CN109040693A - Intelligent warning system and method - Google Patents
Intelligent warning system and method Download PDFInfo
- Publication number
- CN109040693A CN109040693A CN201811014170.XA CN201811014170A CN109040693A CN 109040693 A CN109040693 A CN 109040693A CN 201811014170 A CN201811014170 A CN 201811014170A CN 109040693 A CN109040693 A CN 109040693A
- Authority
- CN
- China
- Prior art keywords
- video image
- intelligent
- video
- semantic segmentation
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of intelligent warning system and methods, and wherein the system includes video acquisition module, intelligent analysis module, interactive module and alarm module.Using the intelligent warning system and method in the invention, video image is detected and analyzed based on deep neural network model, the fishing behavior close to the pond periphery of power circuit can accurately be detected, system operations performance is able to satisfy the requirement to tens road video real-time detections simultaneously in the case where configuring a general GPU server, while can avoid the influence of other chaff interferents.
Description
Technical field
The present invention relates to field of automation technology more particularly to dispatching technique field, in particular to a kind of intelligent alarm systems
System and method.
Background technique
Although power supply department would generally hang with the warning sign that no fishig on the pool side close to power circuit, by fishing
Caused electric shock accidents also happens occasionally.The generation of such accident can be reduced by increasing the manual patrol frequency, but is manually patrolled
Depending on having the characteristics that at high cost, poor in timeliness.Also there is power supply department to use close to the pool side of power circuit installation view at present
The monitored picture on pond periphery is transferred to monitoring center and is remotely checked by frequency monitoring device, but since monitoring point is numerous, depending on
Frequency monitoring operator on duty dig-ins screen guard, and easily causing visual fatigue leads to missing inspection.Therefore manual patrol or remotely screen is dig-inned
Curtain guard on duty is not an efficient solution.
Due in the video monitoring system on the pool side close to power circuit, the monitoring depth of field of camera, illumination condition,
Monitoring visual angle is frequently not changeless, the intelligence view in this monitoring based on general video image processing technology
Frequency division analysis system is not often high to the detection accuracy of fishing behavior.
Since fishing rod is more elongated, when carrying out target mark using the object detection method based on deep neural network,
Its Bounding Box often occupies the most areas of entire image, therefore will not be very to the detection accuracy of fishing rod
It is high.
Therefore either the target based on deep neural network is still utilized to examine using general video image processing technology
Survey technology, carrying out intelligent auto-alarming to fishing protection against electric shock is all very difficult, existing fishing electric shock prevention method and system
Detection accuracy is not high, can generate and much judge by accident or fail to judge, the electric shock thing that may cause to the fishing behavior by power circuit
Therefore alarm preventive effect well is not had.
Summary of the invention
The purpose of the present invention is overcoming the above-mentioned prior art, a kind of intelligence announcement that can be taken precautions against in time is provided
Alert system and method.
To achieve the goals above, intelligent warning system of the invention and method are as follows:
The intelligent warning system, is mainly characterized by, and the system includes:
Video acquisition module, for acquiring real time video image；
Intelligent analysis module is connected, for analyzing the video with the video acquisition module by wireless network
Whether image meets systemic presupposition condition；
Alarm module is connected by an interactive module with the intelligent analysis module, in the video image
When meeting systemic presupposition condition, alarm signal is issued.
The intelligent analysis module of the intelligent warning system includes:
Taxon is connected with the video acquisition module, for the video image to be classified, and stores
Meet the first video image of the first preset condition；
Detection unit is connected with the taxon, for detecting whether first video image meets second
Preset condition；
Semantic segmentation unit is connected with the detection unit, pre- for meeting second in first video image
If when condition, carrying out semantic segmentation to first video image, and detect first video image after semantic segmentation to be
It is no to meet third preset condition.
The interactive module of the intelligent warning system is also connected with the video acquisition module, for configuring the video
The acquisition parameter of acquisition module.
The intelligent warning system further include:
Charhing unit is connected with the video acquisition module, for carrying out charging operations.
The intelligent warning system is applied to anti-fishing electric shock field.
The intelligent alarm method realized based on above-mentioned intelligent warning system, is mainly characterized by, and the method includes
Following steps:
(1) video acquisition module described in carries out the real-time acquisition of video image；
(2) intelligent analysis module described in analyzes whether the video image meets systemic presupposition condition, and is meeting
Continue step (3) after system preset condition, is otherwise back to step (1)；
(3) alarm module described in issues alarm signal.
In the intelligent alarm method, the intelligent analysis module includes taxon, detection unit and semantic segmentation list
Member, the step (2) the following steps are included:
(2.1) taxon described in classifies the video image, and stores and meet the of the first preset condition
One video image；
(2.2) detection unit described in detects whether first video image meets the second preset condition, if meeting
(2.3) are entered step, step (1) is otherwise back to；
(2.3) the semantic segmentation unit described in carries out semantic segmentation to first video image, and detects semantic segmentation
Whether first video image afterwards meets third preset condition, enters step (3) if meeting, is otherwise back to step
(1)。
The step of intelligent alarm method (2.2) specifically:
The detection unit is based on deep neural network model and detects whether first video image meets second in advance
If condition.
The step of intelligent warning system (2.3) the following steps are included:
Semantic segmentation unit described in (2.3.1) is based on deep neural network model and carries out language to first video image
Justice segmentation, and bianry image is exported, the bianry image is first video image after semantic segmentation；
(2.3.2) carries out the single variable linear regression analysis of the bianry image, presets item to judge whether to meet third
Part enters step (3) if meeting, is otherwise back to step (1).
Using the intelligent warning system and method in the invention, video image is carried out based on deep neural network model
Detection and analysis can accurately detect the fishing behavior close to the pond periphery of power circuit, and system operations performance, which is able to satisfy, is matching
Requirement in the case where setting a general GPU server while to tens road video real-time detections, while can avoid other interference
The influence of object.
Detailed description of the invention
Fig. 1 is the attachment structure schematic diagram of intelligent warning system of the invention.
Fig. 2 is the specific embodiment using intelligent warning system of the invention.
Specific embodiment
It is further to carry out combined with specific embodiments below in order to more clearly describe technology contents of the invention
Description.
The present invention relates to a kind of intelligent warning systems (to please refer to shown in Fig. 1), comprising:
Video acquisition module, for acquiring real time video image；
Intelligent analysis module is connected, for analyzing the video with the video acquisition module by wireless network
Whether image meets systemic presupposition condition；
Alarm module is connected by an interactive module with the intelligent analysis module, in the video image
When meeting systemic presupposition condition, alarm signal is issued.
The intelligent analysis module of the intelligent warning system includes:
Taxon is connected with the video acquisition module, for the video image to be classified, and stores
Meet the first video image of the first preset condition；
Detection unit is connected with the taxon, for detecting whether first video image meets second
Preset condition；
Semantic segmentation unit is connected with the detection unit, pre- for meeting second in first video image
If when condition, carrying out semantic segmentation to first video image, and detect first video image after semantic segmentation to be
It is no to meet third preset condition.
The interactive module of the intelligent warning system is also connected with the video acquisition module, for configuring the video
The acquisition parameter of acquisition module.
The invention further relates to a kind of intelligent alarm methods realized based on above-mentioned intelligent warning system, comprising the following steps:
(1) video acquisition module described in carries out the real-time acquisition of video image；
(2) intelligent analysis module described in analyzes whether the video image meets systemic presupposition condition, and is meeting
Continue step (3) after system preset condition, is otherwise back to step (1)；
(3) alarm module described in issues alarm signal.
In the intelligent alarm method, the intelligent analysis module includes taxon, detection unit and semantic segmentation list
Member, the step (2) the following steps are included:
(2.1) taxon described in classifies the video image, and stores and meet the of the first preset condition
One video image；
(2.2) detection unit described in detects whether first video image meets the second preset condition, if meeting
(2.3) are entered step, step (1) is otherwise back to；
(2.3) the semantic segmentation unit described in carries out semantic segmentation to first video image, and detects semantic segmentation
Whether first video image afterwards meets third preset condition, enters step (3) if meeting, is otherwise back to step
(1)。
The step of intelligent alarm method (2.2) specifically:
The detection unit is based on deep neural network model and detects whether first video image meets second in advance
If condition.
The step of intelligent warning system (2.3) the following steps are included:
Semantic segmentation unit described in (2.3.1) is based on deep neural network model and carries out language to first video image
Justice segmentation, and bianry image is exported, the bianry image is first video image after semantic segmentation；
(2.3.2) carries out the single variable linear regression analysis of the bianry image, presets item to judge whether to meet third
Part enters step (3) if meeting, is otherwise back to step (1).
In a specific embodiment, video acquisition module of the invention may include high definition ball machine, with 360 degree of acquisition videos
Image, specifically, in order to also can be carried out the acquisition of video image at night, the video acquisition module is further equipped with
Infrared night vision unit.
In a specific embodiment, alarm module of the invention includes power amplifier and high-pitched speaker, and is interacted
The control of module is output to high-pitched speaker after being amplified by power amplifier and is broadcasted when carrying out the transmission of alarm signal.
In a specific embodiment, intelligent analysis module of the invention is remotely being realized, and by the control of interactive module,
The setting of the parameters such as starting, termination and analysis video number, the analysis frequency of the intelligent analysis module is carried out by interactive module,
And the analysis result of the intelligent analysis module also can transmit interactive module and carry out real-time exhibition.
In a specific embodiment, interactive module of the invention is realized in user terminal, and by computer WEB interface or
Cell phone application interacts, and the program request of live video is checked in realization, the control of intelligent analysis module, the confirmation for analyzing result, defeated
The functions such as statistical analysis of alarm prompt voice messaging, each monitoring point and each period warning information out.
In one embodiment, it please refers to shown in Fig. 2, is led for intelligent warning system of the invention in anti-fishing electric shock technology
Application in domain, specifically includes the following steps:
(1) image of each monitoring point is acquired by video acquisition module in turn at regular intervals, time interval can be
It is configured in interactive module, such as time interval can be taken as 1 second, acquired image is gone fishing by 4G network transmission to backstage
In behavior intelligent analysis system；
(2) by acquired image be input to pedestrian detection deep neural network carry out pedestrian detection, judge be in image
It is no to have " people ", as detected " people " in image, then continue the following steps；Otherwise it is back to and continues to acquire new figure in step (1)
Picture；
It (3) is also to pass through by target detection and semantic segmentation deep neural network model and its network, model parameter
Obtained by training field samples image study, this network can carry out the target detection and " fishing rod " of " holding the people of fishing rod " simultaneously
Semantic segmentation, target detection and semantic segmentation deep neural network can select the Mask RCNN network architecture；
(4) " image of someone " detection unit is input to detect, if detecting " people for holding fishing rod ",
Continue the following steps；Otherwise it is back to and continues to acquire new image in step (1)；
(5) by semantic segmentation deep neural network, semantic segmentation, output are carried out to the fishing rod in Bounding Box
For the bianry image of fishing rod；
(6) by single variable linear regression block, a linear equation is fitted to the bianry image of fishing rod, and calculate
The slope of linear equation out；
(7) slope for the fishing rod linear equation for fitting present image with it is same before certain intervals time (configurable)
The slope for the fishing rod linear equation that image fits all the way is compared, if difference is greater than threshold value, judges to go fishing
Pole is moved, and continues the following steps；Otherwise it is back to and continues to acquire new image in step (1).Such as time interval
It can be configured to 10 seconds, the threshold value of slope differences can be set as 0.05；
(8) it beeps, and pop-up display this road monitor video, is reminded at monitoring operator on duty in interactive module
Reason, monitoring operator on duty confirms after checking, once confirmation, then save alarm picture and issue from trend scene alarm device
Alert broadcast is reported by mistake in this way, is then cancelled.
In a specific embodiment, intelligent warning system of the invention and method can be applied to anti-fishing electric shock field,
Specifically, high-precision inspection is carried out to the people in video image first with the target detection technique based on deep neural network
It surveys, filters out the image of nobody, system operations performance can not only be substantially improved in this way, and can be reduced erroneous detection.Thereafter sharp again
With target detection and semantic segmentation technology based on deep neural network, filtered image is detected again and " holds fishing
The people of pole ", while semantic segmentation is carried out to fishing rod target in Bounding Box, then the fishing rod being partitioned into is used
Single variable linear regression algorithm fits a linear equation, calculates its slope, with same video figure all the way after a certain period of time
The slope of the fitting a straight line equation for the fishing rod that picture detects is compared, if slope differences are greater than a threshold value, then it is assumed that be
Fishing rod is moved, and due to having had been detected by this time, " people ", " people for holding fishing rod ", " people holds fishing rod
This 3 kinds fishing behavioral primitives of movement ", and then can accurately be judged as fishing behavior, and to the 3D of certain period of time view
For frequency according to being analyzed, further avoiding branch or other interfering object erroneous detections is fishing rod.
Using the intelligent warning system and method in the invention, video image is carried out based on deep neural network model
Detection and analysis can accurately detect the fishing behavior close to the pond periphery of power circuit, and system operations performance, which is able to satisfy, is matching
Requirement in the case where setting a general GPU server while to tens road video real-time detections, while can avoid other interference
The influence of object.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (9)
1. a kind of intelligent warning system, which is characterized in that the system includes:
Video acquisition module, for acquiring real time video image；
Intelligent analysis module is connected, for analyzing the video image with the video acquisition module by wireless network
Whether systemic presupposition condition is met；
Alarm module is connected by an interactive module with the intelligent analysis module, for meeting in the video image
When systemic presupposition condition, alarm signal is issued.
2. intelligent warning system according to claim 1, which is characterized in that the intelligent analysis module includes:
Taxon is connected with the video acquisition module, for the video image to be classified, and stores and meets
First video image of the first preset condition；
Detection unit is connected with the taxon, and for detecting first video image, whether to meet second default
Condition；
Semantic segmentation unit is connected with the detection unit, for meeting the second default item in first video image
When part, semantic segmentation is carried out to first video image, and whether detect first video image after semantic segmentation full
Sufficient third preset condition.
3. intelligent warning system according to claim 1, which is characterized in that the interactive module also with the video
Acquisition module is connected, for configuring the acquisition parameter of the video acquisition module.
4. intelligent warning system according to claim 1, which is characterized in that the system further include:
Charhing unit is connected with the video acquisition module, for carrying out charging operations.
5. intelligent warning system according to any one of claim 1 to 4, which is characterized in that the system is applied to
Anti- fishing electric shock field.
6. a kind of intelligent alarm method realized based on intelligent warning system described in claim 1, which is characterized in that described
Method the following steps are included:
(1) video acquisition module described in carries out the real-time acquisition of video image；
(2) intelligent analysis module described in analyzes whether the video image meets systemic presupposition condition, and pre- meeting system
If continuing step (3) after condition, it is otherwise back to step (1)；
(3) alarm module described in issues alarm signal.
7. intelligent alarm method according to claim 6, which is characterized in that the intelligent analysis module includes grouping sheet
Member, detection unit and semantic segmentation unit, the step (2) the following steps are included:
(2.1) taxon described in classifies the video image, and stores the first view for meeting the first preset condition
Frequency image；
(2.2) detection unit described in detects whether first video image meets the second preset condition, enters if meeting
Step (2.3) is otherwise back to step (1)；
(2.3) semantic segmentation unit described in carries out semantic segmentation to first video image, and after detecting semantic segmentation
Whether first video image meets third preset condition, enters step (3) if meeting, is otherwise back to step (1).
8. intelligent alarm method according to claim 7, which is characterized in that the step (2.2) specifically:
The detection unit is based on deep neural network model and detects whether first video image meets the second default item
Part.
9. intelligent warning system according to claim 7, which is characterized in that the step (2.3) the following steps are included:
Semantic segmentation unit described in (2.3.1) is based on deep neural network model and carries out semantic point to first video image
It cuts, and exports bianry image, the bianry image is first video image after semantic segmentation；
(2.3.2) carries out the single variable linear regression analysis of the bianry image, to judge whether to meet third preset condition, if
Satisfaction then enters step (3), is otherwise back to step (1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014170.XA CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014170.XA CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040693A true CN109040693A (en) | 2018-12-18 |
| CN109040693B CN109040693B (en) | 2020-11-10 |
Family
ID=64622681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811014170.XA Active CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040693B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110503812A (en) * | 2019-08-23 | 2019-11-26 | 陈�峰 | A kind of flammability hazard source behavior monitoring system and method based on convolutional neural networks |
| CN111583265A (en) * | 2020-05-07 | 2020-08-25 | 赛特斯信息科技股份有限公司 | Method for realizing phishing behavior detection processing based on codec structure and corresponding semantic segmentation network system |
| CN111695492A (en) * | 2020-06-10 | 2020-09-22 | 国网山东省电力公司电力科学研究院 | Method and system for detecting fishing hidden danger of power transmission line |
| CN112233353A (en) * | 2020-09-24 | 2021-01-15 | 国网浙江兰溪市供电有限公司 | Artificial intelligence-based anti-fishing monitoring system and monitoring method thereof |
| CN113305858A (en) * | 2021-06-07 | 2021-08-27 | 仲恺农业工程学院 | Visual robot method and device for removing shellfish in raw water pipeline |
| CN114124653A (en) * | 2021-10-20 | 2022-03-01 | 北京电子工程总体研究所 | Real-time alarm method, device and system for command control system |
| CN114241717A (en) * | 2021-12-17 | 2022-03-25 | 广州西麦科技股份有限公司 | Electric shock prevention safety early warning method and system |
| CN115240278A (en) * | 2022-09-23 | 2022-10-25 | 东莞先知大数据有限公司 | Fishing behavior detection method |
| CN115331386A (en) * | 2022-10-13 | 2022-11-11 | 合肥中科类脑智能技术有限公司 | Anti-fishing detection alarm system and method based on computer vision |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090118582A (en) * | 2008-05-14 | 2009-11-18 | 주식회사 토페스 | Unexpcted accident monitoring system |
| CN104484666A (en) * | 2014-12-17 | 2015-04-01 | 中山大学 | Advanced image semantic parsing method based on human-computer interaction |
| CN106845396A (en) * | 2017-01-18 | 2017-06-13 | 南京理工大学 | Illegal fishing Activity recognition method based on automated graphics identification |
| CN107169468A (en) * | 2017-05-31 | 2017-09-15 | 北京京东尚科信息技术有限公司 | Method for controlling a vehicle and device |
| CN107220604A (en) * | 2017-05-18 | 2017-09-29 | 清华大学深圳研究生院 | A kind of fall detection method based on video |
| CN107341446A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | Specific pedestrian's method for tracing and system based on inquiry self-adaptive component combinations of features |
| CN206710819U (en) * | 2017-03-22 | 2017-12-05 | 国网山东省电力公司莱芜供电公司 | The supervisory systems and stringing tower of power transmission and transformation line |
-
2018
- 2018-08-31 CN CN201811014170.XA patent/CN109040693B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090118582A (en) * | 2008-05-14 | 2009-11-18 | 주식회사 토페스 | Unexpcted accident monitoring system |
| CN104484666A (en) * | 2014-12-17 | 2015-04-01 | 中山大学 | Advanced image semantic parsing method based on human-computer interaction |
| CN106845396A (en) * | 2017-01-18 | 2017-06-13 | 南京理工大学 | Illegal fishing Activity recognition method based on automated graphics identification |
| CN206710819U (en) * | 2017-03-22 | 2017-12-05 | 国网山东省电力公司莱芜供电公司 | The supervisory systems and stringing tower of power transmission and transformation line |
| CN107220604A (en) * | 2017-05-18 | 2017-09-29 | 清华大学深圳研究生院 | A kind of fall detection method based on video |
| CN107169468A (en) * | 2017-05-31 | 2017-09-15 | 北京京东尚科信息技术有限公司 | Method for controlling a vehicle and device |
| CN107341446A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | Specific pedestrian's method for tracing and system based on inquiry self-adaptive component combinations of features |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110503812A (en) * | 2019-08-23 | 2019-11-26 | 陈�峰 | A kind of flammability hazard source behavior monitoring system and method based on convolutional neural networks |
| CN111583265A (en) * | 2020-05-07 | 2020-08-25 | 赛特斯信息科技股份有限公司 | Method for realizing phishing behavior detection processing based on codec structure and corresponding semantic segmentation network system |
| CN111695492A (en) * | 2020-06-10 | 2020-09-22 | 国网山东省电力公司电力科学研究院 | Method and system for detecting fishing hidden danger of power transmission line |
| CN112233353A (en) * | 2020-09-24 | 2021-01-15 | 国网浙江兰溪市供电有限公司 | Artificial intelligence-based anti-fishing monitoring system and monitoring method thereof |
| CN113305858A (en) * | 2021-06-07 | 2021-08-27 | 仲恺农业工程学院 | Visual robot method and device for removing shellfish in raw water pipeline |
| CN114124653A (en) * | 2021-10-20 | 2022-03-01 | 北京电子工程总体研究所 | Real-time alarm method, device and system for command control system |
| CN114241717A (en) * | 2021-12-17 | 2022-03-25 | 广州西麦科技股份有限公司 | Electric shock prevention safety early warning method and system |
| CN115240278A (en) * | 2022-09-23 | 2022-10-25 | 东莞先知大数据有限公司 | Fishing behavior detection method |
| CN115240278B (en) * | 2022-09-23 | 2023-01-06 | 东莞先知大数据有限公司 | Fishing behavior detection method |
| CN115331386A (en) * | 2022-10-13 | 2022-11-11 | 合肥中科类脑智能技术有限公司 | Anti-fishing detection alarm system and method based on computer vision |
| CN115331386B (en) * | 2022-10-13 | 2022-12-27 | 合肥中科类脑智能技术有限公司 | Prevent fishing detection alarm system based on computer vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040693B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040693A (en) | Intelligent warning system and method | |
| US10943357B2 (en) | Video based indoor leak detection | |
| CA2860014C (en) | Video based indoor leak detection | |
| US20190122082A1 (en) | Intelligent content displays | |
| KR101822924B1 (en) | Image based system, method, and program for detecting fire | |
| US20130265423A1 (en) | Video-based detector and notifier for short-term parking violation enforcement | |
| US8301577B2 (en) | Intelligent monitoring system for establishing reliable background information in a complex image environment | |
| KR101927364B1 (en) | Outside Intruding and Monitering Radar Syatem Based on Deep -Learning and Method thereof | |
| KR20080054368A (en) | Flame detecting method and device | |
| CN103606236A (en) | Real time safety monitoring system based on distribution type optical fiber invasion alarm unit | |
| CN104658188A (en) | Channel security early-warning system and channel early-warning method | |
| CN107122743A (en) | Security-protecting and monitoring method, device and electronic equipment | |
| US10326917B2 (en) | Monitoring camera | |
| CN112757300A (en) | Robot protection system and method | |
| CN106210636A (en) | Wisdom gold eyeball people based on intelligent video technology and thing Activity recognition instrument | |
| JP2018151834A (en) | Lost child detection apparatus and lost child detection method | |
| CN101930540A (en) | Video-based multi-feature fusion flame detecting device and method | |
| CN110928305A (en) | Patrol method and system for railway passenger station patrol robot | |
| KR101552564B1 (en) | Fusion security system based on gas sensor and IP network camera | |
| CN104463913A (en) | Intelligent illegal parking detection device and method | |
| CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
| KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
| CN202904792U (en) | Intelligent visualized alarm system | |
| CN114445779B (en) | Method, system, equipment and medium for determining safety state of area to be detected | |
| CN112637418A (en) | Danger reminding method and device |
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 |