CN113965729B - Regional safety monitoring system and method - Google Patents
Regional safety monitoring system and method Download PDFInfo
- Publication number
- CN113965729B CN113965729B CN202111267943.7A CN202111267943A CN113965729B CN 113965729 B CN113965729 B CN 113965729B CN 202111267943 A CN202111267943 A CN 202111267943A CN 113965729 B CN113965729 B CN 113965729B
- Authority
- CN
- China
- Prior art keywords
- image
- difference
- images
- image library
- pixel points
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000005236 sound signal Effects 0.000 claims abstract description 21
- 238000012795 verification Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000010206 sensitivity analysis Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000470 constituent Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/57—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for processing of video signals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a regional safety monitoring system and a regional safety monitoring method, wherein the regional safety monitoring system comprises: the monitoring end is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal; the monitoring end is also used for generating a target image library, and the target image library comprises the area image and the difference image; the center platform is used for receiving an operation request of a user and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established; the method is also used for acquiring the target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image; and operating the region images in the extracted information image group based on the operation request, and generating feedback information. The invention has the advantages of extremely strong information extraction capability, high utilization rate of computing resources and convenient popularization and use.
Description
Technical Field
The invention belongs to the technical field of remote monitoring, and particularly relates to a regional safety monitoring system and a regional safety monitoring method.
Background
With the development of computer technology and network technology, the current security management work is mostly completed by means of a monitoring system, information of a certain area is obtained in real time through a monitoring end, and then the actual situation is analyzed according to the information; in the process, the data volume acquired by the monitoring end is extremely large, most of the data volume is invalid information, the utilization rate of computing resources is extremely low, and the analysis difficulty of staff is also high, because the information extraction capacity is almost zero in the existing monitoring system.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a regional security monitoring system and a regional security monitoring method so as to improve the information extraction capability and the computing resource utilization rate.
In order to solve the above technical problems, the present invention provides an area security monitoring system, including:
the monitoring end is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal; the monitoring end is further used for generating a target image library, and the target image library comprises the region image and a difference image generated according to the time information;
the center platform is used for receiving an operation request of a user and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established; the method is also used for acquiring the target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image; and operating the region images in the extracted information image group based on the operation request, and generating feedback information.
Further, the monitoring terminal includes:
the image acquisition module is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal;
the screening module is used for judging whether the area image is a dynamic image or not, and marking the area image when the area image is the dynamic image;
the sequencing calculation module is used for counting the marked area images, sequencing the area images according to the time information of the area images, and sequentially calculating the time difference values of the adjacent area images;
the image library generating module is used for generating a difference image according to the time difference value, inserting the difference image into the sequenced regional images and generating a target image library; the region images and the difference images in the target image library are distributed at intervals.
Further, the center platform includes:
the identity verification module is used for receiving an operation request of a user and carrying out identity verification on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
the image extraction module is used for acquiring a target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image;
and the feedback module is used for operating the region images in the extracted information image group based on the operation request and generating feedback information.
Further, the image acquisition module includes:
the fluctuation identification unit is used for acquiring an audio signal, carrying out fluctuation identification on the audio signal and obtaining an effective wave band according to a fluctuation identification result;
the voice recognition unit is used for carrying out voice recognition on the effective wave band, judging whether the effective wave band is a voice signal, and carrying out voice recognition on the effective wave band when the effective wave band is the voice signal;
and the sensitivity analysis unit is used for generating a text according to the voice recognition result, carrying out sensitivity analysis on the text, and adjusting the dangerous field image acquisition frequency when the text is a sensitive text.
Further, the sensitive analysis unit comprises:
a symbol deleting subunit, configured to generate a text according to the speech recognition result, and delete symbols in the text to obtain a plain text file;
the first execution subunit is used for sequentially reading the characters in the plain text file, inputting the characters into a trained sensitive analysis model, judging whether the characters are sensitive characters, and marking the characters when the characters are sensitive characters;
the ratio calculating subunit is used for counting marked characters to obtain the number of marks, and calculating the ratio of the number of marks to the number of characters of the plain text file;
and the frequency adjustment subunit is used for judging the text as the sensitive text and adjusting the acquisition frequency of the dangerous field image when the ratio exceeds a preset sensitive threshold value.
Further, the image extraction module includes:
the reading unit is used for acquiring a target image library according to the connecting channel, extracting difference images according to index items in the target image library, and obtaining a difference image library based on time sequence sequencing;
the contour recognition unit is used for carrying out contour recognition on the difference images in the difference image library to obtain characteristic contours; comparing the characteristic profile with a preset reference profile to determine a time difference value;
the comparison unit is used for comparing the time difference value with a preset time threshold value, and marking a corresponding difference image when the time difference value is smaller than the preset time threshold value;
and the image group positioning unit is used for extracting adjacent area images according to the marked difference images to obtain an information image group.
Further, the contour recognition unit includes:
the color value acquisition subunit is used for reading the difference images in the difference image library, traversing pixel points in the difference images and acquiring color values of the pixel points;
the pixel point marking subunit is used for sequentially reading the color values of the adjacent pixel points, judging the size between the color value difference of the adjacent pixel points and a preset tolerance, marking the pixel points if the color value difference of the adjacent pixel points is larger than the tolerance, and continuously reading the next adjacent pixel points if the color value difference of the adjacent pixel points is smaller than the tolerance;
and the second execution subunit is used for generating a characteristic contour based on the marked pixel points.
The invention also provides a regional safety monitoring method which is applied to the center platform and comprises the following steps:
receiving an operation request of a user, and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
acquiring a target image library according to the connecting channel, extracting a difference image in the target image library, and extracting an information image group according to the difference image;
operating the region images in the extracted information image group based on the operation request, and generating feedback information;
the target image library is generated by a monitoring end, and comprises region images and difference images, wherein the region images and the difference images in the target image library are distributed at intervals.
Further, the step of obtaining a target image library according to the connection channel, extracting a difference image in the target image library, and extracting an information image group according to the difference image includes:
acquiring a target image library according to the connecting channel, and extracting a difference image according to index items in the target image library to obtain a difference image library based on time sequence sequencing;
performing contour recognition on the difference images in the difference image library to obtain characteristic contours; comparing the characteristic profile with a preset reference profile to determine a time difference value;
comparing the time difference value with a preset time threshold value, and marking a corresponding difference image when the time difference value is smaller than the preset time threshold value;
and extracting adjacent area images according to the marked difference images to obtain an information image group.
Further, the step of performing contour recognition on the difference images in the difference image library to obtain a feature contour includes:
reading a difference image in a difference image library, traversing pixel points in the difference image, and obtaining color values of the pixel points;
sequentially reading the color values of adjacent pixel points, judging the size between the color value difference of the adjacent pixel points and a preset tolerance, marking the pixel points if the color value difference of the adjacent pixel points is larger than the tolerance, and continuously reading the next adjacent pixel points if the color value difference of the adjacent pixel points is smaller than the tolerance;
a feature profile is generated based on the labeled pixels.
The implementation of the invention has the following beneficial effects: the method comprises the steps that a monitoring end obtains an area image, and a target image library containing difference images is generated based on the area image; the method and the system have the advantages that the operation request of the user is received through the center platform, and the feedback is made based on the target image library, so that the information extraction capability is extremely strong, the utilization rate of computing resources is high, and the popularization and the use are convenient.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram showing the constitution of an area security monitoring system according to an embodiment of the present invention.
Fig. 2 is a block diagram showing the constitution of a monitor terminal according to a first embodiment of the present invention.
Fig. 3 is a block diagram showing the structure of an image acquisition module in a monitoring terminal according to the first embodiment of the present invention.
Fig. 4 is a block diagram showing the constitution of a sensitive analysis unit in an image acquisition module according to the first embodiment of the present invention.
Fig. 5 is a block diagram showing the constitution of a center platform in the first embodiment of the present invention.
Fig. 6 is a block diagram showing the structure of an image extraction module in a central platform according to the first embodiment of the present invention.
Fig. 7 is a block diagram showing the constitution of a contour recognition unit in an image extraction module according to the first embodiment of the present invention.
Fig. 8 is a flow chart of a regional security monitoring method according to a second embodiment of the present invention.
Fig. 9 shows a first sub-flowchart of the second embodiment of the present invention.
Fig. 10 shows a second sub-flowchart of the second embodiment of the present invention.
Detailed Description
The following description of embodiments refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced.
Referring to fig. 1, the present invention provides a regional security monitoring system, which includes:
the monitoring end 10 is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal; the region image contains time information, and the monitoring terminal 10 is further configured to generate a target image library, where the target image library includes the region image and a difference image generated according to the time information;
the central platform 20 is configured to receive an operation request of a user, and perform identity authentication on the user according to a type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established; the method is also used for acquiring the target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image; and operating the region images in the extracted information image group based on the operation request, and generating feedback information.
In this embodiment, the regional security monitoring system includes two parts, namely, a monitoring end 10 and a central platform 20; the monitoring end is used for acquiring area images, and as for the acquired images of the areas, the images are related to actual application scenes, and the areas, road conditions or schools and the like can be one of the areas; the monitoring terminal 10 is different from the prior art in that the image library generated by the monitoring terminal 10 includes a difference image, which can be understood as an image with a difference, for example, the background of the image is white, then the data representing the time is represented by black, and the purpose of generating the image is to build a unified target image library with the image as an element. The central platform 20 is the end that interacts with the user, and the user has many requests for operations, such as querying, extracting, analyzing, etc., and samples of these operations are information image groups in the target image library. In popular terms, only a small portion of the images acquired by a monitoring terminal 10 are useful and contain much information, the purpose of which is to extract images with much information.
Referring to fig. 2 again, in this embodiment, the functions of the monitoring end are subdivided, and different modules individually complete the corresponding functions, where the monitoring end 10 specifically includes:
the image acquisition module 11 is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal;
a screening module 12, configured to determine whether the area image is a dynamic image, and mark the area image when the area image is a dynamic image;
a sorting calculation module 13, configured to count marked area images, sort the area images according to time information of the area images, and sequentially calculate time difference values of adjacent area images;
the image library generating module 14 is configured to generate a difference image according to the time difference value, insert the difference image into the sorted region images, and generate a target image library; the region images and the difference images in the target image library are distributed at intervals.
Further, referring to fig. 3 again, the image acquisition module 11 in the monitoring end specifically includes:
a fluctuation recognition unit 111, configured to obtain an audio signal, perform fluctuation recognition on the audio signal, and obtain an effective band according to a fluctuation recognition result;
a voice recognition unit 112, configured to perform voice recognition on the effective band, determine whether the effective band is a voice signal, and perform voice recognition on the effective band when the effective band is the voice signal;
and the sensitivity analysis unit 113 is used for generating a text according to the voice recognition result, performing sensitivity analysis on the text, and adjusting the dangerous field image acquisition frequency when the text is a sensitive text.
The above describes the image acquisition module 11 in detail, in the image acquisition process, the image acquisition frequency is an important parameter, the image acquisition frequency is high, the more the acquired images are, the more accurate the subsequent operations based on the images are, but the corresponding computing resources are also high, and the purpose of the invention is to extract the key images, including the images with more information, and optimize from the view of the image acquisition frequency, thereby playing the role of reducing the resource pressure.
Firstly, the fluctuation identification needs to be carried out on an audio signal, a stable audio is low in probability of being intentional information no matter how high the intensity of the stable audio is, and the audio which continuously fluctuates is likely to be human voice, so that the stable audio is of course meaningful; of course, there are many sounds that are constantly fluctuating in addition to the human voice, such as the sound of a thunder, and therefore, after the effective band is acquired, a voice recognition process determines whether it is a human voice signal.
Fig. 4 shows a composition structure of a sensitive analysis unit in the image acquisition module, and the sensitive analysis unit 113 specifically includes:
a symbol deleting subunit 1131, configured to generate a text according to the speech recognition result, delete symbols in the text, and obtain a plain text file;
the first execution subunit 1132 is configured to sequentially read the characters in the plain text file, input the characters into a trained sensitive analysis model, determine whether the characters are sensitive characters, and mark the characters when the characters are sensitive characters;
the ratio calculating subunit 1133 is configured to count the marked characters to obtain a number of marks, and calculate a ratio of the number of marks to the number of characters of the plain text file;
and the frequency adjustment subunit 1134 is configured to determine that the text is a sensitive text and adjust the acquisition frequency of the dangerous field image when the ratio exceeds a preset sensitivity threshold.
If the voice signal is the voice signal, further detecting the voice signal in a way of converting the voice signal into a text, analyzing the text to judge whether the voice signal is meaningful or not, and further extracting useful information; in addition, some misjudgment cases, such as a section of non-human voice signal, may be filtered, and it is possible to detect adult voice signals due to similarity with human voice signals, but text obtained according to the non-human voice signals is mostly nonsensical phrase or phrase.
Referring to fig. 5 again, in this embodiment, the functions of the center platform are subdivided, and different modules individually complete the corresponding functions, and the center platform 20 specifically includes:
the identity verification module 21 is configured to receive an operation request of a user, and perform identity verification on the user according to a type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
the image extraction module 22 is configured to obtain a target image library according to the connection channel, extract a difference image in the target image library, and extract an information image group according to the difference image;
and a feedback module 23, configured to operate on the region images in the extracted information image group based on the operation request, and generate feedback information.
Fig. 6 shows the composition of an image extraction module in the center platform, and the image extraction module 22 specifically includes:
a reading unit 221, configured to obtain a target image library according to the connection channel, extract a difference image according to an index item in the target image library, and obtain a difference image library based on time sequence ordering;
the contour recognition unit 222 is configured to perform contour recognition on the difference images in the difference image library to obtain a feature contour; comparing the characteristic profile with a preset reference profile to determine a time difference value;
a comparison unit 223, configured to compare the time difference value with a preset time threshold, and mark a corresponding difference image when the time difference value is smaller than the preset time threshold;
and an image group positioning unit 224, configured to extract adjacent area images according to the marked difference images, and obtain an information image group.
The above-mentioned function is to analyze the difference image, extract the time difference from the difference image, the precondition of this scheme is that the contrast of the difference image should be as high as possible, especially the difference between the time difference and the background, the most common way is white paper black word, the invention is not limited further.
Fig. 7 shows a constituent structure of a contour recognition unit in the image extraction module, and the contour recognition unit 222 specifically includes:
the color value obtaining subunit 2221 is configured to read a difference image in a difference image library, traverse a pixel point in the difference image, and obtain a color value of the pixel point;
the pixel point marking subunit 2222 is configured to sequentially read the color values of the adjacent pixel points, determine the size between the color value difference of the adjacent pixel points and a preset tolerance, mark the pixel points if the color value difference of the adjacent pixel points is greater than the tolerance, and continuously read the next adjacent pixel points if the color value difference of the adjacent pixel points is less than the tolerance;
a second execution subunit 2223 is configured to generate a feature profile based on the labeled pixel points.
The above is similar to magic wand tools in Photoshop software, and since the difference image of the present invention is determined by the monitoring terminal 10, the determination mode is determined by the developer according to the actual situation, and in general, the color value difference between the outline to be identified and the background is large, and the accuracy of the identification process is extremely high.
Referring to fig. 8, a regional security monitoring method according to a second embodiment of the present invention is applied to the center platform according to the first embodiment of the present invention, and the regional security monitoring method includes:
step S100, receiving an operation request of a user, and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
step S200, a target image library is obtained according to the connecting channel, a difference image in the target image library is extracted, and an information image group is extracted according to the difference image;
step S300, operating the region images in the extracted information image group based on the operation request, and generating feedback information;
the target image library is generated by a monitoring end, and comprises region images and difference images, wherein the region images and the difference images in the target image library are distributed at intervals.
Specifically, referring to fig. 9, the steps of obtaining a target image library according to the connection channel, extracting a difference image in the target image library, and extracting an information image group according to the difference image specifically include:
step S201, a target image library is obtained according to the connecting channel, and difference images are extracted according to index items in the target image library, so that a difference image library based on time sequence ordering is obtained;
step S202, carrying out contour recognition on the difference images in the difference image library to obtain characteristic contours; comparing the characteristic profile with a preset reference profile to determine a time difference value;
step S203, comparing the time difference value with a preset time threshold value, and marking a corresponding difference image when the time difference value is smaller than the preset time threshold value;
step S204, extracting adjacent area images according to the marked difference images to obtain an information image group.
Referring to fig. 10 again, the step of performing contour recognition on the difference images in the difference image library to obtain a feature contour includes:
step S2021, reading a difference image in a difference image library, traversing pixel points in the difference image, and obtaining color values of the pixel points;
step S2022, sequentially reading the color values of the adjacent pixels, judging the size between the color value difference of the adjacent pixels and a preset tolerance, if the color value difference of the adjacent pixels is larger than the tolerance, marking the pixels, and if the color value difference of the adjacent pixels is smaller than the tolerance, continuing to read the next adjacent pixels;
in step S2023, a feature profile is generated based on the labeled pixel points.
As can be seen from the above description, compared with the prior art, the invention has the following beneficial effects: the method comprises the steps that a monitoring end obtains an area image, and a target image library containing difference images is generated based on the area image; the method and the system have the advantages that the operation request of the user is received through the center platform, and the feedback is made based on the target image library, so that the information extraction capability is extremely strong, the utilization rate of computing resources is high, and the popularization and the use are convenient.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (6)
1. An area security monitoring system, comprising:
the monitoring end is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal; the monitoring end is further used for generating a target image library, and the target image library comprises the region image and a difference image generated according to the time information;
the center platform is used for receiving an operation request of a user and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established; the method is also used for acquiring the target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image; operating the region images in the extracted information image group based on the operation request, and generating feedback information;
the monitoring end comprises:
the image acquisition module is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode of the monitoring end based on the audio signal;
the screening module is used for judging whether the area image is a dynamic image or not, and marking the area image when the area image is the dynamic image;
the sequencing calculation module is used for counting the marked area images, sequencing the area images according to the time information of the area images, and sequentially calculating the time difference values of the adjacent area images;
the image library generating module is used for generating a difference image according to the time difference value, inserting the difference image into the sequenced regional images and generating a target image library; the region images and the difference images in the target image library are distributed at intervals;
the image acquisition module includes:
the fluctuation identification unit is used for acquiring an audio signal, carrying out fluctuation identification on the audio signal and obtaining an effective wave band according to a fluctuation identification result;
the voice recognition unit is used for carrying out voice recognition on the effective wave band, judging whether the effective wave band is a voice signal, and carrying out voice recognition on the effective wave band when the effective wave band is the voice signal;
the sensitivity analysis unit is used for generating a text according to the voice recognition result, carrying out sensitivity analysis on the text, and adjusting the dangerous field image acquisition frequency when the text is a sensitive text;
the center platform includes:
the identity verification module is used for receiving an operation request of a user and carrying out identity verification on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
the image extraction module is used for acquiring a target image library according to the connecting channel, extracting a difference image in the target image library and extracting an information image group according to the difference image;
the feedback module is used for operating the region images in the extracted information image group based on the operation request and generating feedback information;
the image extraction module includes:
the reading unit is used for acquiring a target image library according to the connecting channel, extracting difference images according to index items in the target image library, and obtaining a difference image library based on time sequence sequencing;
the contour recognition unit is used for carrying out contour recognition on the difference images in the difference image library to obtain characteristic contours; comparing the characteristic profile with a preset reference profile to determine a time difference value;
the comparison unit is used for comparing the time difference value with a preset time threshold value, and marking a corresponding difference image when the time difference value is smaller than the preset time threshold value;
and the image group positioning unit is used for extracting adjacent area images according to the marked difference images to obtain an information image group.
2. The zonal security monitoring system of claim 1, wherein the sensitive analysis unit comprises:
a symbol deleting subunit, configured to generate a text according to the speech recognition result, and delete symbols in the text to obtain a plain text file;
the first execution subunit is used for sequentially reading the characters in the plain text file, inputting the characters into a trained sensitive analysis model, judging whether the characters are sensitive characters, and marking the characters when the characters are sensitive characters;
the ratio calculating subunit is used for counting marked characters to obtain the number of marks, and calculating the ratio of the number of marks to the number of characters of the plain text file;
and the frequency adjustment subunit is used for judging the text as the sensitive text and adjusting the acquisition frequency of the dangerous field image when the ratio exceeds a preset sensitive threshold value.
3. The zonal security monitoring system according to claim 1, wherein the profile recognition unit includes:
the color value acquisition subunit is used for reading the difference images in the difference image library, traversing pixel points in the difference images and acquiring color values of the pixel points;
the pixel point marking subunit is used for sequentially reading the color values of the adjacent pixel points, judging the size between the color value difference of the adjacent pixel points and a preset tolerance, marking the pixel points if the color value difference of the adjacent pixel points is larger than the tolerance, and continuously reading the next adjacent pixel points if the color value difference of the adjacent pixel points is smaller than the tolerance;
and the second execution subunit is used for generating a characteristic contour based on the marked pixel points.
4. A zonal security monitoring method, wherein the zonal security monitoring method is applied to the zonal security monitoring system according to any one of claims 1 to 3, the zonal security monitoring method comprising:
receiving an operation request of a user, and carrying out identity authentication on the user according to the type of the operation request; when the identity verification passes, a connection channel with the monitoring end is established;
acquiring a target image library according to the connecting channel, extracting a difference image in the target image library, and extracting an information image group according to the difference image;
operating the region images in the extracted information image group based on the operation request, and generating feedback information;
the target image library is generated by a monitoring end, and comprises region images and difference images, wherein the region images and the difference images in the target image library are distributed at intervals.
5. The regional security monitoring method of claim 4, wherein the steps of acquiring a target image library according to the connection channel, extracting a difference image in the target image library, and extracting an information image group according to the difference image comprise:
acquiring a target image library according to the connecting channel, and extracting a difference image according to index items in the target image library to obtain a difference image library based on time sequence sequencing;
performing contour recognition on the difference images in the difference image library to obtain characteristic contours; comparing the characteristic profile with a preset reference profile to determine a time difference value;
comparing the time difference value with a preset time threshold value, and marking a corresponding difference image when the time difference value is smaller than the preset time threshold value;
and extracting adjacent area images according to the marked difference images to obtain an information image group.
6. The regional security monitoring method of claim 5, wherein the step of performing contour recognition on the difference images in the difference image library to obtain the feature contour comprises:
reading a difference image in a difference image library, traversing pixel points in the difference image, and obtaining color values of the pixel points;
sequentially reading the color values of adjacent pixel points, judging the size between the color value difference of the adjacent pixel points and a preset tolerance, marking the pixel points if the color value difference of the adjacent pixel points is larger than the tolerance, and continuously reading the next adjacent pixel points if the color value difference of the adjacent pixel points is smaller than the tolerance;
a feature profile is generated based on the labeled pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111267943.7A CN113965729B (en) | 2021-10-29 | 2021-10-29 | Regional safety monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111267943.7A CN113965729B (en) | 2021-10-29 | 2021-10-29 | Regional safety monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113965729A CN113965729A (en) | 2022-01-21 |
| CN113965729B true CN113965729B (en) | 2023-12-26 |
Family
ID=79468295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111267943.7A Active CN113965729B (en) | 2021-10-29 | 2021-10-29 | Regional safety monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113965729B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182990A (en) * | 2014-08-12 | 2014-12-03 | 中国科学院上海微系统与信息技术研究所 | A method for acquiring a sequence image motion target area in real-time |
| CN110445954A (en) * | 2019-07-26 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Image-pickup method, device and electronic equipment |
| CN110472623A (en) * | 2019-06-29 | 2019-11-19 | 华为技术有限公司 | Image detecting method, equipment and system |
| CN113542692A (en) * | 2021-07-19 | 2021-10-22 | 临沂边锋自动化设备有限公司 | Face recognition system and method based on monitoring video |
-
2021
- 2021-10-29 CN CN202111267943.7A patent/CN113965729B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182990A (en) * | 2014-08-12 | 2014-12-03 | 中国科学院上海微系统与信息技术研究所 | A method for acquiring a sequence image motion target area in real-time |
| CN110472623A (en) * | 2019-06-29 | 2019-11-19 | 华为技术有限公司 | Image detecting method, equipment and system |
| CN110445954A (en) * | 2019-07-26 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Image-pickup method, device and electronic equipment |
| CN113542692A (en) * | 2021-07-19 | 2021-10-22 | 临沂边锋自动化设备有限公司 | Face recognition system and method based on monitoring video |
Non-Patent Citations (1)
| Title |
|---|
| 吴吴诺.视频跟踪算法在安防辅助定位中的应用.数字技术与应用.2011,(05),51-52. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113965729A (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147726B (en) | Service quality inspection method and device, storage medium and electronic device | |
| CN108108902B (en) | Risk event warning method and device | |
| CN111583180B (en) | Image tampering identification method and device, computer equipment and storage medium | |
| CN110287311B (en) | Text classification method and device, storage medium and computer equipment | |
| US20190205589A1 (en) | Latent fingerprint ridge flow map improvement | |
| CN111932363A (en) | Identification and verification method, device, equipment and system for authorization book | |
| CN110765292A (en) | Image retrieval method, training method and related device | |
| CN105138886B (en) | Robot biometric identification system | |
| CN115953123A (en) | Method, device and equipment for generating robot automation flow and storage medium | |
| CN111553241A (en) | Method, device and equipment for rejecting mismatching points of palm print and storage medium | |
| CN114722199A (en) | Risk identification method and device based on call recording, computer equipment and medium | |
| CN112163019B (en) | Trusted electronic batch record processing method based on block chain and block chain service platform | |
| CN113965729B (en) | Regional safety monitoring system and method | |
| CN112669850A (en) | Voice quality detection method and device, computer equipment and storage medium | |
| CN114817518B (en) | License handling method, system and medium based on big data archive identification | |
| CN116110066A (en) | Information extraction method, device and equipment of bill text and storage medium | |
| CN116343300A (en) | Face feature labeling method, device, terminal and medium | |
| US20230084845A1 (en) | Entry detection and recognition for custom forms | |
| CN115393867A (en) | Text recognition model generation method, text recognition device, and storage medium | |
| CN117827991B (en) | Method and system for identifying personal identification information in semi-structured data | |
| CN115375954B (en) | Chemical experiment solution identification method, device, equipment and readable storage medium | |
| CN116306576B (en) | Book printing error detection system and method thereof | |
| CN111507085B (en) | Sentence pattern recognition method | |
| CN111783447B (en) | Sensitive word detection method, device and equipment based on ngram distance and storage medium | |
| CN109325126B (en) | Method and device for objectification processing of language text and computer storage medium |
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 |