CN112084963B - Monitoring early warning method, system and storage medium - Google Patents
Monitoring early warning method, system and storage medium Download PDFInfo
- Publication number
- CN112084963B CN112084963B CN202010955424.9A CN202010955424A CN112084963B CN 112084963 B CN112084963 B CN 112084963B CN 202010955424 A CN202010955424 A CN 202010955424A CN 112084963 B CN112084963 B CN 112084963B
- Authority
- CN
- China
- Prior art keywords
- abnormal event
- video stream
- module
- monitoring
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000002159 abnormal effect Effects 0.000 claims abstract description 94
- 238000007781 pre-processing Methods 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 235000002566 Capsicum Nutrition 0.000 claims description 2
- 239000006002 Pepper Substances 0.000 claims description 2
- 235000016761 Piper aduncum Nutrition 0.000 claims description 2
- 235000017804 Piper guineense Nutrition 0.000 claims description 2
- 244000203593 Piper nigrum Species 0.000 claims description 2
- 235000008184 Piper nigrum Nutrition 0.000 claims description 2
- 230000007797 corrosion Effects 0.000 claims description 2
- 238000005260 corrosion Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 150000003839 salts Chemical class 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 230000000877 morphologic effect Effects 0.000 claims 1
- 230000003287 optical effect Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Abstract
The invention relates to a monitoring and early warning method, a monitoring and early warning system and a storage medium. The method comprises the following specific steps: s1: acquiring a video stream and processing the video stream; s2: acquiring target characteristics of the preprocessed video stream; s3: constructing an abnormal event identification criterion; s4: identifying whether an abnormal event occurs in the video stream according to the abnormal event identification criterion; s5: and when the occurrence of the abnormal event is detected, responding to the abnormal event. The system comprises: the system comprises an acquisition and preprocessing module, an abnormal event identification module, an early warning and information backtracking module, a display module and a communication module; the invention identifies whether abnormal events occur in the monitoring area according to an abnormal event identification algorithm arranged in the computer, transmits an abnormal event occurrence signal back to the monitoring center, and synchronously starts an emergency plan by the staff.
Description
Technical Field
The invention relates to the technical field of video processing, in particular to a monitoring and early warning method, a monitoring and early warning system and a storage medium.
Background
The monitoring system is one of the most applied systems in the security system, and the traditional monitoring system needs a monitor to monitor abnormal conditions of different monitoring points in a complex scene in real time through a plurality of independent monitoring windows in a monitoring room.
In the monitoring mode, the monitoring pictures are mutually isolated and have no relevance, and because the visual angle monitored by the camera is limited, complete and comprehensive image picture information and clear visual characteristic information in a visual field can not be obtained, once an abnormal event occurs in a monitoring area, monitoring personnel can not effectively identify the actual condition or visual characteristic currently presented by the abnormal event through scattered video pictures, effectively position the actual geographic position of the abnormal event and quickly trace back the video of the abnormal event, the processing efficiency of the abnormal event by professional personnel and the arrangement and scheduling of the personnel for processing the abnormal event are greatly influenced, and further serious consequences can be caused.
The above information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a monitoring and early warning method, a monitoring and early warning system and a storage medium.
The invention provides a monitoring and early warning method which is characterized by comprising the following steps:
s1: acquiring a video stream, and preprocessing the video stream;
s2: acquiring target characteristics of the preprocessed video stream;
s3: constructing an abnormal event identification criterion;
s4: identifying whether an abnormal event occurs in the video stream according to an abnormal event identification criterion;
s5: and when the occurrence of the abnormal event is detected, responding to the abnormal event.
Preferably, in the above technical solution, the preprocessing the video stream in S1 specifically includes:
s11: decoding the video stream and extracting key frames;
s12: preprocessing the key frame;
s13: and performing image optimization on the preprocessed key frames.
Preferably, in the above technical solution, the specific step of S2 includes:
s21: calculating an interest point feature coordinate set of each frame of target feature in the video stream;
s22: and calculating the feature coordinate set of the interest points to obtain a target feature vector set.
Preferably, in the above technical solution, step S3 further includes:
s31: calculating target characteristic parameters by combining a target characteristic vector set;
s32: and inputting the target characteristic parameters into an abnormal event recognition model for training.
Preferably, in the above technical solution, the target characteristic parameters include: motion vector kinetic energy, motion direction information entropy and adjacent target information quantity.
Preferably, in the above technical solution, step S5 further includes: and after the abnormal event is detected, automatically carrying out early warning and recording on the abnormal event.
Preferably, in the above technical solution, the step S5 further includes, after detecting the abnormal event, positioning the occurrence direction of the abnormal event.
The monitoring and early warning system comprises an acquisition and preprocessing module, an abnormal event identification module, an early warning and information backtracking module, a display module and a communication module, wherein the acquisition and preprocessing module is used for acquiring and processing the abnormal events;
the acquisition and preprocessing module is used for acquiring and storing the video stream and preprocessing the video stream;
the abnormal event identification module is used for judging whether an abnormal event occurs in the preprocessed video stream;
the early warning and information backtracking module is used for starting an early warning mechanism when an abnormal event occurs and transmitting the information of the abnormal event back to the monitoring center;
the display module is used for displaying the video stream by adopting any one display method of grid arrangement or single-point arrangement;
and the communication module is used for communication connection among the modules.
A computer storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the monitoring and forewarning method.
Compared with the prior art, the invention has the following beneficial effects: according to the monitoring and early warning method, the monitoring and early warning system and the storage medium, whether an abnormal event occurs in a monitored area can be automatically identified according to an abnormal event identification algorithm arranged in the monitoring and early warning system, a video image of the abnormal event is intercepted and stored, the geographic position coordinate of the abnormal event is automatically acquired, the information is transmitted back to a monitoring center, and a worker can start an emergency plan according to the transmitted information.
Drawings
FIG. 1 is a flow chart of a monitoring and forewarning method of the present invention;
FIG. 2 is a flow chart of a method for pre-processing a video stream according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for determining and identifying an abnormal event according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a monitoring and forewarning system of the present invention;
fig. 5 is another schematic block diagram of a monitoring and warning system according to the present invention.
100-acquisition and preprocessing module, 200-display module, 300-abnormal event identification module, 310-abnormal event distinguishing module, 320-abnormal information positioning module, 400-early warning and information backtracking module and 500-communication module.
Detailed Description
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations such as "comprises" or "comprising", etc., will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
Example 1
The monitoring and early warning method provided by the invention comprises the following steps:
step S1: acquiring a video stream, and preprocessing the video stream;
the method and means for acquiring the video stream comprise all methods and means for acquiring the video stream, and the specific method for preprocessing the video stream comprises the following steps:
s11, decoding the video stream and extracting key frames;
analyzing the video stream into video frame images, screening the video frame images with the moving targets and marking the video frame images as key frames;
s12, preprocessing the key frame;
performing noise reduction processing on salt and pepper noise and Gaussian noise in the key frame image by using image processing modes of median filtering and mean filtering respectively;
s13, carrying out image optimization on the preprocessed key frame;
carrying out foreground detection on the key frame highlight after noise reduction by using a Gaussian mixture model based on an EM (effective noise) algorithm, and carrying out shadow removal by using an RCB (residual color B) color model; and (3) carrying out image optimization by using a binary morphology algorithm, namely carrying out denoising operation on the preliminarily obtained image, namely respectively carrying out corrosion, expansion, opening operation and closing operation, and finally obtaining a binary key frame foreground image, namely a binary image of the moving target.
It should be noted that when the video stream is collected, the attribute information of the collection module, that is, the geographic position Information (ID) and the angle deflection information corresponding to the collection module, etc. need to be returned in real time (that is, the attribute information corresponding to the ID of the dome camera at least includes the camera GPS position, the roll angle, the tilt angle, and the yaw angle), so that the collection module can be positioned to the corresponding position in the monitoring through GPS positioning in the following procedure, and the corresponding geographic position information is returned.
Step S2: acquiring target characteristics of the preprocessed video stream; the specific method comprises the following steps:
s21: calculating an interest point feature coordinate set of the target feature of each frame in the video stream;
and (3) constructing a key frame mask template, calculating each frame by combining a feature extraction algorithm to obtain an interest point feature coordinate set of target features, namely, taking the moving target binary image obtained in S1 as a binary mask template, detecting and extracting the interest point features of each frame of video image by using the feature extraction algorithm, and obtaining the target features, namely the interest point feature coordinate set of the moving target.
S22: calculating the characteristic coordinate set of the interest points to construct a target characteristic vector set
And performing optical flow calculation on the interest point characteristics of the moving target in the interest point characteristic coordinate set of the moving target by using an LK optical flow method to obtain an optical flow vector set of the moving target characteristics, and using the optical flow vector set as a calculation basis for subsequently constructing abnormal event identification criteria.
It should be noted that: the interest point feature in the invention is an angular point feature; the feature extraction algorithm in the invention is preferably Shi-Tomasi algorithm; the optical flow vector in the invention is the motion vector of the moving object.
And step S3: constructing an abnormal event identification criterion; the specific method comprises the following steps:
s31: calculating target characteristic parameters by combining a target characteristic vector set;
calculating characteristic parameters of the moving target by using a multi-source dynamic information fusion algorithm and combining a motion vector set of the moving target; therefore, the construction of the abnormal event identification criterion in the video stream is realized.
The invention constructs abnormal event identification criterion by utilizing three characteristics of motion vector kinetic energy, namely optical flow vector kinetic energy, motion direction information entropy and adjacent video frame mutual information, and comprises the following specific steps:
s311, calculating the average kinetic energy of the motion vector of the moving target as a judgment index of the motion intensity of the dynamic target in the video image;
s312, calculating the motion direction information entropy of the moving target;
and (3) calculating the motion direction information entropy of the moving object by using the formula (1) as the dispersity, namely the chaos degree, of the motion direction of the foreground dynamic object in the video.
Wherein, p (x)i) Is the probability distribution p (x) of the occurrence of an eventi)=w(xi) And m,0 < i < n, wherein m is the total number of motion vectors in each frame of image. w (x)i)={qi0 < i < n } is aHistogram of motion vector direction of frame image, where n represents the number of square bars, qiIndicating the number of motion vectors corresponding to a certain direction in the ith strip.
S313, calculating the information quantity of adjacent video frames;
and (3) calculating the information quantity of adjacent video frames by using the formula (2) as the motion mode abrupt change characteristics in the video image.
It should be noted that the mutual information quantity is proposed based on the similarity criterion of the mutual information in the information theory, and can be used to describe the degree of similarity between the motion vector fields of the two images.
S32: inputting the target characteristic parameters into an abnormal event recognition model for training;
the steps S311, S312, and S313 are used to calculate the motion characteristic parameters of the moving object corresponding to the normal video frame and the abnormal video frame, i.e. the average motion vector kinetic energy, the motion direction information entropy, and the mutual information amount of the adjacent video frames of the moving object, respectively, and transmit the calculated normal motion characteristic parameters and abnormal characteristic parameters as inputs to the abnormal event recognition model for training, so as to classify and recognize the abnormal event in the video stream.
It should be noted that the anomaly identification model is trained by using the inclusion v4 network in the present invention.
S4: and identifying whether the abnormal event occurs in the video stream according to the abnormal event identification criterion.
It should be noted that, the average motion vector kinetic energy is used to represent the intensity of the motion of the dynamic target in the video, and the motion direction information entropy is used to represent the dispersion, i.e. the chaos, of the motion direction of the dynamic target in the video; and the mutual information quantity of adjacent video frames is used for representing the sudden change characteristics of the motion mode in the video image.
And S5, when the occurrence of the abnormal event is detected, responding to the abnormal event.
After the abnormal event is detected, the early warning and the occurrence information of the abnormal event can be further started, for example, the signal of the abnormal event is transmitted back to the monitoring center, and the emergency plan is synchronously started by the staff.
In addition, when the video content is monitored by the abnormal event identification algorithm, once the abnormal event is detected, the video image of the abnormal event can be automatically intercepted and displayed on a monitoring screen, various parameters such as the geographic position information, the camera angle information, the time information and the like of the place where the abnormal event occurs are automatically acquired and transmitted back to a monitoring center, the video images of a period of time before and after the event occurs are automatically stored according to the time when the abnormal event occurs, the whole abnormal event occurrence process is completely recorded, and the image of the abnormal event can be further amplified.
Example 2
In the monitoring and early warning system provided in this embodiment, the method and algorithm mentioned in embodiment 1 need to be applied, and are not discussed in this embodiment, and the monitoring and early warning system includes an acquisition and preprocessing module 100, a display module 200, an abnormal event identification module 300, an early warning and information backtracking module 400, and a communication module 500;
the acquisition and preprocessing module 100 is used for acquiring and storing a video stream and preprocessing the video stream;
an abnormal event identification module 300, configured to determine whether an abnormal event occurs in the video stream;
the abnormal event recognition module 300 includes an abnormal event determination module 310 and an abnormal information positioning module 320;
an abnormal event determination module 310, configured to construct the abnormal event identification basis, and determine whether an abnormal event occurs in the preprocessed video stream;
the abnormal information positioning module 320 is used for returning the geographic position information of the abnormal event.
The early warning and information backtracking module 400 is used for starting an early warning mechanism when an abnormal event occurs and transmitting the information of the abnormal event back to the monitoring center;
the display module 200 is configured to display the video stream by using any one of a grid arrangement method and a single-point arrangement method;
and a communication module 500 for communication connection between the modules.
Example 3
The present embodiment provides a computer storage medium, which stores one or more programs, wherein the one or more programs are executable by one or more processors to implement the monitoring and early-warning method described in embodiment 1, and further, the monitoring and early-warning system described in embodiment 2 can be installed in the computer storage medium.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (8)
1. A monitoring and early warning method is characterized by comprising the following steps:
s1: acquiring a video stream, and preprocessing the video stream;
s2: acquiring target characteristics of the video stream after preprocessing;
s3: constructing an abnormal event identification criterion;
s4: identifying whether an abnormal event occurs in the video stream according to the abnormal event identification criterion;
s5: when the occurrence of the abnormal event is detected, responding to the abnormal event;
the preprocessing of the video stream in the S1 comprises the following steps:
s11: decoding the video stream and extracting key frames; analyzing a video stream into video frame images, screening the video frame images with moving targets and marking the video frame images as key frames;
s12: preprocessing the key frame; specifically, noise reduction processing is carried out on salt and pepper noise and Gaussian noise in a key frame image by using image processing modes of median filtering and mean filtering respectively;
s13: performing image optimization on the preprocessed key frames; specifically, foreground detection is carried out on the key frame highlight after noise reduction by using a Gaussian mixture model based on an EM algorithm, and shadow removal is carried out by using an RCB color model; carrying out image optimization by using a binary morphological algorithm, namely carrying out denoising operation on the preliminarily obtained image, namely respectively carrying out corrosion, expansion, opening operation and closing operation, and finally obtaining a binary key frame foreground image, namely a binary image of the moving target;
the specific steps of S2 include:
s21: calculating an interest point feature coordinate set of the target feature of each frame in the video stream; specifically, a key frame mask template is constructed, each frame is calculated by combining a feature extraction algorithm to obtain an interest point feature coordinate set of target features, namely, a moving target binary image obtained in S1 is used as a binarization mask template, the feature extraction algorithm is utilized to realize the detection and extraction of the interest point features of each frame of video image, and the target features, namely, the interest point feature coordinate set of a moving target, are obtained;
s22: and calculating the feature coordinate set of the interest points to construct the target feature vector set.
2. A monitoring and pre-warning method according to claim 1, wherein the step S3 further comprises:
s31: calculating target characteristic parameters by combining the target characteristic vector set;
s32: and inputting the target characteristic parameters into an abnormal event recognition model for training.
3. A monitoring and pre-warning method according to claim 2, wherein the target characteristic parameters include: motion vector kinetic energy, motion direction information entropy and adjacent target information quantity.
4. A monitoring and pre-warning method according to claim 1, wherein the step S5 further comprises: and after the abnormal event is detected, automatically carrying out early warning and recording on the abnormal event.
5. A monitoring and pre-warning method according to claim 1, wherein the step S5 further includes locating the position of the abnormal event after the abnormal event is detected.
6. A monitoring and early warning system applied to the method of any one of claims 1 to 5, wherein the system comprises: the system comprises an acquisition and preprocessing module, an abnormal event identification module, an early warning and information backtracking module, a display module and a communication module;
the acquisition and preprocessing module is used for acquiring and storing a video stream and preprocessing the video stream;
the abnormal event identification module is used for judging whether an abnormal event occurs in the preprocessed video stream;
the early warning and information backtracking module is used for starting an early warning mechanism when the abnormal event occurs and transmitting the abnormal event information back to the monitoring center;
the display module is used for displaying the video stream by adopting any one of a gridding arrangement method or a single-point arrangement method;
and the communication module is used for communication connection among the modules.
7. The monitoring and pre-warning system of claim 6, wherein the abnormal event recognition module comprises:
the abnormal event distinguishing module is used for constructing the abnormal event identification basis and distinguishing whether the abnormal event occurs in the preprocessed video stream;
and the abnormal information positioning module is used for returning the geographical position information of the abnormal event.
8. A computer storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the monitoring and forewarning method of any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010955424.9A CN112084963B (en) | 2020-09-11 | 2020-09-11 | Monitoring early warning method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010955424.9A CN112084963B (en) | 2020-09-11 | 2020-09-11 | Monitoring early warning method, system and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112084963A CN112084963A (en) | 2020-12-15 |
CN112084963B true CN112084963B (en) | 2022-11-01 |
Family
ID=73737642
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010955424.9A Active CN112084963B (en) | 2020-09-11 | 2020-09-11 | Monitoring early warning method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112084963B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112530021B (en) * | 2020-12-24 | 2023-06-23 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing data |
CN113673406A (en) * | 2021-08-16 | 2021-11-19 | 杭州图灵视频科技有限公司 | Curtain wall glass burst detection method and system, electronic equipment and storage medium |
CN113992896A (en) * | 2021-10-28 | 2022-01-28 | 南京奥拓电子科技有限公司 | Safety monitoring and early warning management method, system and storage medium |
CN114554153A (en) * | 2022-02-24 | 2022-05-27 | 西安健尚智能科技有限公司 | Video streaming transmission control method for monitoring system and monitoring system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180229A (en) * | 2017-05-04 | 2017-09-19 | 南京邮电大学 | Anomaly detection method based on the direction of motion in a kind of monitor video |
CN111062281A (en) * | 2019-12-05 | 2020-04-24 | 亿利生态大数据有限公司 | Abnormal event monitoring method and device, storage medium and electronic equipment |
CN111601074A (en) * | 2020-04-24 | 2020-08-28 | 平安科技(深圳)有限公司 | Security monitoring method and device, robot and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108629316A (en) * | 2018-05-08 | 2018-10-09 | 东北师范大学人文学院 | A kind of video accident detection method of various visual angles |
-
2020
- 2020-09-11 CN CN202010955424.9A patent/CN112084963B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180229A (en) * | 2017-05-04 | 2017-09-19 | 南京邮电大学 | Anomaly detection method based on the direction of motion in a kind of monitor video |
CN111062281A (en) * | 2019-12-05 | 2020-04-24 | 亿利生态大数据有限公司 | Abnormal event monitoring method and device, storage medium and electronic equipment |
CN111601074A (en) * | 2020-04-24 | 2020-08-28 | 平安科技(深圳)有限公司 | Security monitoring method and device, robot and storage medium |
Non-Patent Citations (1)
Title |
---|
基于Vibe改进算法的中高密度人群异常检测方法研究;李丹丹;《中国优秀硕士学位论文全文数据库社会科学Ⅰ辑》;20180215;第14-60页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112084963A (en) | 2020-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112084963B (en) | Monitoring early warning method, system and storage medium | |
CN110044486B (en) | Method, device and equipment for avoiding repeated alarm of human body inspection and quarantine system | |
CN111191586B (en) | Method and system for inspecting wearing condition of safety helmet of personnel in construction site | |
CN106128022B (en) | A kind of wisdom gold eyeball identification violent action alarm method | |
CN111047818A (en) | Forest fire early warning system based on video image | |
CN106128053A (en) | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device | |
CN112396658B (en) | Indoor personnel positioning method and system based on video | |
KR102149832B1 (en) | Automated Violence Detecting System based on Deep Learning | |
CN103106766A (en) | Forest fire identification method and forest fire identification system | |
CN111091098B (en) | Training method of detection model, detection method and related device | |
CN111325048B (en) | Personnel gathering detection method and device | |
CN104881643B (en) | A kind of quick remnant object detection method and system | |
CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
CN111476964A (en) | Remote forest fire prevention monitoring system and method | |
CN112188164A (en) | AI vision-based violation real-time monitoring system and method | |
CN113963301A (en) | Space-time feature fused video fire and smoke detection method and system | |
CN111401310B (en) | Kitchen sanitation safety supervision and management method based on artificial intelligence | |
CN113283369A (en) | Port wharf operating personnel safety protection measure monitoring system and method | |
CN105095891A (en) | Human face capturing method, device and system | |
CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
CN102339465B (en) | Method and system for detecting the mutual closing and/or contact of moving objects | |
CN111753587B (en) | Ground falling detection method and device | |
CN115719464A (en) | Water meter durability device water leakage monitoring method based on machine vision | |
TWI730795B (en) | Multi-target human body temperature tracking method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |