a bulls-eye of a target image through a circle detection algorithm to obtain an initial bulls-eye position;
based on the initial target position, performing secondary positioning on the target of the target image by utilizing a multidirectional pixel scanning method to obtain an accurate target position;
calibrating each loop line of the target image based on the accurate target position, and calculating target points corresponding to each pixel on the target image;
the video image and the target range image are images obtained by shooting the same target range;
based on the initial target position, performing secondary positioning on the target of the target image by using a multi-directional pixel scanning method to obtain an accurate target position, including:
starting from the initial bulls-eye position, scanning pixels on the target image along multiple directions towards the periphery until black pixels are scanned;
and fine-tuning the initial target position according to the pixel distance of each direction scanning to obtain an accurate target position, so that the distances from the accurate target position to black pixels in each direction are equal, or the difference of the pixel distances of each direction scanning is minimized.
2. The method for reporting targets based on image recognition according to claim 1, wherein calibrating each loop line of the target image based on the accurate target position and calculating a target score corresponding to each pixel on the target image comprises:
starting from the accurate target position, calibrating all loops of the target image one by one according to the characteristics of the target paper image, and determining target components corresponding to each pixel on the target image in the loop calibration process;
the target paper image is characterized in that white and black areas are spaced outwards from a target center, and pixel distances between different areas are changed according to a preset fixed proportion.
3. The method for capturing images based on image recognition according to claim 1, wherein for any frame of video image in the captured video, determining whether a newly added bullet hole exists in the video image by a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole if the newly added bullet hole exists in the video image, comprises:
for any frame of video image in the target video, acquiring n frames of images including the current video image, and carrying out differential calculation on each frame of images except the video image in the n frames of images and the video image to obtain n-1 frames of differential images;
carrying out weighted average on the n-1 frame differential image to obtain a calculation result;
if the calculation result is smaller than a preset threshold value, determining that no newly added bullet holes exist on the video image; or,
if the calculated result is greater than or equal to a preset threshold value, determining that a newly added bullet hole exists in the video image, and determining the position of the newly added bullet hole by searching the maximum position of the difference of the n-1 frames of differential images;
wherein n is a natural number greater than 2.
4. The image recognition-based targeting method of claim 1, wherein preprocessing the range image to obtain a target image comprises:
performing edge extraction, binarization and filtering denoising on the target range image to obtain a target image;
the threshold value of the binarization processing is adaptively determined according to illumination change.
5. A target-reporting device based on image recognition, comprising:
the system comprises a bullet hole determining unit, a target shooting unit and a target shooting unit, wherein the bullet hole determining unit is used for determining whether a newly added bullet hole exists in any frame of video image in a target shooting video through a multi-frame difference algorithm, and acquiring the position of the newly added bullet hole under the condition that the newly added bullet hole exists in the video image;
the target score determining unit is used for determining the target score corresponding to the video image according to the position of the newly added bullet hole and the target score corresponding to each pixel in the predetermined target image;
the preprocessing unit is used for acquiring a target range image, preprocessing the target range image and acquiring a target image;
the initial positioning unit is used for initially positioning the decannular line and the bulls-eye of the target image through a circle detection algorithm to obtain an initial bulls-eye position;
the accurate positioning unit is used for carrying out secondary positioning on the target of the target image by utilizing a multi-direction pixel scanning method based on the initial target position to obtain an accurate target position;
the loop line calibration unit is used for calibrating each loop line of the target image based on the accurate target position and calculating the target score corresponding to each pixel on the target image;
the video image and the target range image are images obtained by shooting the same target range;
based on the initial target position, performing secondary positioning on the target of the target image by using a multi-directional pixel scanning method to obtain an accurate target position, including:
starting from the initial bulls-eye position, scanning pixels on the target image along multiple directions towards the periphery until black pixels are scanned;
and fine-tuning the initial target position according to the pixel distance of each direction scanning to obtain an accurate target position, so that the distances from the accurate target position to black pixels in each direction are equal, or the difference of the pixel distances of each direction scanning is minimized.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the image recognition based targeting method of any one of claims 1 to 4 when the program is executed.
7. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the image recognition based targeting method according to any of the claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110059192.3A CN112800888B (en) | 2021-01-15 | 2021-01-15 | Target reporting method and device based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110059192.3A CN112800888B (en) | 2021-01-15 | 2021-01-15 | Target reporting method and device based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112800888A CN112800888A (en) | 2021-05-14 |
CN112800888B true CN112800888B (en) | 2023-11-10 |
Family
ID=75809908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110059192.3A Active CN112800888B (en) | 2021-01-15 | 2021-01-15 | Target reporting method and device based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112800888B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113537217B (en) * | 2021-07-22 | 2023-11-14 | 中国科学院半导体研究所 | Target reporting method and device based on ultrasonic wave and image fusion |
WO2024059155A1 (en) * | 2022-09-13 | 2024-03-21 | AccuShoot, Inc. | Systems and methods for automated target identification, classification, and scoring |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103353259A (en) * | 2013-06-22 | 2013-10-16 | 太仓博天网络科技有限公司 | Automatic shoot target-scoring system based on image identification |
CN105930874A (en) * | 2016-04-29 | 2016-09-07 | 浙江大华技术股份有限公司 | Bullet hole identification method and apparatus |
CN106408527A (en) * | 2016-08-25 | 2017-02-15 | 安徽水滴科技有限责任公司 | Automatic target scoring method based on video analysis |
CN110398182A (en) * | 2019-07-04 | 2019-11-01 | 西人马帝言(北京)科技有限公司 | Automatic scoring round target system, method, equipment and medium |
WO2020073505A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技(深圳)有限公司 | Image processing method, apparatus and device based on image recognition, and storage medium |
CN111222504A (en) * | 2019-11-18 | 2020-06-02 | 杭州晨鹰军泰科技有限公司 | Bullet hole target scoring method, device, equipment and medium |
-
2021
- 2021-01-15 CN CN202110059192.3A patent/CN112800888B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103353259A (en) * | 2013-06-22 | 2013-10-16 | 太仓博天网络科技有限公司 | Automatic shoot target-scoring system based on image identification |
CN105930874A (en) * | 2016-04-29 | 2016-09-07 | 浙江大华技术股份有限公司 | Bullet hole identification method and apparatus |
CN106408527A (en) * | 2016-08-25 | 2017-02-15 | 安徽水滴科技有限责任公司 | Automatic target scoring method based on video analysis |
WO2020073505A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技(深圳)有限公司 | Image processing method, apparatus and device based on image recognition, and storage medium |
CN110398182A (en) * | 2019-07-04 | 2019-11-01 | 西人马帝言(北京)科技有限公司 | Automatic scoring round target system, method, equipment and medium |
CN111222504A (en) * | 2019-11-18 | 2020-06-02 | 杭州晨鹰军泰科技有限公司 | Bullet hole target scoring method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN112800888A (en) | 2021-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018176938A1 (en) | Method and device for extracting center of infrared light spot, and electronic device | |
CN112800888B (en) | Target reporting method and device based on image recognition | |
CN111680574B (en) | Face detection method and device, electronic equipment and storage medium | |
US20220084225A1 (en) | Depth Map Processing Method, Electronic Device and Readable Storage Medium | |
CN107341793A (en) | A kind of target surface image processing method and device | |
CN108871185B (en) | Method, device and equipment for detecting parts and computer readable storage medium | |
CN114724000B (en) | Screen shot image moire processing method, device and equipment | |
CN112634262A (en) | Writing quality evaluation method based on Internet | |
KR20180096096A (en) | Coastline monitoring apparatus and method using ocean color image | |
CN112686842B (en) | Light spot detection method and device, electronic equipment and readable storage medium | |
CN113674220A (en) | Image difference detection method, detection device and storage medium | |
CN113822927B (en) | Face detection method, device, medium and equipment suitable for weak quality image | |
CN116129195A (en) | Image quality evaluation device, image quality evaluation method, electronic device, and storage medium | |
CN114037741A (en) | Adaptive target detection method and device based on event camera | |
CN107563981B (en) | Method for evaluating image ringing effect | |
CN111339840A (en) | Face detection method and monitoring system | |
CN110287972B (en) | Animal image contour extraction and matching method | |
CN112712499B (en) | Object detection method and device and computer readable storage medium | |
CN117115926B (en) | Human body action standard judging method and device based on real-time image processing | |
CN117078666B (en) | Two-dimensional and three-dimensional combined defect detection method, device, medium and equipment | |
CN113242422B (en) | Method, device, equipment, system and medium for testing camera module | |
CN113344878B (en) | Image processing method and system | |
CN116958152B (en) | Part size measurement method, device, equipment and medium | |
CN108629806B (en) | Image salient object detection method and system based on image contrast | |
Pan et al. | Infrared Dim Target Detection Based on Multi-scale Space and Multidirectional Gradient Search |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |