CN111325114A - Security image processing method and device for artificial intelligence recognition classification - Google Patents
Security image processing method and device for artificial intelligence recognition classification Download PDFInfo
- Publication number
- CN111325114A CN111325114A CN202010078895.6A CN202010078895A CN111325114A CN 111325114 A CN111325114 A CN 111325114A CN 202010078895 A CN202010078895 A CN 202010078895A CN 111325114 A CN111325114 A CN 111325114A
- Authority
- CN
- China
- Prior art keywords
- luggage
- detected
- image
- animal
- video frame
- 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.)
- Granted
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 241001465754 Metazoa Species 0.000 claims abstract description 98
- 238000007689 inspection Methods 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000005284 excitation Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000561734 Celosia cristata Species 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 241000270295 Serpentes Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
- G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
- G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V9/00—Prospecting or detecting by methods not provided for in groups G01V1/00 - G01V8/00
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- High Energy & Nuclear Physics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides a security inspection image processing method and device for artificial intelligence recognition and classification. The method comprises the following steps: sending sound waves with specified frequency to the luggage to be detected in the security inspection channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode; continuously recording a perspective video of the luggage to be detected passing through a security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying a contour image of contents in the luggage to be detected, comparing the contour image with a standard image in an animal image library, judging whether an animal exists in the luggage to be detected, and obtaining a first comparison result; identifying the central position of each content in all the video frame images, and comparing the central positions of the same content in all the extracted video frame images to obtain a second comparison result; and judging whether the animal exists in the luggage to be detected or not by combining the first comparison result and the second comparison result. The intelligent level of security inspection is improved through the prediction algorithm.
Description
Technical Field
The application relates to the field of artificial intelligence and security check processing, in particular to a security check image processing method and device for artificial intelligence recognition classification.
Background
Currently, image processing methods have been used in a large number of commercial applications. In the security inspection process, animals may exist in some packages, and once the animals pass through security inspection equipment and enter public places such as public transportation equipment, the animals may cause discomfort and disorder of orders of others, and even after some illegal persons carry the animals containing infection sources to pass through the security inspection successfully, the animals will bring great influence to public safety. However, most of the current security inspection systems still perform identification manually, and accurate identification of animals cannot be effectively realized in the security inspection process.
Disclosure of Invention
In view of this, the present application aims to provide a security inspection image processing method and device for artificial intelligence recognition and classification, so as to improve security inspection efficiency and solve the technical problem that security inspection personnel are difficult to recognize hidden animals in luggage in the current security inspection process.
Based on the above purpose, the present application provides a security inspection image processing method for artificial intelligence recognition and classification, comprising:
setting a security check channel into an animal excitation mode, and sending sound waves with specified frequency to luggage to be checked in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode;
continuously recording a perspective video of the to-be-detected luggage passing through the security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying a contour image of contents in the to-be-detected luggage, comparing the contour image with a standard image in an animal image library, judging whether an animal exists in the to-be-detected luggage, and obtaining a first comparison result;
identifying the central position of each content in all the video frame images, and comparing the central positions of the same content in all the extracted video frame images to obtain a second comparison result;
judging whether an animal exists in the luggage to be detected or not by combining the first comparison result and the second comparison result; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
In some embodiments, the method further comprises:
when the first comparison result exceeds a first comparison threshold value, directly judging that animals exist in the luggage to be detected; or
And when the second comparison result exceeds a second comparison threshold value, directly judging that animals exist in the luggage to be detected.
In some embodiments, the method further comprises:
scanning the temperature distribution of the content in the luggage to be detected through a temperature sensor;
and comparing whether the temperature distribution is consistent with the contour image of the content in the luggage to be detected or not, and judging whether animals exist in the luggage to be detected or not.
In some embodiments, randomly extracting a preset number of video frame images from the perspective video, and identifying a contour image of the contents in the baggage to be examined includes:
the video frame images comprise at least two of a bottom view, a top view, a side view, a front view and a back view;
and generating a three-dimensional contour image of the content in the luggage to be detected according to the video frame image.
In some embodiments, the physically traversing and/or vibrating the baggage to be inspected comprises:
enabling the luggage to be tested to vibrate left and right within a preset horizontal amplitude along the horizontal direction; and/or
And enabling the luggage to be tested to vibrate up and down in a preset vertical amplitude along the vertical direction.
In some embodiments, randomly extracting a preset number of video frame images from the perspective video, identifying a contour image of the content in the baggage to be inspected, comparing the contour image with a standard image in an animal image library, and determining whether an animal exists in the baggage to be inspected, includes:
at least the extracted video frame images comprise a first frame image of the luggage to be detected entering the security inspection channel and a last frame image of the luggage to be detected leaving the security inspection channel;
completing the outline images of the same content identified in all the video frame images to form an outline comparison image of each content;
and comparing the outline comparison image of each content with a standard image in an animal image library to judge whether an animal exists in the luggage to be detected.
In some embodiments, identifying the center position of each content in all the video frame images, and comparing the center positions of the same content in all the extracted video frame images comprises:
identifying a main body trunk of the same content in all video frame images, and obtaining the central position of the main body trunk as the central position of the content;
and setting a position deviation threshold value, and judging that no animal exists in the luggage to be checked under the condition that the central position deviation position is smaller than the position deviation threshold value.
Based on the above-mentioned purpose, this application has still provided the categorised security installations of artificial intelligence discernment, includes:
the system comprises an initial module, a security check module and a control module, wherein the initial module is used for setting a security check channel into an animal excitation mode and sending sound waves with specified frequency to luggage to be detected in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode;
the first comparison module is used for continuously recording the perspective video of the to-be-detected luggage passing through the security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying the outline image of the content in the to-be-detected luggage, comparing the outline image with the standard image in the animal image library, judging whether the to-be-detected luggage contains an animal or not, and obtaining a first comparison result;
the second comparison module is used for identifying the central position of each content in all the video frame images through an artificial intelligence algorithm and comparing the central positions of the same content in all the extracted video frame images to obtain a second comparison result;
the combination module is used for combining the first comparison result and the second comparison result to judge whether animals exist in the luggage to be detected; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
In some embodiments, the apparatus further comprises:
the first judgment module is used for directly judging that animals exist in the to-be-detected luggage when the first comparison result exceeds a first comparison threshold;
and the second judgment module is used for directly judging that the animal exists in the to-be-detected luggage when the second comparison result exceeds a second comparison threshold value.
In some embodiments, the first alignment module comprises:
the extraction unit is used for at least extracting video frame images including a first frame image of the luggage to be detected entering the security inspection channel and a last frame image of the luggage to be detected leaving the security inspection channel;
a completion unit configured to form a comparison image of the contour of each content by completing the contour images of the same content identified in all the video frame images;
and the comparison unit is used for comparing the outline comparison image of each content with a standard image in an animal image library and judging whether an animal exists in the luggage to be detected.
Generally speaking, the thinking of this application lies in, when examining the luggage and passing through the inspection passageway, cockscomb structure shake passageway of design can let examine the inside vibrations of examining the article to carry out quick high frequency release through audio frequency release equipment, the purpose promotes the motion of the inside animal of the object that awaits measuring. Continuously recording an image video of an object to be detected, carrying out video frame sampling on the image video at a plurality of random time points to obtain a plurality of data image items, carrying out animal identification on a plurality of images, and preliminarily judging whether the images are animals or not; and then, clustering the relative positions of the plurality of images by using a classification algorithm, and judging whether the object to be detected has relative position change. In addition, animals which do not move, such as hibernating animals like snakes, can move through vibration and sound stimulation, and therefore the animals in the luggage to be detected can be accurately identified.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention.
Fig. 2 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention.
Fig. 3 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention.
Fig. 4 is a block diagram showing a security image processing apparatus for artificial intelligence recognition classification according to an embodiment of the present invention.
Fig. 5 is a block diagram showing a security image processing apparatus for artificial intelligence recognition classification according to an embodiment of the present invention.
Fig. 6 shows a configuration diagram of a first alignment module according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention. As shown in fig. 1, the security inspection image processing method for artificial intelligence recognition classification includes:
s11, setting the security check channel into an animal excitation mode, and sending sound waves with specified frequency to the luggage to be checked in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode.
Specifically, the animal's hearing range and the human's hearing range are not consistent, so if the baggage to be examined is sounded at a frequency that the animal can hear, but the human cannot hear, it may both wake up or excite the animal, but not cause discomfort to the human body. For example, humans can hear 20-20000 hertz sounds, above which are ultrasonic waves and below which are infrasonic waves, so that infrasonic waves below 20 hertz, or ultrasonic waves above 20000 hertz, can be released to wake up or excite animals in luggage at the time of security inspection.
In one embodiment, the physically traversing and/or vibrating the baggage to be inspected includes:
enabling the luggage to be tested to vibrate left and right within a preset horizontal amplitude along the horizontal direction; and/or
And enabling the luggage to be tested to vibrate up and down in a preset vertical amplitude along the vertical direction.
Specifically, the horizontal left-right direction vibration can be realized by arranging an S-shaped case route and enabling the speed of the security check channel to run at a variable speed, so that the luggage vibrates on the security check channel; the horizontal vibration can set regular or irregular protrusions on the security inspection channel, so that the luggage to be inspected can shake up and down when passing through the security inspection channel. Of course, whether it is rocking up and down or left and right, it must be within an acceptable safety range to avoid damage to the luggage being checked. Because the animal is very sensitive to shaking, the up-and-down jolting of the luggage to be detected in the security inspection channel can cause the movement of the animal in the luggage to be detected, and the animal in the luggage to be detected can be identified by utilizing the characteristic.
And S12, continuously recording the perspective video of the luggage to be detected passing through the security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying the outline image of the content in the luggage to be detected, comparing the outline image with the standard image in the animal image library, judging whether the luggage to be detected has animals or not, and obtaining a first comparison result.
For example, multiple cameras can be arranged in the security check passage at multiple angles, so that perspective images of the baggage to be checked are taken from different angles, and the perspective images at different angles are combined to form a three-dimensional image of the content of the baggage to be checked. Compared with the traditional processing process, the method has the advantage that the contrast of the two-dimensional plane image in the animal image library is more accurate.
In one embodiment, randomly extracting a preset number of video frame images from the perspective video, and identifying a contour image of the contents in the baggage to be examined includes:
the video frame images comprise at least two of a bottom view, a top view, a side view, a front view and a back view;
and generating a three-dimensional contour image of the content in the luggage to be detected according to the video frame image.
In one embodiment, randomly extracting a preset number of video frame images from the perspective video, identifying a contour image of the content in the baggage to be inspected, comparing the contour image with a standard image in an animal image library, and determining whether an animal exists in the baggage to be inspected, includes:
at least the extracted video frame images comprise a first frame image of the luggage to be detected entering the security inspection channel and a last frame image of the luggage to be detected leaving the security inspection channel;
completing the outline images of the same content identified in all the video frame images to form an outline comparison image of each content;
and comparing the outline comparison image of each content with a standard image in an animal image library to judge whether an animal exists in the luggage to be detected.
Specifically, the first frame and the last frame of images entering the security check channel are collected, and the relative position of the content of the luggage to be detected passing through the security check channel is compared through a plurality of images in the security check channel process, so that whether the luggage to be detected moves or not can be judged.
And step S13, identifying the center position of each content in all the video frame images, and comparing the center positions of the same content in all the extracted video frame images to obtain a second comparison result.
Specifically, since the baggage to be inspected is generally normal baggage, not an animal, the normal baggage may also shake under the physical action, which may cause an error in the detection result. Inclusion, in identifying the contents, can determine the presence of an animal by first locating the central location of the contents and then determining whether the central location is active.
In one embodiment, identifying the center position of each content in all video frame images and comparing the center positions of the same content in all extracted video frame images comprises:
identifying a main body trunk of the same content in all video frame images, and obtaining the central position of the main body trunk as the central position of the content;
and setting a position deviation threshold value, and judging that no animal exists in the luggage to be checked under the condition that the central position deviation position is smaller than the position deviation threshold value.
Specifically, the normal shaking of the contents is usually shaking along with the shaking of the luggage to be examined, but the shaking of the animal is usually shaking by itself, that is to say, the shaking of the animal is inconsistent with the shaking to be examined. Therefore, it is necessary to set a positional deviation threshold value to determine the animal.
Step S14, judging whether an animal exists in the luggage to be detected or not by combining the first comparison result and the second comparison result; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
It can be seen from the formula that the comparison result can be amplified by multiplying C1 and C2, so that a slight position offset can be reflected in the combined result, and missing detection is avoided.
Fig. 2 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention. As shown in fig. 2, the security image processing method for artificial intelligence recognition classification further includes:
and S15, directly judging that the animal exists in the luggage to be detected when the first comparison result exceeds a first comparison threshold value.
And step S16, directly judging that the animal exists in the luggage to be detected when the second comparison result exceeds a second comparison threshold value.
Particularly, when the first comparison result exceeds the first comparison threshold value or the second comparison result exceeds the second comparison threshold value, the activity of the animal can be determined, detection is not needed again, the animal in the luggage to be detected can be directly judged, and at the moment, the judgment can be immediately and directly carried out, so that the safety inspection efficiency is improved.
Fig. 3 shows a flowchart of a security image processing method of artificial intelligence recognition classification according to an embodiment of the present invention. As shown in fig. 3, the security image processing method for artificial intelligence recognition classification further includes:
step S17, scanning the temperature distribution of the content in the luggage to be detected through a temperature sensor;
and step S18, comparing whether the temperature distribution is consistent with the contour image of the content in the luggage to be detected, and judging whether animals exist in the luggage to be detected.
Fig. 4 is a block diagram showing a security image processing apparatus for artificial intelligence recognition classification according to an embodiment of the present invention. As shown in fig. 4, the whole security image processing apparatus for artificial intelligence recognition and classification may be divided into:
the initial module 41 is used for setting the security check channel into an animal excitation mode and sending sound waves with specified frequency to the luggage to be checked in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode;
the first comparison module 42 is configured to continuously record a perspective video of the to-be-detected luggage passing through the security inspection channel, randomly extract a preset number of video frame images from the perspective video, identify a contour image of contents in the to-be-detected luggage, compare the contour image with a standard image in an animal image library, determine whether an animal exists in the to-be-detected luggage, and obtain a first comparison result;
the second comparison module 43 is configured to identify a central position of each content in all the video frame images through an artificial intelligence algorithm, and compare the central positions of the same content in all the extracted video frame images to obtain a second comparison result;
a combining module 44, configured to combine the first comparison result and the second comparison result to determine whether an animal exists in the to-be-detected baggage; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
Fig. 5 is a block diagram showing a security image processing apparatus for artificial intelligence recognition classification according to an embodiment of the present invention. As shown in fig. 5, the security inspection image processing apparatus for artificial intelligence recognition classification further includes:
the first judging module 45 is configured to directly judge that an animal exists in the to-be-detected luggage when the first comparison result exceeds a first comparison threshold;
and a second judging module 46, configured to directly judge that an animal exists in the to-be-detected luggage when the second comparison result exceeds a second comparison threshold.
Fig. 6 shows a configuration diagram of a first alignment module according to an embodiment of the present invention. As shown in fig. 6, the first comparison module 42 of the security inspection image processing apparatus for artificial intelligence recognition classification includes:
the extracting unit 421 is configured to at least extract a video frame image that includes a first frame image of the baggage to be detected entering the security inspection channel and a last frame image of the baggage leaving the security inspection channel;
a completion unit 422, configured to form a comparison image of the contour of each content by completing the contour images of the same content identified in all the video frame images;
a comparison unit 423, configured to compare the contour comparison image of each content with a standard image in an animal image library, and determine whether an animal exists in the to-be-detected baggage.
The functions of the modules in the systems in the embodiments of the present application may refer to the corresponding descriptions in the above methods, and are not described herein again.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A security inspection image processing method for artificial intelligence recognition classification is characterized by comprising the following steps:
setting a security check channel into an animal excitation mode, and sending sound waves with specified frequency to luggage to be checked in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode;
continuously recording a perspective video of the to-be-detected luggage passing through the security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying a contour image of contents in the to-be-detected luggage, comparing the contour image with a standard image in an animal image library, judging whether an animal exists in the to-be-detected luggage, and obtaining a first comparison result;
identifying the central position of each content in all the video frame images, and comparing the central positions of the same content in all the extracted video frame images to obtain a second comparison result;
judging whether an animal exists in the luggage to be detected or not by combining the first comparison result and the second comparison result; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
2. The method of claim 1, further comprising:
when the first comparison result exceeds a first comparison threshold value, directly judging that animals exist in the luggage to be detected; or
And when the second comparison result exceeds a second comparison threshold value, directly judging that animals exist in the luggage to be detected.
3. The method of claim 1, further comprising:
scanning the temperature distribution of the content in the luggage to be detected through a temperature sensor;
and comparing whether the temperature distribution is consistent with the contour image of the content in the luggage to be detected or not, and judging whether animals exist in the luggage to be detected or not.
4. The method of claim 1, wherein randomly extracting a preset number of video frame images from the perspective video to identify the outline image of the contents of the baggage to be examined comprises:
the video frame images comprise at least two of a bottom view, a top view, a side view, a front view and a back view;
and generating a three-dimensional contour image of the content in the luggage to be detected according to the video frame image.
5. The method according to claim 1, wherein said physically traversing and/or vibrating the baggage to be inspected comprises:
enabling the luggage to be tested to vibrate left and right within a preset horizontal amplitude along the horizontal direction; and/or
And enabling the luggage to be tested to vibrate up and down in a preset vertical amplitude along the vertical direction.
6. The method of claim 1, wherein the randomly extracting a predetermined number of video frame images from the perspective video, identifying the outline image of the contents in the baggage to be inspected, comparing the outline image with the standard image in the animal image library, and determining whether the baggage to be inspected has an animal, comprises:
at least the extracted video frame images comprise a first frame image of the luggage to be detected entering the security inspection channel and a last frame image of the luggage to be detected leaving the security inspection channel;
completing the outline images of the same content identified in all the video frame images to form an outline comparison image of each content;
and comparing the outline comparison image of each content with a standard image in an animal image library to judge whether an animal exists in the luggage to be detected.
7. The method of claim 1, wherein identifying the center position of each content in all video frame images and comparing the center positions of the same content in all extracted video frame images comprises:
identifying a main body trunk of the same content in all video frame images, and obtaining the central position of the main body trunk as the central position of the content;
and setting a position deviation threshold value, and judging that no animal exists in the luggage to be checked under the condition that the central position deviation position is smaller than the position deviation threshold value.
8. An artificial intelligence discerns categorised security check image processing apparatus, its characterized in that includes:
the system comprises an initial module, a security check module and a control module, wherein the initial module is used for setting a security check channel into an animal excitation mode and sending sound waves with specified frequency to luggage to be detected in the channel; the animal excitation mode is a working mode of transversely and/or vibrating the luggage to be detected in a physical mode;
the first comparison module is used for continuously recording the perspective video of the to-be-detected luggage passing through the security inspection channel, randomly extracting a preset number of video frame images from the perspective video, identifying the outline image of the content in the to-be-detected luggage, comparing the outline image with the standard image in the animal image library, judging whether the to-be-detected luggage contains an animal or not, and obtaining a first comparison result;
the second comparison module is used for identifying the central position of each content in all the video frame images through an artificial intelligence algorithm and comparing the central positions of the same content in all the extracted video frame images to obtain a second comparison result;
the combination module is used for combining the first comparison result and the second comparison result to judge whether animals exist in the luggage to be detected; wherein the first alignment result and the second alignment result are combined by the following formula:
wherein R is the result of the binding, C1 is the first alignment, and C2 is the second alignment.
9. The apparatus of claim 8, further comprising:
the first judgment module is used for directly judging that animals exist in the to-be-detected luggage when the first comparison result exceeds a first comparison threshold;
and the second judgment module is used for directly judging that the animal exists in the to-be-detected luggage when the second comparison result exceeds a second comparison threshold value.
10. The apparatus of claim 8, wherein the first comparison module comprises:
the extraction unit is used for at least extracting video frame images including a first frame image of the luggage to be detected entering the security inspection channel and a last frame image of the luggage to be detected leaving the security inspection channel;
a completion unit configured to form a comparison image of the contour of each content by completing the contour images of the same content identified in all the video frame images;
and the comparison unit is used for comparing the outline comparison image of each content with a standard image in an animal image library and judging whether an animal exists in the luggage to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010078895.6A CN111325114B (en) | 2020-02-03 | 2020-02-03 | Security image processing method and device for artificial intelligence recognition classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010078895.6A CN111325114B (en) | 2020-02-03 | 2020-02-03 | Security image processing method and device for artificial intelligence recognition classification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325114A true CN111325114A (en) | 2020-06-23 |
| CN111325114B CN111325114B (en) | 2022-07-19 |
Family
ID=71168876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010078895.6A Active CN111325114B (en) | 2020-02-03 | 2020-02-03 | Security image processing method and device for artificial intelligence recognition classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325114B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113552118A (en) * | 2021-07-15 | 2021-10-26 | 海口市骨科与糖尿病医院(上海市第六人民医院海口骨科与糖尿病医院) | Detection method for indicating card in surgical instrument package |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7109853B1 (en) * | 1999-04-26 | 2006-09-19 | Cherry Corporation | System for detecting and releasing a person locked in the trunk of a vehicle |
| US20120275646A1 (en) * | 2009-07-31 | 2012-11-01 | Optosecurity Inc. | Method, apparatus and system for determining if a piece of luggage contains a liquid product |
| EP2734447A1 (en) * | 2011-07-19 | 2014-05-28 | Vanderlande Industries B.V. | Conveying system for pieces of luggage, check-in system comprising such a conveying system and method for using such a conveying system |
| WO2015161717A1 (en) * | 2014-04-24 | 2015-10-29 | 北京君和信达科技有限公司 | Method and system for conducting radiative inspection on rapid-pass moving object |
| US20180157932A1 (en) * | 2016-12-05 | 2018-06-07 | Sap Se | Systems and methods for integrated cargo inspection |
| CN109978827A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Violated object recognition methods, device, equipment and storage medium based on artificial intelligence |
| CN110008859A (en) * | 2019-03-20 | 2019-07-12 | 北京迈格威科技有限公司 | The dog of view-based access control model only recognition methods and device again |
| US20190347823A1 (en) * | 2018-05-10 | 2019-11-14 | Beijing Sensetime Technology Development Co., Ltd | Method and apparatus for detecting living body, system, electronic device, and storage medium |
| US20190362171A1 (en) * | 2018-05-25 | 2019-11-28 | Beijing Kuangshi Technology Co., Ltd. | Living body detection method, electronic device and computer readable medium |
-
2020
- 2020-02-03 CN CN202010078895.6A patent/CN111325114B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7109853B1 (en) * | 1999-04-26 | 2006-09-19 | Cherry Corporation | System for detecting and releasing a person locked in the trunk of a vehicle |
| US20120275646A1 (en) * | 2009-07-31 | 2012-11-01 | Optosecurity Inc. | Method, apparatus and system for determining if a piece of luggage contains a liquid product |
| EP2734447A1 (en) * | 2011-07-19 | 2014-05-28 | Vanderlande Industries B.V. | Conveying system for pieces of luggage, check-in system comprising such a conveying system and method for using such a conveying system |
| US20140168374A1 (en) * | 2011-07-19 | 2014-06-19 | Vanderlande Industries B.V. | Conveying system for pieces of luggage, check-in system comprising such a conveying system and method for using such a conveying system |
| WO2015161717A1 (en) * | 2014-04-24 | 2015-10-29 | 北京君和信达科技有限公司 | Method and system for conducting radiative inspection on rapid-pass moving object |
| US20180157932A1 (en) * | 2016-12-05 | 2018-06-07 | Sap Se | Systems and methods for integrated cargo inspection |
| US20190347823A1 (en) * | 2018-05-10 | 2019-11-14 | Beijing Sensetime Technology Development Co., Ltd | Method and apparatus for detecting living body, system, electronic device, and storage medium |
| US20190362171A1 (en) * | 2018-05-25 | 2019-11-28 | Beijing Kuangshi Technology Co., Ltd. | Living body detection method, electronic device and computer readable medium |
| CN109978827A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Violated object recognition methods, device, equipment and storage medium based on artificial intelligence |
| CN110008859A (en) * | 2019-03-20 | 2019-07-12 | 北京迈格威科技有限公司 | The dog of view-based access control model only recognition methods and device again |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113552118A (en) * | 2021-07-15 | 2021-10-26 | 海口市骨科与糖尿病医院(上海市第六人民医院海口骨科与糖尿病医院) | Detection method for indicating card in surgical instrument package |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325114B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210056498A1 (en) | Method and device for identifying product purchased by user and intelligent shelf system | |
| US11620898B2 (en) | Visual-acoustic monitoring system for event detection, localization and classification | |
| KR102189205B1 (en) | System and method for generating an activity summary of a person | |
| US9008365B2 (en) | Systems and methods for pedestrian detection in images | |
| CN110046560B (en) | Dangerous driving behavior detection method and camera | |
| KR102429739B1 (en) | Method and apparatus for recognizing illegal behavior in unattended scenario | |
| US6396433B1 (en) | Talking buried object detector | |
| JP2019532387A (en) | Infant detection for electronic gate environments | |
| EP2413265B1 (en) | A system and method for classification of moving object during video surveillance | |
| US10095931B2 (en) | Store-entering person attribute extraction apparatus, store-entering person attribute extraction method, and non-transitory computer readable medium | |
| CN106778559A (en) | The method and device of In vivo detection | |
| AU2013204156B2 (en) | Classification apparatus and program | |
| CN113989702A (en) | Target identification method and device | |
| CN111325114B (en) | Security image processing method and device for artificial intelligence recognition classification | |
| KR20160096905A (en) | Apparatus and method for detecting snoring | |
| JPWO2020195376A1 (en) | Monitoring device, suspicious object detection method, and program | |
| JP2020042785A (en) | Method, apparatus, device and storage medium for identifying passenger state in unmanned vehicle | |
| EP0955557A3 (en) | Method and system for detecting/classifying objects | |
| CN111753658A (en) | Post sleep warning method and device and computer equipment | |
| KR101107120B1 (en) | Device for sound source tracing and object recognition and method for sound source tracing and object recognition | |
| CN112668377A (en) | Information recognition system and method thereof | |
| US9866799B1 (en) | Video monitoring system for an exit | |
| US11410462B2 (en) | Processing system and processing method | |
| CN112380977A (en) | Smoking behavior detection method and device | |
| US9483925B1 (en) | Automatic system and method for detecting presence of people or animals in a vehicle |
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 |