CN113408379A - Mobile phone candid behavior monitoring method and system - Google Patents
Mobile phone candid behavior monitoring method and system Download PDFInfo
- Publication number
- CN113408379A CN113408379A CN202110627531.3A CN202110627531A CN113408379A CN 113408379 A CN113408379 A CN 113408379A CN 202110627531 A CN202110627531 A CN 202110627531A CN 113408379 A CN113408379 A CN 113408379A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- human body
- candid
- behavior
- judging
- 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 46
- 238000000034 method Methods 0.000 title claims abstract description 26
- 210000000746 body region Anatomy 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 95
- 238000013136 deep learning model Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007689 inspection Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a method and a system for monitoring a mobile phone candid behavior, comprising the following steps of A1, acquiring an image; step A2, extracting human body characteristic information and mobile phone characteristic information from the image, wherein the human body characteristic information comprises a human body area and a human body position, and the mobile phone characteristic information comprises a mobile phone area and a mobile phone position; step A3, extracting key features of a human body from a human body region; and step A4, judging whether the mobile phone candid behavior exists or not based on a preset judgment strategy by combining the key characteristics of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, and outputting a judgment result when the judgment result is that the mobile phone candid behavior exists. Compared with manual inspection, the method is time-consuming and labor-consuming, low in cost, high in efficiency, high in accuracy, simple and high in applicability.
Description
Technical Field
The invention relates to the technical field of image processing and monitoring, in particular to a method and a system for monitoring a mobile phone candid behavior.
Background
In some special units or scenes, such as meeting rooms, machine rooms, exhibition halls, religious places and the like, the private photographing is forbidden due to the popular or confidential requirements, the traditional prevention method mainly prohibits the entrance personnel from entering the room with photographing equipment, the entrance personnel can enter the room after checking one by special personnel, the special places are arranged to keep the equipment, time and labor are wasted, and a great deal of inconvenience is brought to the entrance personnel. The prior art lacks a low-cost, simple, accurate and efficient monitoring means.
Disclosure of Invention
The invention provides a method and a system for monitoring a mobile phone candid behavior, and aims to solve the technical problems that manual monitoring in the prior art wastes time and labor and the like.
A method for monitoring a mobile phone candid behavior comprises the following steps:
step A1, acquiring an image;
step A2, extracting human body characteristic information and mobile phone characteristic information from the image by adopting a pre-trained first deep learning model, wherein the human body characteristic information comprises a human body area and a human body position, and the mobile phone characteristic information comprises a mobile phone area and a mobile phone position;
step A3, extracting human body key features from a human body region by adopting a pre-trained second deep learning model;
and step A4, judging whether the mobile phone candid behavior exists or not based on a preset judgment strategy by combining the key characteristics of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, and outputting a judgment result when the judgment result is that the mobile phone candid behavior exists.
Further, the key features of the human body include a human hand, and in step a4, the step of determining whether the mobile phone candid behavior exists based on the preset determination policy includes the following steps:
step A41, judging whether the mobile phone is in the hand based on the relation between the mobile phone area and the hand, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist;
and step A42, judging whether the position of the mobile phone is in the upper area of the position of the human body, if so, outputting a judgment result that the mobile phone candid behavior exists, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Further, the human body position is waist or shoulder.
Further, the human body key features also comprise human faces; after step a41 and before step a42 further comprising:
and step B1, judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Further, step B1 includes: judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing to step B1;
step B2 is: and D, judging whether the distance between each two of the human hand, the human face and the human body meets a preset standard, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Furthermore, the key features of the human body also comprise arms,
step B1 is: determining a human body with the mobile phone based on the relationship among the human hand, the arm, the human face and the human body in the image, judging whether the human face faces the mobile phone based on the human face and the mobile phone area of the human body with the mobile phone, if so, continuing to step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Further, when it is determined in step a4 that the cell phone candid exists, the method further includes:
step A5, transmitting the judgment result to an alarm module, wherein the alarm module generates alarm information to inform a manager; and
step A6, storing the image; and uploading the images to the corresponding client side so as to be conveniently viewed by the management personnel.
The utility model provides a cell-phone behavior monitored control system that candids photograph, aforementioned a cell-phone behavior monitored control system that candids photograph which characterized in that includes:
the image acquisition module is used for acquiring an image;
the first feature extraction module is connected with the image acquisition module and used for extracting human body feature information and mobile phone feature information from the image by adopting a pre-trained first deep learning model, wherein the human body feature information comprises a human body region and a human body position, and the mobile phone feature information comprises a mobile phone region and a mobile phone position;
the second feature extraction module is connected with the first feature extraction module and used for extracting human body key features from the human body region by adopting a pre-trained second deep learning model;
the judging module is respectively connected with the first characteristic extracting module and the second characteristic extracting module, combines the key characteristics of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, judges whether the mobile phone candid behavior exists or not based on a preset judging strategy, and outputs a judging result when the judging result is that the mobile phone candid behavior exists.
Further, human key feature includes the staff, and the judgement module includes:
the first judging unit is used for judging whether the mobile phone is in the hand of the person based on the relation between the mobile phone area and the hand of the person, if not, outputting a judging result that the mobile phone candid behavior does not exist, and if so, outputting a judging result that the mobile phone candid behavior exists to the second judging unit;
and the second judging unit is connected with the first judging unit and used for judging whether the position of the mobile phone is in the upper area of the position of the human body, if so, outputting a judging result that the mobile phone candid behavior exists, and if not, outputting a judging result that the mobile phone candid behavior does not exist.
Further, the human body position is waist or shoulder.
The beneficial technical effects of the invention are as follows: the invention provides a method and a system for monitoring a mobile phone candid behavior, which are used for acquiring human body characteristic information and mobile phone characteristic information and judging whether the mobile phone candid behavior exists or not according to the relation between a human body and a mobile phone.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for monitoring a mobile phone candid behavior according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a method for monitoring a mobile phone candid behavior according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of a method for monitoring a candid camera of a mobile phone according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a general module of a system for monitoring a candid camera behavior of a mobile phone according to the present invention;
fig. 5 is a schematic block diagram of a system for monitoring a candid camera behavior of a mobile phone according to an embodiment of the present invention.
Fig. 6 is a schematic block diagram of a system for monitoring a candid camera behavior of a mobile phone according to an embodiment of the present invention.
Fig. 7 is a schematic block diagram of a system for monitoring a candid camera behavior of a mobile phone according to an embodiment of the present invention.
Fig. 8 is a schematic block diagram of a system for monitoring a candid camera behavior of a mobile phone according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
Referring to fig. 1, the invention provides a method for monitoring a mobile phone candid behavior, comprising the following steps:
step A1, acquiring an image;
step A2, extracting human body characteristic information and mobile phone characteristic information from the image by adopting a pre-trained first deep learning model, wherein the human body characteristic information comprises a human body area and a human body position, and the mobile phone characteristic information comprises a mobile phone area and a mobile phone position;
step A3, extracting human body key features from a human body region by adopting a pre-trained second deep learning model;
and step A4, judging whether the mobile phone candid behavior exists or not based on a preset judgment strategy by combining the key characteristics of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, and outputting a judgment result when the judgment result is that the mobile phone candid behavior exists.
Preferably, in step a1, a video stream is captured from the monitoring camera and decoded into an image.
The monitoring camera is generally installed in a special place, and shoots a monitoring video, so that the monitoring camera is only required to be connected, a video stream is obtained from the monitoring camera, the video stream is decoded into a frame-by-frame image, the image is processed, human body characteristic information and mobile phone characteristic information are obtained, whether a mobile phone candid behavior exists or not is judged according to the relation between a human body and a mobile phone, and compared with manual inspection, the method is time-consuming and labor-consuming, low in cost, high in efficiency, high in accuracy, simple and high in applicability.
The feature extraction is carried out by using the first deep learning model and the second deep learning model which are trained in advance, so that the extracted features are closer to a real target.
Referring to fig. 2, further, the key features of the human body include a human hand, and in step a4, the determining whether there is a cell phone candid behavior based on a preset determination policy includes the following steps:
step A41, judging whether the mobile phone is in the hand based on the relation between the mobile phone area and the hand, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist;
and step A42, judging whether the position of the mobile phone is in the upper area of the position of the human body, if so, outputting a judgment result that the mobile phone candid behavior exists, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
And judging whether the candid camera exists or not according to the relation between the hand and the mobile phone, such as the behavior of judging whether the hand holds the mobile phone or not.
Further, the human body position is waist or shoulder.
Further, the human body key features also comprise human faces; after step a41 and before step a42 further comprising:
and step B1, judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Further, step B1 includes: judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing to step B1;
step B2 is: and D, judging whether the distance between each two of the human hand, the human face and the human body meets a preset standard, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Furthermore, the key features of the human body also comprise arms,
step B1 is: determining a human body with the mobile phone based on the relationship among the human hand, the arm, the human face and the human body in the image, judging whether the human face faces the mobile phone based on the human face and the mobile phone area of the human body with the mobile phone, if so, continuing to step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
The conditions of multiple human faces, human hands and the like can exist in the same image, if the conditions are not screened, a mobile phone is probably owned by a person nearby at the same time, and because the real owner of the mobile phone is screened out through screening and judging the fusion of the key features of multiple human bodies, the misjudgment is avoided.
Whether the mobile phone is in the hand or not is judged by the extracted key features of the mobile phone area and the hand, which are not enough to determine that the mobile phone is a candid act, for example, when the mobile phone is held by the hand, the hand is probably placed at the position of the leg, so that the mobile phone is not a candid act and is only a general holding act, and a plurality of constraint conditions are required to be formulated for filtering, so that whether the mobile phone is a candid act is further judged according to the relation between the position of the mobile phone and the position of the human body. For example, the determined position of the human body may be the waist of the person, if the position of the mobile phone is below the waist, it may be determined that the candid behavior does not exist, and if the position of the mobile phone is above the waist, it may be determined that the candid behavior exists. For example, if the position of the human body is a shoulder, and the position of the mobile phone is below the shoulder, it can be determined that the candid action does not exist, and the position of the mobile phone above the shoulder can be determined that the candid action exists.
General personnel in a special scene are numerous, and a plurality of human bodies or a plurality of mobile phones may exist in the same image, so that interference items can be eliminated by setting a plurality of judgment conditions, and the judgment result is more accurate.
The human body key features can also comprise the head part, the shoulder part, the leg part, the foot part and the like, and the judgment is more accurate and effective by fusing a plurality of parts.
Referring to fig. 3, further, when it is determined in step a4 that the cell phone candid exists, the method further includes:
step A5, transmitting the judgment result to an alarm module, wherein the alarm module generates alarm information to inform a manager; and
step A6, storing the image; and uploading the images to the corresponding client side so as to be conveniently viewed by the management personnel.
When the behavior of mobile phone candid shooting exists, alarm information is generated in time to inform a manager, and the manager can conveniently process the behavior in time.
The image is sent to a manager, and the manager can find the corresponding candid camera in time according to the image.
Referring to fig. 4, the present invention further provides a system for monitoring a candid behavior of a mobile phone, which is characterized in that the system for monitoring a candid behavior of a mobile phone is applied, and comprises:
the image acquisition module (1) is used for acquiring an image;
the first feature extraction module (2) is connected with the image acquisition module (1) and is used for extracting human body feature information and mobile phone feature information from the image by adopting a first deep learning model trained in advance, wherein the human body feature information comprises a human body region and a human body position, and the mobile phone feature information comprises a mobile phone region and a mobile phone position;
the second feature extraction module (3) is connected with the first feature extraction module (2) and is used for extracting human body key features from the human body region by adopting a pre-trained second deep learning model;
the judging module (4) is respectively connected with the first characteristic extracting module (2) and the second characteristic extracting module (3), combines the key characteristics of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, judges whether the mobile phone candid behavior exists or not based on a preset judging strategy, and outputs a judging result when the judging result is that the mobile phone candid behavior exists.
The feature extraction is carried out by using the first deep learning model and the second deep learning model which are trained in advance, so that the extracted features are closer to a real target.
Further, human key feature includes the staff, and the judgement module includes:
a first judging unit (41) for judging whether the mobile phone is in the hand of the person based on the relationship between the area of the mobile phone and the hand of the person, if not, outputting a judgment result that the mobile phone candid behavior does not exist, and if so, outputting a judgment result that the mobile phone candid behavior exists to a second judging unit (42);
and the second judgment unit (42) is connected with the first judgment unit (41) and is used for judging whether the position of the mobile phone is in the upper area of the position of the human body, if so, the judgment result of the existence of the mobile phone candid behavior is output, and if not, the judgment result of the absence of the mobile phone candid behavior is output.
Further, the human body position is waist or shoulder.
Preferably, the image capturing module (1) is further connected to a monitoring camera for capturing a video stream, and the image capturing module includes:
a video acquisition unit (11) for acquiring a video stream from a monitoring camera;
and the decoding unit (12) is connected with the video acquisition unit (11) and is used for decoding the video stream into images.
The monitoring camera is generally installed in a special place, and shoots a monitoring video, so that the monitoring camera is only required to be connected, a video stream is obtained from the monitoring camera, the video stream is decoded into a frame-by-frame image, the image is processed, human body characteristic information and mobile phone characteristic information are obtained, whether a mobile phone candid behavior exists or not is judged according to the relation between a human body and a mobile phone, and compared with manual inspection, the method is time-consuming and labor-consuming, low in cost, high in efficiency, high in accuracy, simple and high in applicability.
Further, the system for monitoring the behavior of candid camera by mobile phone of the invention further comprises:
the sending module (5) is connected with the judging module (4) and used for sending the judging result to the alarming module when the judging result shows that the mobile phone candid behavior exists;
and the alarm module (6) is connected with the sending module (5) and used for generating alarm information according to the judgment result so as to inform a manager.
The storage module (7) is connected with the judgment module (4) and the image acquisition module (1) and is used for storing the image when the judgment result shows that the mobile phone candid behavior exists;
the sending module (5) is also connected with the storage module (7) and is used for uploading the images to the corresponding client side so as to be convenient for the management personnel to view.
The image is sent to a manager, and the manager can find the corresponding candid camera in time according to the image.
Further, the key features of the human body also comprise the human face,
and the third judging unit (43) is respectively connected with the second judging unit (42) and the first judging unit (41) and is used for judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if not, outputting a judging result that the mobile phone candid behavior does not exist, and if so, outputting a judging result that the mobile phone candid behavior exists to the second judging unit (42).
Further, the system for monitoring the behavior of candid camera by mobile phone of the invention further comprises:
the fourth judging unit (44) is respectively connected with the third judging unit (43) and the second judging unit (42) and is used for judging whether the distance between each two of the human hand, the human face and the human body meets a preset standard or not, and if yes, a judgment result of the existence of the mobile phone candid behavior is output to the second judging unit (42); if not, outputting a judgment result that the mobile phone candid behavior does not exist.
Further, the system for monitoring the behavior of candid camera by mobile phone of the invention further comprises: the third judging unit (43) is specifically configured to: determining a human body with a mobile phone based on the relationship among the human hand, the arm, the human face and the human body in the image, judging whether the human face faces the mobile phone based on the human face and the mobile phone area of the human body with the mobile phone, if not, outputting a judgment result that the mobile phone candid behavior does not exist, and if so, outputting the judgment result that the mobile phone candid behavior exists to a second judgment unit (42);
whether the mobile phone is in the hand or not is judged by the extracted key features of the mobile phone area and the hand, which are not enough to determine that the mobile phone is a candid act, for example, when the mobile phone is held by the hand, the hand is probably placed at the position of the leg, so that the mobile phone is not a candid act and is only a general holding act, and a plurality of constraint conditions are required to be formulated for filtering, so that whether the mobile phone is a candid act is further judged according to the relation between the position of the mobile phone and the position of the human body. For example, the determined position of the human body may be the waist of the person, if the position of the mobile phone is below the waist, it may be determined that the candid behavior does not exist, and if the position of the mobile phone is above the waist, it may be determined that the candid behavior exists. For example, if the position of the human body is a shoulder, and the position of the mobile phone is below the shoulder, it can be determined that the candid action does not exist, and the position of the mobile phone above the shoulder can be determined that the candid action exists.
General personnel in a special scene are numerous, and a plurality of human bodies or a plurality of mobile phones may exist in the same image, so that interference items can be eliminated by setting a plurality of judgment conditions, and the judgment result is more accurate.
The human body key features can also comprise the head part, the shoulder part, the leg part, the foot part and the like, and the judgment is more accurate and effective by fusing a plurality of parts.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A method for monitoring a mobile phone candid behavior is characterized by comprising the following steps:
step A1, acquiring an image;
step A2, extracting human body characteristic information and mobile phone characteristic information from the image by adopting a first deep learning model trained in advance, wherein the human body characteristic information comprises a human body area and a human body position, and the mobile phone characteristic information comprises a mobile phone area and a mobile phone position;
step A3, extracting human body key features from the human body region by adopting a pre-trained second deep learning model;
and A4, combining the key features of the human body, the position of the human body, the area of the mobile phone and the position of the mobile phone, judging whether the mobile phone candid behavior exists based on a preset judgment strategy, and outputting a judgment result when the judgment result is that the mobile phone candid behavior exists.
2. The method for monitoring the mobile phone candid behavior as claimed in claim 1, wherein the key features of the human body comprise human hands, and the step a4 of determining whether the mobile phone candid behavior exists based on a preset determination strategy comprises the following steps:
step A41, judging whether the mobile phone is in the hand based on the relation between the mobile phone area and the hand, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist;
and A42, judging whether the position of the mobile phone is in the upper area of the human body position, if so, outputting a judgment result that the mobile phone candid behavior exists, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
3. The method for monitoring the behavior of candid camera shooting by mobile phone according to claim 2, wherein the human body position is waist or shoulder.
4. The method for monitoring the behavior of candid camera shooting by mobile phone according to claim 2, wherein the key features of the human body further comprise human faces; further comprising, after the step A41 and before the step A42:
and B1, judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
5. The method for monitoring the behavior of candid camera shooting by mobile phone according to claim 4, wherein the step B1 comprises the following steps: judging whether the face faces the mobile phone or not based on the face and the mobile phone area, if so, continuing to the step B2;
the step B2 is as follows: and B, judging whether the distance between the hand, the face and the human body position meets a preset standard or not, if so, continuing the step A42, and otherwise, outputting a judgment result that the mobile phone candid behavior does not exist.
6. The method for monitoring the behavior of candid camera of mobile phone according to claim 4, wherein the key features of human body further comprise arms,
the step B1 is as follows: determining the human body with the mobile phone based on the relationship among the human hand, the arm, the face and the human body in the image, judging whether the face faces the mobile phone based on the face and the mobile phone area of the human body with the mobile phone, if so, continuing the step A42, and if not, outputting a judgment result that the mobile phone candid behavior does not exist.
7. The method for monitoring the behavior of candid mobile phone photography according to claim 1, wherein when the determination result in step a4 is that there is behavior of candid mobile phone photography, the method further comprises:
step A5, transmitting the judgment result to an alarm module, wherein the alarm module generates alarm information to inform a manager; and
step A6, saving the image; and uploading the image to a corresponding client so that the image can be conveniently viewed by the manager.
8. A mobile phone candid behavior monitoring system, which is applied to the mobile phone candid behavior monitoring system according to any one of claims 1 to 7, and comprises:
the image acquisition module is used for acquiring an image;
the first feature extraction module is connected with the image acquisition module and used for extracting human body feature information and mobile phone feature information from the image by adopting a first deep learning model trained in advance, wherein the human body feature information comprises a human body region and a human body position, and the mobile phone feature information comprises a mobile phone region and a mobile phone position;
the second feature extraction module is connected with the first feature extraction module and used for extracting human body key features from the human body region by adopting a pre-trained second deep learning model;
and the judging module is respectively connected with the first characteristic extracting module and the second characteristic extracting module, combines the human body key characteristics, the human body position, the mobile phone area and the mobile phone position, judges whether a mobile phone candid behavior exists or not based on a preset judging strategy, and outputs a judging result when the judging result is that the mobile phone candid behavior exists.
9. The system for monitoring the behavior of candid camera shooting by mobile phone according to claim 8, wherein the key features of human body comprise human hands, and the judging module comprises:
the first judging unit is used for judging whether the mobile phone is in the hand or not based on the relation between the mobile phone area and the hand, if not, a judging result that the mobile phone candid behavior does not exist is output, and if yes, a judging result that the mobile phone candid behavior exists is output to the second judging unit;
and the second judging unit is connected with the first judging unit and used for judging whether the position of the mobile phone is in the upper area of the human body position, if so, outputting a judging result that the mobile phone candid behavior exists, and if not, outputting a judging result that the mobile phone candid behavior does not exist.
10. The system for monitoring the behavior of candid camera shooting by mobile phone as claimed in claim 9, wherein the human body position is waist or shoulder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627531.3A CN113408379A (en) | 2021-06-04 | 2021-06-04 | Mobile phone candid behavior monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627531.3A CN113408379A (en) | 2021-06-04 | 2021-06-04 | Mobile phone candid behavior monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408379A true CN113408379A (en) | 2021-09-17 |
Family
ID=77676484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110627531.3A Pending CN113408379A (en) | 2021-06-04 | 2021-06-04 | Mobile phone candid behavior monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408379A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783040A (en) * | 2022-06-23 | 2022-07-22 | 东莞先知大数据有限公司 | Detection method and detection device for candid shooting in building |
| CN116476757A (en) * | 2023-03-23 | 2023-07-25 | 小米汽车科技有限公司 | Equipment control method, device, vehicle and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008021254A (en) * | 2006-07-14 | 2008-01-31 | Sogo Keibi Hosho Co Ltd | Surreptitious photo camera detecting device, surreptitious photo camera detection system and surreptitious photo camera detecting method |
| CN108182396A (en) * | 2017-12-25 | 2018-06-19 | 中国电子科技集团公司电子科学研究院 | A kind of automatic identification is taken pictures the method and device of behavior |
| CN108234741A (en) * | 2017-11-16 | 2018-06-29 | 吴英 | Intelligent mobile phone control method based on action recognition |
| CN110287862A (en) * | 2019-06-21 | 2019-09-27 | 西安电子科技大学 | Anti- detection method of taking on the sly based on deep learning |
| CN110287906A (en) * | 2019-06-26 | 2019-09-27 | 四川长虹电器股份有限公司 | Method and system based on image/video detection people " playing mobile phone " |
| CN111063144A (en) * | 2019-12-03 | 2020-04-24 | 联通物联网有限责任公司 | Abnormal behavior monitoring method, device, equipment and computer readable storage medium |
| CN111523384A (en) * | 2020-03-19 | 2020-08-11 | 浙江省北大信息技术高等研究院 | Vision-based conference anti-candid method and device, storage medium and terminal |
| CN111914667A (en) * | 2020-07-08 | 2020-11-10 | 浙江大华技术股份有限公司 | Smoking detection method and device |
| CN112381068A (en) * | 2020-12-25 | 2021-02-19 | 四川长虹电器股份有限公司 | Method and system for detecting 'playing mobile phone' of person |
-
2021
- 2021-06-04 CN CN202110627531.3A patent/CN113408379A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008021254A (en) * | 2006-07-14 | 2008-01-31 | Sogo Keibi Hosho Co Ltd | Surreptitious photo camera detecting device, surreptitious photo camera detection system and surreptitious photo camera detecting method |
| CN108234741A (en) * | 2017-11-16 | 2018-06-29 | 吴英 | Intelligent mobile phone control method based on action recognition |
| CN108182396A (en) * | 2017-12-25 | 2018-06-19 | 中国电子科技集团公司电子科学研究院 | A kind of automatic identification is taken pictures the method and device of behavior |
| CN110287862A (en) * | 2019-06-21 | 2019-09-27 | 西安电子科技大学 | Anti- detection method of taking on the sly based on deep learning |
| CN110287906A (en) * | 2019-06-26 | 2019-09-27 | 四川长虹电器股份有限公司 | Method and system based on image/video detection people " playing mobile phone " |
| CN111063144A (en) * | 2019-12-03 | 2020-04-24 | 联通物联网有限责任公司 | Abnormal behavior monitoring method, device, equipment and computer readable storage medium |
| CN111523384A (en) * | 2020-03-19 | 2020-08-11 | 浙江省北大信息技术高等研究院 | Vision-based conference anti-candid method and device, storage medium and terminal |
| CN111914667A (en) * | 2020-07-08 | 2020-11-10 | 浙江大华技术股份有限公司 | Smoking detection method and device |
| CN112381068A (en) * | 2020-12-25 | 2021-02-19 | 四川长虹电器股份有限公司 | Method and system for detecting 'playing mobile phone' of person |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783040A (en) * | 2022-06-23 | 2022-07-22 | 东莞先知大数据有限公司 | Detection method and detection device for candid shooting in building |
| CN114783040B (en) * | 2022-06-23 | 2022-09-20 | 东莞先知大数据有限公司 | Detection method and detection device for candid shooting in building |
| CN116476757A (en) * | 2023-03-23 | 2023-07-25 | 小米汽车科技有限公司 | Equipment control method, device, vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6774905B2 (en) | Image data processing | |
| CN102196251B (en) | Smart-city intelligent monitoring method and system | |
| CN107278369A (en) | Method, device and the communication system of people finder | |
| CN107590212A (en) | The Input System and method of a kind of face picture | |
| CN113408379A (en) | Mobile phone candid behavior monitoring method and system | |
| CN111523384A (en) | Vision-based conference anti-candid method and device, storage medium and terminal | |
| CN103957387B (en) | A kind of security protection channel sundries detection method and detection system | |
| KR101514061B1 (en) | Wireless camera device for managing old and weak people and the management system thereby | |
| JP2007158421A (en) | Monitoring camera system and face image tracing recording method | |
| CN108492425A (en) | A kind of automatic track human faces door opening method and system based on face lock | |
| CN100464348C (en) | Video frequency monitoring, identification intelligont device and technical method | |
| US20180151039A1 (en) | Neighborhood Security Cameras | |
| JP2005323046A (en) | Monitoring system and monitoring camera | |
| CN101826226A (en) | Intelligent entrance guard control method and device | |
| CN110390785A (en) | A kind of smart home security inter-linked controlling method, device, medium and terminal device | |
| CN106686353A (en) | Security and protection control system and method based on cloud | |
| CN104299176A (en) | Student pick-up and drop-off security management system | |
| CN109040654B (en) | Method and device for identifying external shooting equipment and storage medium | |
| CN106572324A (en) | Energy-efficient smart monitoring device | |
| CN108197614A (en) | A kind of examination hall monitor camera and system based on face recognition technology | |
| CN105138321B (en) | The control method and system of terminal | |
| CN111908288A (en) | TensorFlow-based elevator safety system and method | |
| CN110867006A (en) | Pedestrian passageway gate machine, control method thereof and pedestrian passageway gate machine system | |
| CN110245648A (en) | The alert system of wisdom list based on Identification of Images | |
| CN112601054B (en) | Pickup picture acquisition method and device, storage medium and electronic equipment |
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 |