CN108830143A - A kind of video analytic system based on deep learning - Google Patents
A kind of video analytic system based on deep learning Download PDFInfo
- Publication number
- CN108830143A CN108830143A CN201810415478.9A CN201810415478A CN108830143A CN 108830143 A CN108830143 A CN 108830143A CN 201810415478 A CN201810415478 A CN 201810415478A CN 108830143 A CN108830143 A CN 108830143A
- Authority
- CN
- China
- Prior art keywords
- video
- deep learning
- video analysis
- analysis terminal
- image data
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 60
- 238000004458 analytical method Methods 0.000 claims abstract description 111
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000004891 communication Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000001537 neural effect Effects 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003585 interneuronal effect Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to fire fighting monitoring technical fields, provide a kind of video analytic system based on deep learning.The system includes:Camera, video analysis terminal, video management server and the video analysis deep learning server communicated to connect respectively with video analysis terminal and video management server with camera communication connection;Video analysis deep learning server, for obtaining the first identification model camera by neural metwork training, for obtaining the image data of fire fighting monitoring point and being sent to video analysis terminal;Image data includes video data and/or image data;Video analysis terminal carries out Classification and Identification to image data by the first identification model, obtains dangerous discernment result and be sent to video management server for receiving the image data of camera transmission.The present invention improves image recognition accuracy using the method for deep learning, and maximization avoids erroneous detection or missing inspection, has stronger practicability and ease for use.
Description
Technical field
The invention belongs to fire Safety Assessment technical field more particularly to a kind of video analysis systems based on deep learning
System.
Background technique
With the setting of visible various cameras everywhere, fire-fighting is obtained by camera in real time in wisdom fire-fighting system
Alert becomes possibility, for example by video surveillance to obtain flame, smog, passageway for fire apparatus blocking and operator on duty not on duty etc.
Situation, then automatic alarm or remind related personnel.The existing video that overhead pass is imaged by server united analysis, service
Device data processing pressure is big, therefore the analyzable camera of individual server is limited, limits the capacity of the camera of system.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of video analytic system based on deep learning, it is current to solve
The video of overhead pass is imaged by server united analysis, the analyzable camera of individual server is limited, takes the photograph to limit
As head capacity the problem of.
The embodiment of the invention provides a kind of video analytic systems based on deep learning, including:
Camera, the video tube with the video analysis terminal of camera communication connection and the communication connection of video analysis terminal
Reason server and the video analysis deep learning service communicated to connect respectively with video analysis terminal and video management server
Device;
The video analysis deep learning server, for obtaining the first identification model by neural metwork training;
The camera, for obtaining the image data of fire fighting monitoring point and being sent to video analysis terminal;The image
Data include video data and/or image data;
The video analysis terminal, for receiving the image data of camera transmission, by the first identification model to image
Data carry out Classification and Identification, obtain dangerous discernment result and are sent to the video management server;
The video management server, for receiving the dangerous discernment of video analysis terminal transmission as a result, executing institute
State the corresponding preset alarm process flow of dangerous discernment result;
The video analysis deep learning server is also used to obtain video data corresponding with the dangerous discernment result
And/or image data to be to make training sample, and is trained by the training sample to the neural network, building can be known
The identification model is sent to video analysis terminal so that video analysis terminal will by the second identification model of not dangerous scene
First identification model is updated to second identification model.
Optionally, the dangerous scene includes flame scene and/or smog scene, and first identification model and second are known
Other model is specifically used for constructing the identification model that can identify flame scene and/or smog scene.
Optionally, the video analysis deep learning server is also used to:
Training sample is used for the training of deepness belief network;
The training result of deepness belief network is used for the initialization of multilayer perceptron;
Using multilayer perceptron first model good as neural metwork training.
Optionally, the video management server is also used to store and manage the image data of the camera.
Optionally, the video analytic system based on deep learning include at least two cameras, and including with institute
State at least one video analysis terminal of at least two cameras communication connection.
Optionally, the image data that the video analysis terminal is used to send at least two camera carries out batch
Processing.
Optionally, the video analysis terminal and camera pass through wireless network connection, video management server and video
Analysing terminal is taken by wireless communication connection, video analysis deep learning server and video analysis terminal and video management
Business device passes through wireless network connection respectively.
Optionally, the video analysis terminal connect with camera by wifi network, video management server and video
Analysing terminal is taken by wifi network communication connection, video analysis deep learning server and video analysis terminal and video management
Device be engaged in respectively by wifi network connection.
Optionally, the video analysis terminal connect with camera by cable network, video management server and video
Analysing terminal is taken by wired network communication connection, video analysis deep learning server and video analysis terminal and video management
Device be engaged in respectively by cable network connection.
Optionally, the image data further includes suspicious human face data, and the video analysis deep learning server is also used
The identification model of suspicious face scene can be identified in building.
The video analytic system based on deep learning of the embodiment of the present invention, first in video analysis deep learning server
The first identification model is obtained by neural metwork training, the image data of fire fighting monitoring point is obtained by camera and is sent to view
Frequency analysis terminal, the image data include video data and/or image data, receive camera in the video analysis terminal
The image data of transmission, and the first identification model by obtaining in deep learning server carries out classification knowledge to image data
Not, it obtains dangerous discernment result and is sent to the video management server;It is whole that video analysis is received in video management server
The dangerous discernment sent is held as a result, passing through the analysis work of the existing server of video analysis terminals share, system camera
Capacity can be more, meanwhile, the dangerous discernment result is sent to video analysis deep learning server, using deep learning
Method can be improved image recognition accuracy, and maximization avoids erroneous detection or missing inspection situation;In addition, passing through the video analysis depth
Learning server obtains video data corresponding with the dangerous discernment result and/or image data to make training sample, and
The neural network is trained by the training sample, the second identification model of hazard recognition scene is capable of in building, by institute
It states identification model and is sent to video analysis terminal so that first identification model is updated to described by video analysis terminal
Two identification models enable video analysis terminal to obtain history identification experience as human brain, not the limitation of scene, no
A set of algorithm must all be constructed to every kind of scene, therefore have versatility, scalability has stronger practicability and ease for use.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the schematic diagram for the video analytic system based on deep learning that the embodiment of the present invention one provides;
Fig. 2 be another embodiment of the present invention provides the video analytic system based on deep learning schematic diagram;
Fig. 3 is the schematic diagram for the video analytic system based on deep learning that yet another embodiment of the invention provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that "
Or " if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to
Determine " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
Fig. 1 shows the schematic diagram of the video analytic system based on deep learning of the offer of the embodiment of the present invention one.It is based on
The video analytic system of deep learning includes:Camera 11 divides with the video analysis terminal 12 of camera communication connection, with video
It analyses the video management server 13 of terminal communication connection and distinguishes communication link with video analysis terminal and video management server
The video analysis deep learning server 14 connect.
Video analysis deep learning server 12, for obtaining the first identification model by neural metwork training.
The camera 11, for obtaining the image data of fire fighting monitoring point and being sent to video analysis terminal;The shadow
As data include video data and/or image data.
Wherein, the first identification model is by inputting using the current collected image data of camera 11 as training sample
What neural metwork training obtained, image data includes video data and/or image data, and video data can shoot for camera
The fire fighting monitoring point arrived is in video in different time periods or image data.
Video analysis terminal 13, for receiving the image data of camera transmission, by the first identification model to image number
According to Classification and Identification is carried out, obtains dangerous discernment result and be sent to the video management server.
Wherein, Classification and Identification includes flame, the smog or other relevant to fire-fighting that Classification and Identification goes out in image data
Substance.Dangerous discernment result is determining recognition result, such as there are there are cigarettes in flame and/or image data in image data
Mist.
Video management server 14, for receiving the dangerous discernment of video analysis terminal transmission as a result, described in execution
The corresponding preset alarm process flow of dangerous discernment result.
For example, preset alarm process flow is the alert process process of fire alarm, specifically when dangerous discernment result is flame
Process flow herein with no restrictions.Wherein, type of alarm includes but is not limited to audio alert (such as whistle sound) and message alarm
(as alarm message occurs).
Video analysis deep learning server 12 is also used to obtain video data corresponding with the dangerous discernment result
And/or image data to be to make training sample, and is trained by the training sample to the neural network, building can be known
The identification model is sent to video analysis terminal so that video analysis terminal will by the second identification model of not dangerous scene
First identification model is updated to second identification model.
In embodiments of the present invention, the second identification model is real-time update, this enables video analysis terminal with most
The second new identification model removes the image data of the analysis collected fire fighting monitoring point of camera, more accurate so as to obtain
Recognition result.
Optionally, the dangerous scene includes flame scene and/or smog scene, and first identification model and second are known
Other model is specifically used for constructing the identification model that can identify flame scene and/or smog scene.
Optionally, video analysis deep learning server 12 is also used to:
Training sample is used for the training of deepness belief network (DBN);
The training result of deepness belief network (DBN) is used for the initialization of multilayer perceptron (MLP);
By multilayer perceptron (MLP) first model good as neural metwork training.
Wherein, deepness belief network be by training its interneuronal weight, can allow entire depth belief network by
Training data is generated according to maximum probability.
Optionally, the video management server is also used to store and manage the image data of the camera.
Optionally, the video analytic system based on deep learning includes at least two cameras as described in Figure 2, and including
With at least one video analysis terminal of at least two camera communication connection.
As shown in figure 3, when video analysis terminal is multiple, the processing of each video analysis terminal image data can be with
It is parallel, to improve the speed of processing with geometric multiple.It should be noted that each video analysis terminal can be in Fig. 3
It is communicated to connect at least two cameras and is not limited to two.
Wherein, the image data that the video analysis terminal is used to send at least two camera carries out at batch
Reason.
Optionally, the video analysis terminal and camera pass through wireless network connection, video management server and video
Analysing terminal is taken by wireless communication connection, video analysis deep learning server and video analysis terminal and video management
Business device passes through wireless network connection respectively.
Optionally, the video analysis terminal connect with camera by wifi network, video management server and video
Analysing terminal is taken by wifi network communication connection, video analysis deep learning server and video analysis terminal and video management
Device be engaged in respectively by wifi network connection.
Optionally, the video analysis terminal connect with camera by cable network, video management server and video
Analysing terminal is taken by wired network communication connection, video analysis deep learning server and video analysis terminal and video management
Device be engaged in respectively by cable network connection.
Optionally, the image data further includes suspicious human face data, and the video analysis deep learning server is also used
The identification model of suspicious face scene can be identified in building.
Wherein, suspicious human face data may include the face being not belonging in default face database.
The video analytic system based on deep learning of the embodiment of the present invention, first in video analysis deep learning server
The first identification model is obtained by neural metwork training, the image data of fire fighting monitoring point is obtained by camera and is sent to view
Frequency analysis terminal, the image data include video data and/or image data, receive camera in the video analysis terminal
The image data of transmission, and the first identification model by obtaining in deep learning server carries out classification knowledge to image data
Not, it obtains dangerous discernment result and is sent to the video management server;It is whole that video analysis is received in video management server
The dangerous discernment sent is held as a result, passing through the analysis work of the existing server of video analysis terminals share, system camera
Capacity can be more, meanwhile, the dangerous discernment result is sent to video analysis deep learning server, using deep learning
Method can be improved image recognition accuracy, and maximization avoids erroneous detection or missing inspection situation;In addition, passing through the video analysis depth
Learning server obtains video data corresponding with the dangerous discernment result and/or image data to make training sample, and
The neural network is trained by the training sample, the second identification model of hazard recognition scene is capable of in building, by institute
It states identification model and is sent to video analysis terminal so that first identification model is updated to described by video analysis terminal
Two identification models enable video analysis terminal to obtain history identification experience as human brain, not the limitation of scene, no
A set of algorithm must all be constructed to every kind of scene, therefore have versatility, scalability has stronger practicability and ease for use.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that:It still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of video analytic system based on deep learning, which is characterized in that including:Camera is communicated to connect with camera
Video analysis terminal, with video analysis terminal communication connection video management server and with video analysis terminal and view
The video analysis deep learning server that frequency management server communicates to connect respectively;
The video analysis deep learning server, for obtaining the first identification model by neural metwork training;
The camera, for obtaining the image data of fire fighting monitoring point and being sent to video analysis terminal;The image data
Including video data and/or image data;
The video analysis terminal, for receiving the image data of camera transmission, by the first identification model to image data
It is identified, obtain dangerous discernment result and is sent to the video management server;
The video management server, for receiving the dangerous discernment of video analysis terminal transmission as a result, executing the danger
The corresponding preset alarm process flow of dangerous recognition result;
The video analysis deep learning server, be also used to obtain corresponding with dangerous discernment result video data and/
Or image data to be to make training sample, and is trained by the training sample to the neural network, building can identify
The identification model is sent to video analysis terminal so that video analysis terminal is by institute by the second identification model of dangerous scene
It states the first identification model and is updated to second identification model.
2. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that it is described danger scene include
Flame scene and/or smog scene, first identification model and the second identification model, which are specifically used for building, can identify flame
The identification model of scene and/or smog scene.
3. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the video analysis depth
Learning server is also used to:
Training sample is used for the training of deepness belief network;
The training result of deepness belief network is used for the initialization of multilayer perceptron;
Using multilayer perceptron first model good as neural metwork training.
4. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the video management service
Device is also used to store and manage the image data of the camera.
5. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that described to be based on deep learning
Video analytic system include at least two cameras, and at least one including being communicated to connect at least two camera
A video analysis terminal.
6. as claimed in claim 5 based on the video analytic system of deep learning, which is characterized in that the video analysis terminal
Image data for sending at least two camera carries out batch processing.
7. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the video analysis terminal
It connect, regarded by wireless communication by wireless network connection, video management server and video analysis terminal with camera
Frequency analysis deep learning server and video analysis terminal and video management server pass through wireless network connection respectively.
8. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the video analysis terminal
It is connect with camera by wifi network, video management server and video analysis terminal are communicated to connect by wifi network, regarded
Frequency analysis deep learning server passes through wifi network with video analysis terminal and video management server respectively and connect.
9. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the video analysis terminal
It is connect with camera by cable network, video management server and video analysis terminal are connected by wired network communication, regarded
Frequency analysis deep learning server passes through cable network with video analysis terminal and video management server respectively and connect.
10. as described in claim 1 based on the video analytic system of deep learning, which is characterized in that the image data is also
Including suspicious human face data, the video analysis deep learning server is also used to construct the knowledge that can identify suspicious face scene
Other model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810415478.9A CN108830143A (en) | 2018-05-03 | 2018-05-03 | A kind of video analytic system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810415478.9A CN108830143A (en) | 2018-05-03 | 2018-05-03 | A kind of video analytic system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108830143A true CN108830143A (en) | 2018-11-16 |
Family
ID=64148131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810415478.9A Pending CN108830143A (en) | 2018-05-03 | 2018-05-03 | A kind of video analytic system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108830143A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020629A (en) * | 2019-04-10 | 2019-07-16 | 杨文广 | A kind of fusion intelligent video service system and method based on Internet of Things |
CN110335435A (en) * | 2019-06-26 | 2019-10-15 | 深圳市微纳集成电路与系统应用研究院 | Fire disaster alarming device based on Smoke Detection |
CN111476124A (en) * | 2020-03-26 | 2020-07-31 | 杭州鸿泉物联网技术股份有限公司 | Camera detection method and device, electronic equipment and system |
CN111665177A (en) * | 2020-06-11 | 2020-09-15 | 太原理工大学 | Laboratory protection system based on object recognition, toxic gas and heat source detection |
CN111818237A (en) * | 2020-07-21 | 2020-10-23 | 南京智金科技创新服务中心 | Video monitoring analysis system and method |
CN112116067A (en) * | 2020-08-27 | 2020-12-22 | 济南浪潮高新科技投资发展有限公司 | FPGA-based camera device implementation method and equipment |
CN112115975A (en) * | 2020-08-18 | 2020-12-22 | 山东信通电子股份有限公司 | Deep learning network model fast iterative training method and equipment suitable for monitoring device |
CN112532921A (en) * | 2020-10-28 | 2021-03-19 | 深圳英飞拓科技股份有限公司 | Water conservancy system intelligent monitoring implementation method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106097346A (en) * | 2016-06-13 | 2016-11-09 | 中国科学技术大学 | A kind of video fire hazard detection method of self study |
CN106845410A (en) * | 2017-01-22 | 2017-06-13 | 西安科技大学 | A kind of flame identification method based on deep learning model |
CN107808139A (en) * | 2017-11-01 | 2018-03-16 | 电子科技大学 | A kind of real-time monitoring threat analysis method and system based on deep learning |
-
2018
- 2018-05-03 CN CN201810415478.9A patent/CN108830143A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106097346A (en) * | 2016-06-13 | 2016-11-09 | 中国科学技术大学 | A kind of video fire hazard detection method of self study |
CN106845410A (en) * | 2017-01-22 | 2017-06-13 | 西安科技大学 | A kind of flame identification method based on deep learning model |
CN107808139A (en) * | 2017-11-01 | 2018-03-16 | 电子科技大学 | A kind of real-time monitoring threat analysis method and system based on deep learning |
Non-Patent Citations (1)
Title |
---|
顾志强等: "《黑科技》", 31 March 2017 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020629A (en) * | 2019-04-10 | 2019-07-16 | 杨文广 | A kind of fusion intelligent video service system and method based on Internet of Things |
CN110335435A (en) * | 2019-06-26 | 2019-10-15 | 深圳市微纳集成电路与系统应用研究院 | Fire disaster alarming device based on Smoke Detection |
CN111476124A (en) * | 2020-03-26 | 2020-07-31 | 杭州鸿泉物联网技术股份有限公司 | Camera detection method and device, electronic equipment and system |
CN111665177A (en) * | 2020-06-11 | 2020-09-15 | 太原理工大学 | Laboratory protection system based on object recognition, toxic gas and heat source detection |
CN111818237A (en) * | 2020-07-21 | 2020-10-23 | 南京智金科技创新服务中心 | Video monitoring analysis system and method |
WO2022016573A1 (en) * | 2020-07-21 | 2022-01-27 | 南京智金科技创新服务中心 | Video monitoring analysis system and method |
CN112115975A (en) * | 2020-08-18 | 2020-12-22 | 山东信通电子股份有限公司 | Deep learning network model fast iterative training method and equipment suitable for monitoring device |
CN112115975B (en) * | 2020-08-18 | 2024-04-12 | 山东信通电子股份有限公司 | Deep learning network model rapid iterative training method and equipment suitable for monitoring device |
CN112116067A (en) * | 2020-08-27 | 2020-12-22 | 济南浪潮高新科技投资发展有限公司 | FPGA-based camera device implementation method and equipment |
CN112532921A (en) * | 2020-10-28 | 2021-03-19 | 深圳英飞拓科技股份有限公司 | Water conservancy system intelligent monitoring implementation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108830143A (en) | A kind of video analytic system based on deep learning | |
CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
CN111582016A (en) | Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning | |
CN111263114B (en) | Abnormal event alarm method and device | |
CN109936634B (en) | fire-fighting dangerous case processing method and system based on Internet of things sensing | |
CN107911653A (en) | The module of intelligent video monitoring in institute, system, method and storage medium | |
US11729597B2 (en) | Digital twin disaster management system customized for underground public areas | |
CN105847769A (en) | Construction site behavior analysis system and analysis method | |
CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
CN107610431A (en) | A kind of anomaly analysis and alarm control system and method | |
CN115376269B (en) | Fire monitoring system based on unmanned aerial vehicle | |
KR20210123671A (en) | Drone blackbox system and drone monitoring action method | |
CN115880631A (en) | Power distribution station fault identification system, method and medium | |
CN107895453A (en) | Building safety warning system and method | |
CN109348173B (en) | Monitoring video management method and device and terminal equipment | |
KR102676020B1 (en) | Interaction behavior detection apparatus between objects in the image and, method thereof | |
CN114882688A (en) | Bar safety monitoring system based on edge calculation | |
KR20130136251A (en) | Method and apparatus for situation recognition using object energy function | |
CN109327681B (en) | Specific personnel identification alarm system and method thereof | |
CN107820051A (en) | Monitoring system and its monitoring method and device | |
CN115766401B (en) | Industrial alarm information analysis method and device, electronic equipment and computer medium | |
Baidal et al. | Design and testing of a dynamic reactive signage network towards fire emergency evacuations. | |
CN117156386A (en) | Intelligent positioning, calling for help and alarming intercom equipment for fire control | |
KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
CN111667657A (en) | Electromechanical management device and system method for communication 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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 1106, Hengmei Daxia, No. 3 Ganli Road, Jihua Street, Longgang District, Shenzhen City, Guangdong Province, 518000 Applicant after: Shenzhen CLP smart security Polytron Technologies Inc Address before: 518000 Workshop 401, No. 5, Juyin Science and Technology Industrial Factory Area, Buji Street, Longgang District, Shenzhen City, Guangdong Province Applicant before: Shenzhen CLP smart security Polytron Technologies Inc |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181116 |