CN113542692A - Face recognition system and method based on monitoring video - Google Patents
Face recognition system and method based on monitoring video Download PDFInfo
- Publication number
- CN113542692A CN113542692A CN202110811688.1A CN202110811688A CN113542692A CN 113542692 A CN113542692 A CN 113542692A CN 202110811688 A CN202110811688 A CN 202110811688A CN 113542692 A CN113542692 A CN 113542692A
- Authority
- CN
- China
- Prior art keywords
- determining
- image
- face
- information
- area
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000005236 sound signal Effects 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000003550 marker Substances 0.000 claims description 4
- 238000011161 development Methods 0.000 abstract description 3
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 19
- 230000015654 memory Effects 0.000 description 15
- 230000006870 function Effects 0.000 description 14
- 238000004590 computer program Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 4
- 241001465754 Metazoa Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 241001061106 Sargocentron rubrum Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of monitoring information processing, and particularly discloses a face recognition system and a face recognition method based on a monitoring video, wherein the system comprises a monitoring end and a central platform, and the monitoring end comprises an adjusting unit, a target image generating unit and a positioning and sending unit; the central platform comprises a receiving unit, an information area determining unit, a face area determining unit and an executing unit; the execution unit is used for identifying ear information in the face area, acquiring a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and performing face identification based on the face orientation. According to the invention, information is selectively acquired by a monitoring terminal, a face area is screened out by a central platform, the face orientation is determined according to ear information and monitoring end positions in the face area, and then different identification modes are determined for face identification; the invention has high resource utilization rate and strong recognition capability and is convenient for secondary development.
Description
Technical Field
The invention relates to the technical field of monitoring information processing, in particular to a face recognition system and method based on a monitoring video.
Background
With the popularization of computer equipment and the development of network technology, monitoring equipment gradually enters our lives, and cameras are often installed in factories and families, so that remote monitoring is realized; it can be imagined that the purpose of our installation monitoring is absolutely not to see a still thing, but we would rather see a visitor.
Most visitors have identities, and a monitor at a monitoring end can easily judge the personal identities, but once a life civil dispute or criminal case occurs, the camera serves as the identity similar to a witness, and can possibly monitor strangers, so that the strangers need to be subjected to face recognition to determine the identities.
The existing face recognition technology is usually a front face and is mostly suitable for the payment process, and in a monitoring video acquired by a camera, the situation of a front face rarely occurs, so that the face recognition process is difficult to proceed; therefore, it is meaningful to design a face recognition system based on the surveillance video.
Disclosure of Invention
The present invention provides a face recognition system and method based on a surveillance video, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a surveillance video based face recognition system, the system comprising:
the monitoring terminal is used for acquiring regional images and audio signals in real time and adjusting the image definition and the monitoring mode based on the audio signals; generating a target image based on the region image, and inserting a dynamic mark into the target image; receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform; wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer;
the central platform is used for sending an image acquisition request to the monitoring terminal and receiving a target image with a dynamic mark sent by the monitoring terminal; determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region; reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information; the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
As a further limitation of the technical solution of the present invention, the monitoring terminal includes:
the adjusting unit is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode based on the audio signal;
a target image generation unit configured to generate a target image based on the region image and insert a dynamic marker into the target image;
the positioning and sending unit is used for receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark and sending the target image to the central platform;
wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
As a further limitation of the technical solution of the present invention, the central platform comprises:
the receiving unit is used for sending an image acquisition request to the monitoring terminal and receiving a target image with a dynamic mark sent by the monitoring terminal;
the information area determining unit is used for determining a dynamic outline based on the target image, performing area identification on the dynamic outline and determining an information area;
the face area determining unit is used for reading temperature information in the information area and determining the face area based on the position relation of the information area and the temperature information;
and the execution unit is used for identifying ear information in the face area, acquiring a monitoring end position, determining the face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
As a further limitation of the technical solution of the present invention, the adjusting unit includes:
the first mean value calculation module is used for determining backtracking time, intercepting an audio signal based on the backtracking time and calculating an amplitude mean value;
the audio identification module is used for identifying the amplitude change rate determined based on the amplitude mean value, carrying out audio identification on the audio signal based on the amplitude change rate and judging whether the audio signal is a human sound signal based on an identification result;
and the instruction generating module is used for generating an image definition adjusting instruction and a monitoring mode adjusting instruction based on the judgment result.
As a further limitation of the technical solution of the present invention, the target image generating unit includes:
the second mean value calculation module is used for judging the type of the area image, and calculating a mean value of gray scale if the area image is a gray scale image;
the third mean value calculating module is used for carrying out gray level conversion on the color image to generate a gray level image and calculating a gray level mean value if the area image is the color image;
the first judgment module is used for determining a change threshold, judging the change rate of the gray-scale average value based on the change threshold and determining a target image based on a judgment result.
As a further limitation of the technical solution of the present invention, the information area determining unit includes:
the contour recognition module is used for reading target images in sequence and recognizing the contours of the target images;
the first calculation module is used for calculating the number of the contours and screening a target image based on the number of the contours;
the second calculation module is used for determining the position of the center point of each contour and calculating the offset distance of the position of the center point of each contour of the adjacent target images;
and the second judging module is used for determining a distance threshold, judging the size of the offset distance based on the distance threshold and determining the dynamic contour based on a judgment result.
As a further limitation of the technical solution of the present invention, the information area determining unit further includes:
the color value reading module is used for traversing the pixel points of the dynamic contour and reading corresponding color values;
a region contour determining module for determining tolerance, judging the size of color value difference of adjacent pixels based on the tolerance, determining region contour based on the judgment result,
and the screening module is used for calculating the number of pixel points in the area outline and screening the information area based on the number of the pixel points.
The technical scheme of the invention also provides a face recognition method based on the monitoring video, which is applied to a monitoring end and comprises the following steps:
acquiring regional images and audio signals in real time, and adjusting image definition and a monitoring mode based on the audio signals;
generating a target image based on the region image, and inserting a dynamic mark into the target image;
receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform;
wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
The technical scheme of the invention also provides a face recognition method based on the monitoring video, which is applied to a central platform and comprises the following steps:
sending an image acquisition request to a monitoring end, and receiving a target image with a dynamic mark sent by the monitoring end;
determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region;
reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information;
the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
As a further limitation of the technical solution of the present invention, the step of determining the dynamic contour based on the target image and performing region identification on the dynamic contour includes:
sequentially reading target images and carrying out contour recognition on the target images;
calculating the number of contours, and screening a target image based on the number of contours;
determining the position of the center point of each contour, and calculating the offset distance of the position of the center point of each contour of the adjacent target images;
determining a distance threshold, judging the size of the offset distance based on the distance threshold, and determining a dynamic profile based on a judgment result;
traversing the pixel points of the dynamic contour, and reading corresponding color values;
determining tolerance, judging the size of color value difference of adjacent pixels based on the tolerance, determining region contour based on the judgment result,
and calculating the number of pixel points in the area outline, and screening the information area based on the number of the pixel points.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps that a monitoring end obtains regional images and audio signals in real time, and image definition and a monitoring mode are adjusted based on the audio signals; generating a target image based on the region image, and inserting a dynamic mark into the target image; receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform; wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer; sending an image acquisition request to a monitoring end through a central platform, and receiving a target image with a dynamic mark sent by the monitoring end; determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region; reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information; the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
According to the invention, information is selectively acquired by a monitoring terminal, a face area is screened out by a central platform, the face orientation is determined according to ear information and monitoring end positions in the face area, and then different identification modes are determined for face identification; the invention has high resource utilization rate and strong recognition capability and is convenient for secondary development.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is an architecture diagram of a surveillance video based face recognition system.
Fig. 2 is a block diagram of a monitoring end in a face recognition system based on a monitoring video.
Fig. 3 is a block diagram of a central platform in a surveillance video-based face recognition system.
Fig. 4 is a block diagram of the structure of the adjusting unit in the monitoring end.
Fig. 5 is a block diagram of a structure of a target image generating unit in the monitoring end.
Fig. 6 is a block diagram of a first composition structure of an information area determination unit in a center platform.
Fig. 7 is a block diagram of a second composition structure of the information area determination unit in the center platform.
Fig. 8 is a first flow diagram of a surveillance video-based face recognition method.
Fig. 9 is a second flow chart of the face recognition method based on the surveillance video.
Fig. 10 is a sub-flow block diagram of a second flow block diagram in the surveillance video-based face recognition method.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, etc. may be used herein to describe various modules in embodiments of the invention, these modules should not be limited by these terms. These terms are only used to distinguish one type of module from another. For example, a first determination module may also be referred to as a second determination module without necessarily requiring or implying any such actual relationship or order between such entities or operations without departing from the scope of embodiments of the present invention. Similarly, the second determination module may also be referred to as the first determination module. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a diagram illustrating an architecture of a surveillance video-based face recognition system, in an embodiment of the present invention, a surveillance video-based face recognition system includes:
the monitoring terminal 10 is used for acquiring regional images and audio signals in real time and adjusting the image definition and the monitoring mode based on the audio signals; generating a target image based on the region image, and inserting a dynamic mark into the target image; receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform; wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer;
the central platform 20 is used for sending an image acquisition request to the monitoring terminal and receiving a target image with a dynamic mark sent by the monitoring terminal; determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region; reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information; the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
Specifically, the technical solution of the present invention may include a monitoring terminal 10, a central platform 20, and a network. The network may be the medium used to provide the communication link between the monitoring terminal 10 and the central platform 20. The network may include a variety of connection types, but the present invention is dominated by wireless communication links.
The monitoring terminal 10 has a communication function, an audio acquisition function and an image acquisition function, wherein the image acquisition function has at least two modes, namely a black-and-white mode and a color mode; the monitoring terminal 10 may be hardware or software. When the monitoring terminal 10 is hardware, it is at least an electronic device with communication and image acquisition functions, and the most common electronic device is a camera; when the monitoring terminal 10 is software, it can be installed in the electronic device. It may be implemented as multiple pieces of software or software modules, or as a single piece of software or software module. And is not particularly limited herein.
The central platform 20 may be hardware or software. When the central platform 20 is hardware, it may be implemented as a distributed service device group formed by a plurality of service devices, or may be implemented as a single service device. When the service device is software, it may be implemented as a plurality of software or software modules, or may be implemented as a single software or software module. And is not particularly limited herein.
It should be understood that the number of monitoring terminals 10 and center platforms 20 in fig. 1 is merely illustrative. There may be any number of monitoring terminals 10 and central platforms 20, as desired for the implementation.
The purpose of the monitoring end is to acquire a monitoring video, but the process of acquiring the monitoring video is not the video acquiring process of the traditional camera, and most obviously, the monitoring end can perform mode adjustment according to the acquired audio information when acquiring the monitoring video; in the technical scheme of the invention, the definition and the monitoring mode of an image are adjusted based on the audio signal, the definition can be adjusted, and the monitoring mode can be adjusted, so that the invention is a distinctive place, and the advantage is very outstanding in the process of acquiring portrait information, the higher the definition is, the better the definition is, but a scene can be imagined, and in a room, such as a room for storing files, most of the time is nobody, if a camera with ultrahigh performance is used, the waste of resources is avoided, but real-time monitoring is needed, and the time period for monitoring cannot be specified; if the technical scheme is the architecture of the invention, the specific monitoring mode can be determined according to the audio signal, and obviously, the mode not only reduces the resource waste, but also obtains excellent monitoring effect; of course, if a person silently steals a file, the method still obtains a blurred image, and in a special case, the capability of the technical scheme of the invention depends on the audio obtaining capability.
Furthermore, after the regional image is acquired, the target image is acquired, and the acquisition of the target image means the acquisition of a dynamic image, and because the purpose of the invention is to identify the face information in the monitoring video, the significance of the dynamic image is greater; certainly, after a dynamic image, that is, a target image is obtained, the monitoring end also needs to store the dynamic image, and for convenience of searching, the monitoring end inserts a mark, that is, the dynamic mark, into the target image.
The central platform interacts with a user on one hand and performs data transmission with the monitoring end on the other hand, and in the working process, the central platform sends an image acquisition request to the monitoring end, and the acquired image is a more meaningful target image.
After the target image is obtained, the central platform determines a dynamic contour based on the target image, performs region identification on the dynamic contour and determines an information region; the dynamic contours differ from the dynamic image (target image) by: the dynamic contour is a small area in the dynamic image; the dynamic contour is human body information, then, a human face needs to be positioned for face recognition, when the human face is positioned, the conventional face recognition process is carried out, and the following contents are detailed for how to position the human face.
Fig. 2 is a block diagram illustrating a structure of a monitoring end in a face recognition system based on a monitoring video, where the monitoring end 10 includes:
the adjusting unit 11 is configured to acquire an area image and an audio signal in real time, and adjust image definition and a monitoring mode based on the audio signal;
a target image generation unit 12 for generating a target image based on the region image and inserting a dynamic marker into the target image;
a positioning and sending unit 13, configured to receive an image acquisition request of a central platform, locate a target image based on the dynamic marker, and send the target image to the central platform;
wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
The monitoring end is divided into three parts, firstly, the image definition and the monitoring mode are adjusted based on the audio signal; secondly, generating a target image based on the area image and inserting a dynamic mark into the target image; thirdly, interacting with a central platform; the three parts are sequential, but the actual work is independent, and therefore, is done in three units, respectively.
Fig. 3 is a block diagram illustrating a structure of a central platform in a surveillance video-based face recognition system, where the central platform 20 includes:
the receiving unit 21 is configured to send an image acquisition request to the monitoring terminal, and receive a target image with a dynamic mark sent by the monitoring terminal;
an information area determination unit 22 configured to determine a dynamic contour based on the target image, perform area recognition on the dynamic contour, and determine an information area;
a face region determining unit 23, configured to read temperature information in the information region, and determine a face region based on a positional relationship of the information region and the temperature information;
and the execution unit 24 is configured to identify ear information in the face area, acquire a monitoring end position, determine a face orientation based on the monitoring end position and the ear information, and perform face identification based on the face orientation.
The central platform comprises four parts, namely, a first part for acquiring a target image with a dynamic mark; secondly, determining a dynamic contour; thirdly, determining a face area; fourthly, determining the face orientation, and selecting different face recognition algorithms. The fourth part, namely the function to be completed by the execution unit, is to acquire the face orientation and then perform face recognition, the face recognition process is essentially a process of feature extraction and comparison with a database, in the process, a side face is different from a front face, and different side faces are different, in the technical scheme of the invention, the execution unit determines the face orientation first, then connects with different databases, and adopts a corresponding recognition mode; the specific flow of determining the face orientation is described here by taking a specific example, if a camera is in the southeast corner, the camera is in the lower right corner in a top view, at this time, people indoors are all in the west of the camera, and at this time, after the face region is obtained, if the ear is on the left, the face is indicated to face the east side, and if the ear is on the right, the face is indicated to face the west side, so that the face orientation can be determined according to ear information.
Fig. 4 is a block diagram showing a structure of an adjusting unit in a monitoring terminal, where the adjusting unit 11 includes:
a first mean value calculating module 111, configured to determine a backtracking time, intercept an audio signal based on the backtracking time, and calculate an amplitude mean value;
an audio recognition module 112, configured to identify an amplitude change rate determined based on the amplitude mean, perform audio recognition on the audio signal based on the amplitude change rate, and determine whether the audio signal is a human voice signal based on a recognition result;
and the instruction generating module 113 is configured to generate an image definition adjusting instruction and a monitoring mode adjusting instruction based on the determination result.
The key point of the adjusting unit is audio recognition, firstly, there are many audio recognition modes, and the most conceivable one is to perform character conversion in real time, perform audio recognition according to converted characters, and judge whether the voice is human voice, but the degree of calculation required by the mode is very large, and the purpose of audio recognition is to improve efficiency, so that image acquisition is selectively performed, therefore, the recognition method with large degree of calculation is combined with the idea of the invention. In the above process, the method is an identification method for determining whether the audio signal has sudden change, for example, the audio in the first 10 minutes is selected, if the audio is still quiet, that is, the amplitude is small, at this time, a large-amplitude wave band suddenly exists, people can be considered to come, and then voice identification is performed.
Fig. 5 is a block diagram showing a structure of a target image generating unit in the monitoring terminal, where the target image generating unit 12 includes:
a second mean value calculating module 121, configured to determine the type of the area image, and calculate a mean value of gray scales if the area image is a gray scale image;
a third average value calculating module 122, configured to perform gray level conversion on the color image to generate a gray level image and calculate a gray level average value if the area image is a color image;
the first judging module 123 is configured to determine a change threshold, judge the change rate of the grayscale mean based on the change threshold, and determine a target image based on a judgment result;
the reason for using the gray image is that one pixel point in the gray image has only one determined value, and if the color image is, for example, an image in an RGB color value mode, the color image has three values, which are not easy to judge, so that the color image is converted into the gray image to be judged.
Fig. 6 shows a first constitutional block diagram of an information area determination unit in the central platform, the information area determination unit 22 including:
the contour identification module 221 is configured to sequentially read target images and perform contour identification on the target images;
a first calculation module 222, configured to calculate the number of contours and filter the target image based on the number of contours;
a second calculating module 223, configured to determine a position of a center point of each contour, and calculate an offset distance of the position of the center point of each contour of adjacent target images;
a second determining module 224, configured to determine a distance threshold, determine the offset distance based on the distance threshold, and determine a dynamic profile based on the determination result;
the image is subjected to contour recognition, the process is similar to a magic stick tool in Photoshop, the target image is decomposed into different regions, and small regions are screened out after the decomposition, because the regions are generally not human, and even if the regions are human, the human face recognition of the regions is difficult, and the possibility of wrong recognition is high; after the large area is determined, whether the outline changes in the adjacent images is judged, if yes, the image is an animal, and under the condition that the human voice is detected, the animal can be almost considered as a human, and the probability of error in the identification is not high.
Fig. 7 shows a second constitutional block diagram of the information area determination unit in the central platform, and the information area determination unit 22 further includes:
a color value reading module 225, configured to traverse the pixel points of the dynamic contour and read corresponding color values;
a region contour determining module 226 for determining tolerance, determining the magnitude of color value difference of adjacent pixels based on the tolerance, determining region contour based on the determination result,
the screening module 227 is configured to calculate the number of pixels in the region contour, and screen an information region based on the number of pixels;
after the dynamic contour is determined, the color value of each pixel point is obtained, when the color value difference of adjacent pixel points is too large, the pixel points are indicated to be a boundary, for example, if a person wears a red coat, the color value difference at the boundary of the coat and the neck is definitely too large, and therefore, the contour can be determined by calculating the color value difference value.
Example 2
Fig. 8 shows a first flow chart in a face recognition method based on a surveillance video, and in an embodiment of the present invention, a face recognition method based on a surveillance video is provided, where the method is applied to a surveillance end, and the method includes:
step S11: acquiring regional images and audio signals in real time, and adjusting image definition and a monitoring mode based on the audio signals;
step S11 is completed by the adjusting unit 11;
step S12: generating a target image based on the region image, and inserting a dynamic mark into the target image;
step S12 is completed by the target image generation unit 12;
step S13: receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform;
step S13 is completed by the positioning transmission unit 13.
Wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
Example 3
Fig. 9 shows a second flow chart in the face recognition method based on the surveillance video, and in the embodiment of the present invention, a face recognition method based on the surveillance video is provided, where the method is applied to a central platform, and the method includes:
step S21: sending an image acquisition request to a monitoring end, and receiving a target image with a dynamic mark sent by the monitoring end;
said step S21 is completed by the receiving unit 21;
step S22: determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region;
said step S22 is completed by the information area determination unit 22;
step S23: reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information;
the step S23 is completed by the face region determining unit 23;
step S24: identifying ear information in a face area, acquiring a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying a face based on the face orientation;
the step S24 is completed by the execution unit 24.
Fig. 10 is a sub-flow diagram of a second flow diagram in the face recognition method based on the surveillance video, in which a dynamic contour is determined based on the target image and the dynamic contour is subjected to region recognition, and the step of determining the information region includes:
step S221: sequentially reading target images and carrying out contour recognition on the target images;
the step S221 is completed by the contour recognition module 221;
step S222: calculating the number of contours, and screening a target image based on the number of contours;
the step S222 is completed by the first calculation module 222;
step S223: determining the position of the center point of each contour, and calculating the offset distance of the position of the center point of each contour of the adjacent target images;
said step S223 is completed by the second calculation module 223;
step S224: determining a distance threshold, judging the size of the offset distance based on the distance threshold, and determining a dynamic profile based on a judgment result;
said step S224 is performed by the second decision module 224;
step S225: traversing the pixel points of the dynamic contour, and reading corresponding color values;
the step S225 is completed by the color value reading module 225;
step S226: determining tolerance, judging the size of color value difference of adjacent pixel points based on the tolerance, and determining the area outline based on the judgment result;
said step S226 is completed by the region contour determining module 226;
step S227: calculating the number of pixel points in the area outline, and screening an information area based on the number of the pixel points;
said step S227 is completed by the screening module 227.
The functions that can be realized by the above-mentioned surveillance video-based face recognition system are all completed by a computer device, the computer device comprises one or more processors and one or more memories, at least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to realize the functions of the surveillance video-based face recognition system.
The processor fetches instructions and analyzes the instructions one by one from the memory, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A surveillance video based face recognition system, the system comprising:
the monitoring terminal is used for acquiring regional images and audio signals in real time and adjusting the image definition and the monitoring mode based on the audio signals; generating a target image based on the region image, and inserting a dynamic mark into the target image; receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform; wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer;
the central platform is used for sending an image acquisition request to the monitoring terminal and receiving a target image with a dynamic mark sent by the monitoring terminal; determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region; reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information; the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
2. The surveillance video-based face recognition system of claim 1, wherein the surveillance end comprises:
the adjusting unit is used for acquiring the regional image and the audio signal in real time and adjusting the image definition and the monitoring mode based on the audio signal;
a target image generation unit configured to generate a target image based on the region image and insert a dynamic marker into the target image;
the positioning and sending unit is used for receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark and sending the target image to the central platform;
wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
3. The surveillance video-based face recognition system of claim 1, wherein the central platform comprises:
the receiving unit is used for sending an image acquisition request to the monitoring terminal and receiving a target image with a dynamic mark sent by the monitoring terminal;
the information area determining unit is used for determining a dynamic outline based on the target image, performing area identification on the dynamic outline and determining an information area;
the face area determining unit is used for reading temperature information in the information area and determining the face area based on the position relation of the information area and the temperature information;
and the execution unit is used for identifying ear information in the face area, acquiring a monitoring end position, determining the face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
4. The surveillance video-based face recognition system of claim 2, wherein the adjustment unit comprises:
the first mean value calculation module is used for determining backtracking time, intercepting an audio signal based on the backtracking time and calculating an amplitude mean value;
the audio identification module is used for identifying the amplitude change rate determined based on the amplitude mean value, carrying out audio identification on the audio signal based on the amplitude change rate and judging whether the audio signal is a human sound signal based on an identification result;
and the instruction generating module is used for generating an image definition adjusting instruction and a monitoring mode adjusting instruction based on the judgment result.
5. The surveillance video-based face recognition system of claim 2, wherein the target image generation unit comprises:
the second mean value calculation module is used for judging the type of the area image, and calculating a mean value of gray scale if the area image is a gray scale image;
the third mean value calculating module is used for carrying out gray level conversion on the color image to generate a gray level image and calculating a gray level mean value if the area image is the color image;
the first judgment module is used for determining a change threshold, judging the change rate of the gray-scale average value based on the change threshold and determining a target image based on a judgment result.
6. The surveillance video-based face recognition system and method according to claim 3, wherein the information region determining unit comprises:
the contour recognition module is used for reading target images in sequence and recognizing the contours of the target images;
the first calculation module is used for calculating the number of the contours and screening a target image based on the number of the contours;
the second calculation module is used for determining the position of the center point of each contour and calculating the offset distance of the position of the center point of each contour of the adjacent target images;
and the second judging module is used for determining a distance threshold, judging the size of the offset distance based on the distance threshold and determining the dynamic contour based on a judgment result.
7. The surveillance video-based face recognition system and method according to claim 6, wherein the information region determining unit further comprises:
the color value reading module is used for traversing the pixel points of the dynamic contour and reading corresponding color values;
a region contour determining module for determining tolerance, judging the size of color value difference of adjacent pixels based on the tolerance, determining region contour based on the judgment result,
and the screening module is used for calculating the number of pixel points in the area outline and screening the information area based on the number of the pixel points.
8. A face recognition method based on a monitoring video is characterized in that the method is applied to a monitoring end, and comprises the following steps:
acquiring regional images and audio signals in real time, and adjusting image definition and a monitoring mode based on the audio signals;
generating a target image based on the region image, and inserting a dynamic mark into the target image;
receiving an image acquisition request of a central platform, positioning a target image based on the dynamic mark, and sending the target image to the central platform;
wherein the monitoring mode comprises a black-and-white mode and a color mode; the area image includes a temperature layer.
9. A face recognition method based on a surveillance video is characterized in that the method is applied to a central platform, and the method comprises the following steps:
sending an image acquisition request to a monitoring end, and receiving a target image with a dynamic mark sent by the monitoring end;
determining a dynamic contour based on the target image, performing region identification on the dynamic contour, and determining an information region;
reading temperature information in the information area, and determining a face area based on the position relation of the information area and the temperature information;
the method comprises the steps of identifying ear information in a face area, obtaining a monitoring end position, determining face orientation based on the monitoring end position and the ear information, and identifying the face based on the face orientation.
10. The surveillance video-based face recognition method of claim 9, wherein the dynamic contour is determined based on the target image, and the region recognition is performed on the dynamic contour, and the step of determining the information region includes:
sequentially reading target images and carrying out contour recognition on the target images;
calculating the number of contours, and screening a target image based on the number of contours;
determining the position of the center point of each contour, and calculating the offset distance of the position of the center point of each contour of the adjacent target images;
determining a distance threshold, judging the size of the offset distance based on the distance threshold, and determining a dynamic profile based on a judgment result;
traversing the pixel points of the dynamic contour, and reading corresponding color values;
determining tolerance, judging the size of color value difference of adjacent pixel points based on the tolerance, and determining the area outline based on the judgment result;
and calculating the number of pixel points in the area outline, and screening the information area based on the number of the pixel points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811688.1A CN113542692A (en) | 2021-07-19 | 2021-07-19 | Face recognition system and method based on monitoring video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811688.1A CN113542692A (en) | 2021-07-19 | 2021-07-19 | Face recognition system and method based on monitoring video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113542692A true CN113542692A (en) | 2021-10-22 |
Family
ID=78100101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110811688.1A Pending CN113542692A (en) | 2021-07-19 | 2021-07-19 | Face recognition system and method based on monitoring video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113542692A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965729A (en) * | 2021-10-29 | 2022-01-21 | 深圳供电局有限公司 | Regional security monitoring system and method |
| CN114067340A (en) * | 2022-01-17 | 2022-02-18 | 山东北软华兴软件有限公司 | Intelligent judgment method and system for information importance |
| CN114565895A (en) * | 2022-04-28 | 2022-05-31 | 深圳市博铭维系统工程有限公司 | Security monitoring system and method based on intelligent society |
| CN115499578A (en) * | 2022-07-25 | 2022-12-20 | 安徽冠成教育科技有限公司 | Online education learning process monitoring system and method based on face recognition |
| CN115905733A (en) * | 2022-10-28 | 2023-04-04 | 广州地铁集团有限公司 | Mask wearing abnormity detection and trajectory tracking method based on machine vision |
| CN116437116A (en) * | 2023-03-03 | 2023-07-14 | 深圳市宏辉智通科技有限公司 | Audio and video scheduling method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050169546A1 (en) * | 2004-01-29 | 2005-08-04 | Samsung Electronics Co., Ltd. | Monitoring system and method for using the same |
| CN105611252A (en) * | 2015-12-31 | 2016-05-25 | 浙江大华技术股份有限公司 | Video recording method and device |
| CN108259817A (en) * | 2016-12-28 | 2018-07-06 | 南宁富桂精密工业有限公司 | Picture shooting system and method |
| CN108427871A (en) * | 2018-01-30 | 2018-08-21 | 深圳奥比中光科技有限公司 | 3D faces rapid identity authentication method and device |
| CN110796029A (en) * | 2019-10-11 | 2020-02-14 | 北京达佳互联信息技术有限公司 | Face correction and model training method and device, electronic equipment and storage medium |
| CN112784645A (en) * | 2019-11-09 | 2021-05-11 | 北京航天长峰科技工业集团有限公司 | Human face recognition technology-based human evidence integration realization method |
-
2021
- 2021-07-19 CN CN202110811688.1A patent/CN113542692A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050169546A1 (en) * | 2004-01-29 | 2005-08-04 | Samsung Electronics Co., Ltd. | Monitoring system and method for using the same |
| CN105611252A (en) * | 2015-12-31 | 2016-05-25 | 浙江大华技术股份有限公司 | Video recording method and device |
| CN108259817A (en) * | 2016-12-28 | 2018-07-06 | 南宁富桂精密工业有限公司 | Picture shooting system and method |
| CN108427871A (en) * | 2018-01-30 | 2018-08-21 | 深圳奥比中光科技有限公司 | 3D faces rapid identity authentication method and device |
| CN110796029A (en) * | 2019-10-11 | 2020-02-14 | 北京达佳互联信息技术有限公司 | Face correction and model training method and device, electronic equipment and storage medium |
| CN112784645A (en) * | 2019-11-09 | 2021-05-11 | 北京航天长峰科技工业集团有限公司 | Human face recognition technology-based human evidence integration realization method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965729A (en) * | 2021-10-29 | 2022-01-21 | 深圳供电局有限公司 | Regional security monitoring system and method |
| CN113965729B (en) * | 2021-10-29 | 2023-12-26 | 深圳供电局有限公司 | Regional safety monitoring system and method |
| CN114067340A (en) * | 2022-01-17 | 2022-02-18 | 山东北软华兴软件有限公司 | Intelligent judgment method and system for information importance |
| CN114565895A (en) * | 2022-04-28 | 2022-05-31 | 深圳市博铭维系统工程有限公司 | Security monitoring system and method based on intelligent society |
| CN115499578A (en) * | 2022-07-25 | 2022-12-20 | 安徽冠成教育科技有限公司 | Online education learning process monitoring system and method based on face recognition |
| CN115905733A (en) * | 2022-10-28 | 2023-04-04 | 广州地铁集团有限公司 | Mask wearing abnormity detection and trajectory tracking method based on machine vision |
| CN115905733B (en) * | 2022-10-28 | 2024-03-08 | 广州地铁集团有限公司 | Mask wearing abnormality detection and track tracking method based on machine vision |
| CN116437116A (en) * | 2023-03-03 | 2023-07-14 | 深圳市宏辉智通科技有限公司 | Audio and video scheduling method and system |
| CN116437116B (en) * | 2023-03-03 | 2024-01-30 | 深圳市宏辉智通科技有限公司 | Audio and video scheduling method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113542692A (en) | Face recognition system and method based on monitoring video | |
| CN110660066B (en) | Training method of network, image processing method, network, terminal equipment and medium | |
| CN109858384B (en) | Face image capturing method, computer readable storage medium and terminal device | |
| CN109325429B (en) | Method, device, storage medium and terminal for associating feature data | |
| US20210166015A1 (en) | Certificate image extraction method and terminal device | |
| CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
| CN111898520B (en) | Certificate authenticity identification method and device, computer readable medium and electronic equipment | |
| CN106651797B (en) | Method and device for determining effective area of signal lamp | |
| CN109583299A (en) | Electronic device, certificate recognition methods and storage medium | |
| CN111160202A (en) | AR equipment-based identity verification method, AR equipment-based identity verification device, AR equipment-based identity verification equipment and storage medium | |
| CN110992502A (en) | Face recognition attendance checking method and system and readable storage medium | |
| CN112016363A (en) | Personnel monitoring method and device, computer device and readable storage medium | |
| CN113989858A (en) | Work clothes identification method and system | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN109784379B (en) | Updating method and device of textile picture feature library | |
| CN108769521B (en) | Photographing method, mobile terminal and computer readable storage medium | |
| CN111539975B (en) | Method, device, equipment and storage medium for detecting moving object | |
| CN111062279B (en) | Photo processing method and photo processing device | |
| CN111199050B (en) | System for automatically desensitizing medical records and application | |
| CN114463685B (en) | Behavior recognition method, behavior recognition device, electronic equipment and storage medium | |
| CN112989924B (en) | Target detection method, target detection device and terminal equipment | |
| CN115375886A (en) | Data acquisition method and system based on cloud computing service | |
| CN114140427A (en) | Object detection method and device | |
| CN115082326A (en) | Processing method for deblurring video, edge computing equipment and central processor | |
| CN112200080A (en) | Face recognition method and device, electronic equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |