CN110245696A - Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video - Google Patents
Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video Download PDFInfo
- Publication number
- CN110245696A CN110245696A CN201910464895.7A CN201910464895A CN110245696A CN 110245696 A CN110245696 A CN 110245696A CN 201910464895 A CN201910464895 A CN 201910464895A CN 110245696 A CN110245696 A CN 110245696A
- Authority
- CN
- China
- Prior art keywords
- illegal
- picture
- convolutional neural
- neural networks
- networks model
- 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
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Abstract
The invention discloses a kind of illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video, method include: the normal picture for obtaining the illegal picture shot under illegal scene and shooting under normal scene；By the illegal picture and normal picture, preset convolutional neural networks model is trained based on the mode of repetitive exercise, obtains target convolution neural network model；Picture to be identified is inputted into the target convolution neural network model, obtains the recognition result of the picture to be identified；If the recognition result is illegal, outputting alarm prompt.Through the invention, it the use of the picture that the judgement of convolutional neural networks model takes whether is illegal picture, when being judged as illegal picture, it is considered as and monitors illegal incidents, just outputting alarm prompt, so that related law enfrocement official handles illegal incidents, so that work of urban management is more intelligent, and the efficiency of work of urban management is improved.
Description
Technical field
The present invention relates to city management technical fields, more particularly to the illegal incidents monitoring method based on video, equipment and
Readable storage medium storing program for executing.
Background technique
Existing work of urban management, the mode for relying primarily on law enfrocement official's tour carry out.Since urban size is big, illegal
The factors such as sudden of event, have aggravated the working strength of law enfrocement official, and are difficult to find illegal incidents in first time, so that
City management is ineffective.
Summary of the invention
The main purpose of the present invention is to provide a kind of illegal incidents monitoring method, equipment and readable storage based on video
Medium, it is intended to solve the ineffective technical problem of city management in the prior art.
To achieve the above object, the present invention provides a kind of illegal incidents monitoring method based on video, described to be based on video
Illegal incidents monitoring method the following steps are included:
The normal picture for obtaining the illegal picture shot under illegal scene and being shot under normal scene；
By the illegal picture and normal picture, based on the mode of repetitive exercise to preset convolutional neural networks model
It is trained, obtains target convolution neural network model；
Picture to be identified is inputted into the target convolution neural network model, obtains the identification knot of the picture to be identified
Fruit；
If the recognition result is illegal, outputting alarm prompt.
Optionally, described by the illegal picture and normal picture, based on the mode of repetitive exercise to preset convolution
The step of neural network model is trained, and obtains target convolution neural network model include:
Illegal picture and normal picture are inputted into preset convolutional neural networks model, and pass through preset convolutional neural networks
The feature extraction network of model extracts the characteristic information of illegal picture and normal picture；
The characteristic information of the illegal picture and normal picture is inputted to the prediction interval of preset convolutional neural networks model,
Obtain illegal picture and the respective prediction result of normal picture；
Whether the prediction result for detecting the illegal picture is illegal, if so, it is correct labeled as prediction, otherwise it is labeled as
Prediction error；
Whether the prediction result for detecting the normal picture is normal, if so, correctly labeled as prediction, being otherwise labeled as
Prediction error；
The ratio for predicting that correct number is shared in always prediction number is calculated, and judges whether ratio is greater than or waits
In preset threshold；
If the ratio is greater than or equal to preset threshold, using current preset convolutional neural networks model as target volume
Product neural network model；
If the ratio is less than preset threshold, parameter adjustment is carried out to the preset convolutional neural networks model, is obtained
New convolutional neural networks model；
Using the new convolutional neural networks model as preset convolutional neural networks model, and execute described by illegal figure
Piece and normal picture input preset convolutional neural networks model, and pass through the feature extraction net of preset convolutional neural networks model
Network extracts the step of characteristic information of illegal picture and normal picture.
Optionally, if the recognition result be it is illegal, the step of outputting alarm prompt includes:
If the recognition result be it is illegal, obtain the geographical location of the corresponding filming apparatus of the picture to be identified；
Outputting alarm prompt is to the corresponding law-executor's terminal in the geographical location.
In addition, to achieve the above object, the present invention also provides a kind of illegal incidents monitoring device based on video, the base
Include: memory, processor in the illegal incidents monitoring device of video and is stored on the memory and can be in the processing
The illegal incidents monitoring programme based on video run on device, the illegal incidents monitoring programme based on video are held by processor
The step of illegal incidents monitoring method based on video as described above is realized when row.
In addition, to achieve the above object, the present invention also provides a kind of readable storage medium storing program for executing, being deposited on the readable storage medium storing program for executing
The illegal incidents monitoring programme based on video is contained, it is real when the illegal incidents monitoring programme based on video is executed by processor
Now as described above illegal incidents monitoring method based on video the step of.
In the present invention, the normal picture that obtains the illegal picture shot under illegal scene and shot under normal scene；It is logical
The illegal picture and normal picture are crossed, preset convolutional neural networks model is trained based on the mode of repetitive exercise,
Obtain target convolution neural network model；Picture to be identified is inputted into the target convolution neural network model, obtain it is described to
Identify the recognition result of picture；If the recognition result is illegal, outputting alarm prompt.Through the invention, using convolution mind
Whether the picture taken through network model judgement is illegal picture, when being judged as illegal picture, is considered as and monitors illegal thing
Part, just outputting alarm prompt, so that related law enfrocement official handles illegal incidents, so that work of urban management more intelligence
Can, and improve the efficiency of work of urban management.
Detailed description of the invention
Fig. 1 is the illegal incidents monitoring device knot based on video for the hardware running environment that the embodiment of the present invention is related to
Structure schematic diagram；
Fig. 2 is that the present invention is based on the flow diagrams of the illegal incidents monitoring method first embodiment of video.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in FIG. 1, FIG. 1 is the illegal incidents based on video for the hardware running environment that the embodiment of the present invention is related to
Monitoring device structural schematic diagram.
As shown in Figure 1, being somebody's turn to do the illegal incidents monitoring device based on video may include: processor 1001, such as CPU, net
Network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing these
Connection communication between component.User interface 1003 may include display screen (Display), input unit such as keyboard
(Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 is optional
May include standard wireline interface and wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory,
It is also possible to stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally may be used also
To be independently of the storage device of aforementioned processor 1001.
It will be understood by those skilled in the art that the illegal incidents monitoring device structure shown in Fig. 1 based on video is not
The restriction to the illegal incidents monitoring device based on video is constituted, may include than illustrating more or fewer components or group
Close certain components or different component layouts.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and the illegal incidents monitoring programme based on video.
In illegal incidents monitoring device based on video shown in Fig. 1, network interface 1004 is mainly used for connection backstage
Server carries out data communication with background server；User interface 1003 is mainly used for connecting client (user terminal), with client
End carries out data communication；And processor 1001 can be used for calling the illegal incidents prison based on video stored in memory 1005
Program is controlled, and executes following operation:
The normal picture for obtaining the illegal picture shot under illegal scene and being shot under normal scene；
By the illegal picture and normal picture, based on the mode of repetitive exercise to preset convolutional neural networks model
It is trained, obtains target convolution neural network model；
Picture to be identified is inputted into the target convolution neural network model, obtains the identification knot of the picture to be identified
Fruit；
If the recognition result is illegal, outputting alarm prompt.
Further, processor 1001 can call the illegal incidents monitoring journey based on video stored in memory 1005
Sequence also executes following operation:
Illegal picture and normal picture are inputted into preset convolutional neural networks model, and pass through preset convolutional neural networks
The feature extraction network of model extracts the characteristic information of illegal picture and normal picture；
The characteristic information of the illegal picture and normal picture is inputted to the prediction interval of preset convolutional neural networks model,
Obtain illegal picture and the respective prediction result of normal picture；
Whether the prediction result for detecting the illegal picture is illegal, if so, it is correct labeled as prediction, otherwise it is labeled as
Prediction error；
Whether the prediction result for detecting the normal picture is normal, if so, correctly labeled as prediction, being otherwise labeled as
Prediction error；
The ratio for predicting that correct number is shared in always prediction number is calculated, and judges whether ratio is greater than or waits
In preset threshold；
If the ratio is greater than or equal to preset threshold, using current preset convolutional neural networks model as target volume
Product neural network model；
If the ratio is less than preset threshold, parameter adjustment is carried out to the preset convolutional neural networks model, is obtained
New convolutional neural networks model；
Using the new convolutional neural networks model as preset convolutional neural networks model, and execute described by illegal figure
Piece and normal picture input preset convolutional neural networks model, and pass through the feature extraction net of preset convolutional neural networks model
Network extracts the step of characteristic information of illegal picture and normal picture.
Further, processor 1001 can call the illegal incidents monitoring journey based on video stored in memory 1005
Sequence also executes following operation:
If the recognition result be it is illegal, obtain the geographical location of the corresponding filming apparatus of the picture to be identified；
Outputting alarm prompt is to the corresponding law-executor's terminal in the geographical location.
It is that the present invention is based on the flow diagrams of the illegal incidents monitoring method first embodiment of video referring to Fig. 2, Fig. 2.
In one embodiment, the illegal incidents monitoring method based on video includes:
Step S10, the normal picture for obtaining the illegal picture shot under illegal scene and being shot under normal scene；
In the present embodiment, the high target convolution neural network model of prediction accuracy, it is most to need to obtain quantity in order to obtain
Picture more than possible is for training.Picture includes the illegal picture shot under illegal scene and shoots under normal scene normal
Picture.In the present embodiment, the illegal picture number of acquisition can be identical or not identical with normal picture quantity, but the two quantity is poor
It cannot be excessive.For example, setting maximum quantity difference is that 1 the percent of picture sum are disobeyed if the picture sum obtained is 10000
The difference of method picture number and normal picture quantity is no more than 100.
Step S20, by the illegal picture and normal picture, based on the mode of repetitive exercise to preset convolutional Neural
Network model is trained, and obtains target convolution neural network model；
In the present embodiment, step S20 includes: that illegal picture and normal picture are inputted preset convolutional neural networks mould
Type, and believed by the feature that the feature extraction network of preset convolutional neural networks model extracts illegal picture and normal picture
Breath；The prediction interval that the characteristic information of the illegal picture and normal picture is inputted to preset convolutional neural networks model, obtains
Illegal picture and the respective prediction result of normal picture；Whether the prediction result for detecting the illegal picture is illegal, if so,
It is then correct labeled as prediction, otherwise it is labeled as prediction error；Whether the prediction result for detecting the normal picture is normal, if
Be, then it is correct labeled as prediction, otherwise it is labeled as prediction error；It calculates shared by predicting correct number in always prediction number
Ratio, and judge whether ratio is greater than or equal to preset threshold；If the ratio is greater than or equal to preset threshold, to work as
Preceding preset convolutional neural networks model is as target convolution neural network model；If the ratio is less than preset threshold, right
The preset convolutional neural networks model carries out parameter adjustment, obtains new convolutional neural networks model；By the new convolution
Neural network model executes described that illegal picture and normal picture input is preset as preset convolutional neural networks model
Convolutional neural networks model, and by the illegal picture of the feature extraction network of preset convolutional neural networks model extraction and normally
The step of characteristic information of picture.In the present embodiment, neural network is substantially a calculation process, inputs and believes in front end receiver
After number, process complicated operation from level to level exports result in least significant end.Then calculated result is compared with correct result, is obtained
To error, further according to error by the relevant parameter of corresponding advance in caculating means network internal, so that network receives next time again
When same data, the final error calculated between the obtained result of output and correct result can be smaller and smaller.
Picture to be identified is inputted the target convolution neural network model, obtains the picture to be identified by step S30
Recognition result；
In the present embodiment, by step S20, preset convolutional neural networks model is trained to obtain target convolutional Neural
Picture to be identified is inputted target convolution neural network model, the recognition result of picture to be identified can be obtained, known by network model
Other result includes two kinds: illegal or normal.
Step S40, if the recognition result is illegal, outputting alarm prompt.
In the present embodiment, if recognition result be it is illegal, illustrate that illegal incidents have occurred, then outputting alarm prompt, for
Related law enfrocement official handles illegal incidents.
In the present embodiment, the normal picture that obtains the illegal picture shot under illegal scene and shot under normal scene；
By the illegal picture and normal picture, preset convolutional neural networks model is instructed based on the mode of repetitive exercise
Practice, obtains target convolution neural network model；Picture to be identified is inputted into the target convolution neural network model, is obtained described
The recognition result of picture to be identified；If the recognition result is illegal, outputting alarm prompt.Through this embodiment, using volume
Whether the picture that takes of product neural network model judgement is illegal picture, when being judged as illegal picture, be considered as monitor it is separated
Method event, just outputting alarm prompt, so that related law enfrocement official handles illegal incidents, so that work of urban management is more
Intelligence, and improve the efficiency of work of urban management.
Further, the present invention is based in one embodiment of illegal incidents monitoring method of video, step S40 includes:
If the recognition result be it is illegal, obtain the geographical location of the corresponding filming apparatus of the picture to be identified；
Outputting alarm prompt is to the corresponding law-executor's terminal in the geographical location.
In the present embodiment, if recognition result be it is illegal, that is, monitor illegal incidents, then further obtain picture pair to be identified
The geographical location for the filming apparatus answered.Determine which photographic device shooting the picture to be identified is, this point can pass through
The data source of picture to be identified determines, to further determine that the geographical location of the filming apparatus, then sends out alarm prompt
Law-executor's terminal corresponding to geographical location is sent, so that law enfrocement official handles rapidly the illegal incidents.
In addition, the embodiment of the present invention also proposes a kind of readable storage medium storing program for executing, it is stored with and is based on the readable storage medium storing program for executing
The illegal incidents monitoring programme of video, the illegal incidents monitoring programme based on video realize base as above when being executed by processor
In the illegal incidents monitoring method of video each embodiment the step of.
Readable storage medium storing program for executing, that is, computer readable storage medium of the present invention, the specific embodiment of readable storage medium storing program for executing of the present invention
Essentially identical with each embodiment of the above-mentioned illegal incidents monitoring method based on video, this will not be repeated here.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device executes the present invention respectively
Method described in a embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content, is directly or indirectly used.
Claims (7)
1. a kind of illegal incidents monitoring method based on video, which is characterized in that the illegal incidents monitoring side based on video
Method the following steps are included:
The normal picture for obtaining the illegal picture shot under illegal scene and being shot under normal scene；
By the illegal picture and normal picture, preset convolutional neural networks model is carried out based on the mode of repetitive exercise
Training, obtains target convolution neural network model；
Picture to be identified is inputted into the target convolution neural network model, obtains the recognition result of the picture to be identified；
If the recognition result is illegal, outputting alarm prompt.
2. the illegal incidents monitoring method based on video as described in claim 1, which is characterized in that described by described illegal
Picture and normal picture are trained preset convolutional neural networks model based on the mode of repetitive exercise, obtain target volume
Product neural network model the step of include:
Illegal picture and normal picture are inputted into preset convolutional neural networks model, and pass through preset convolutional neural networks model
Feature extraction network extract the characteristic information of illegal picture and normal picture；
The prediction interval that the characteristic information of the illegal picture and normal picture is inputted to preset convolutional neural networks model, obtains
Illegal picture and the respective prediction result of normal picture；
Whether the prediction result for detecting the illegal picture is illegal, if so, it is correct labeled as prediction, otherwise labeled as prediction
Mistake；
Whether the prediction result for detecting the normal picture is normal, if so, correctly labeled as prediction, otherwise labeled as prediction
Mistake；
The ratio for predicting that correct number is shared in always prediction number is calculated, and it is pre- to judge whether ratio is greater than or equal to
If threshold value；
If the ratio is greater than or equal to preset threshold, using current preset convolutional neural networks model as target convolution mind
Through network model；
If the ratio is less than preset threshold, parameter adjustment is carried out to the preset convolutional neural networks model, is obtained new
Convolutional neural networks model；
Using the new convolutional neural networks model as preset convolutional neural networks model, and execute it is described by illegal picture with
And normal picture inputs preset convolutional neural networks model, and is mentioned by the feature extraction network of preset convolutional neural networks model
The step of taking the characteristic information of illegal picture and normal picture.
3. the illegal incidents monitoring method based on video as described in claim 1, which is characterized in that if the identification is tied
Fruit be it is illegal, then the step of outputting alarm prompt includes:
If the recognition result be it is illegal, obtain the geographical location of the corresponding filming apparatus of the picture to be identified；
Outputting alarm prompt is to the corresponding law-executor's terminal in the geographical location.
4. a kind of illegal incidents monitoring device based on video, which is characterized in that the illegal incidents monitoring based on video is set
Standby includes: memory, processor and the disobeying based on video that is stored on the memory and can run on the processor
Religious services or rituals part monitoring programme, the illegal incidents monitoring programme based on video realize following steps when being executed by the processor:
The normal picture for obtaining the illegal picture shot under illegal scene and being shot under normal scene；
By the illegal picture and normal picture, preset convolutional neural networks model is carried out based on the mode of repetitive exercise
Training, obtains target convolution neural network model；
Picture to be identified is inputted into the target convolution neural network model, obtains the recognition result of the picture to be identified；
If the recognition result is illegal, outputting alarm prompt.
5. the illegal incidents monitoring device based on video as claimed in claim 4, which is characterized in that the disobeying based on video
Religious services or rituals part monitoring programme also realizes following steps when being executed by the processor:
Illegal picture and normal picture are inputted into preset convolutional neural networks model, and pass through preset convolutional neural networks model
Feature extraction network extract the characteristic information of illegal picture and normal picture；
The prediction interval that the characteristic information of the illegal picture and normal picture is inputted to preset convolutional neural networks model, obtains
Illegal picture and the respective prediction result of normal picture；
Whether the prediction result for detecting the illegal picture is illegal, if so, it is correct labeled as prediction, otherwise labeled as prediction
Mistake；
Whether the prediction result for detecting the normal picture is normal, if so, correctly labeled as prediction, otherwise labeled as prediction
Mistake；
The ratio for predicting that correct number is shared in always prediction number is calculated, and it is pre- to judge whether ratio is greater than or equal to
If threshold value；
If the ratio is greater than or equal to preset threshold, using current preset convolutional neural networks model as target convolution mind
Through network model；
If the ratio is less than preset threshold, parameter adjustment is carried out to the preset convolutional neural networks model, is obtained new
Convolutional neural networks model；
Using the new convolutional neural networks model as preset convolutional neural networks model, and execute it is described by illegal picture with
And normal picture inputs preset convolutional neural networks model, and is mentioned by the feature extraction network of preset convolutional neural networks model
The step of taking the characteristic information of illegal picture and normal picture.
6. the illegal incidents monitoring device based on video as claimed in claim 4, which is characterized in that the disobeying based on video
Religious services or rituals part monitoring programme also realizes following steps when being executed by the processor:
If the recognition result be it is illegal, obtain the geographical location of the corresponding filming apparatus of the picture to be identified；
Outputting alarm prompt is to the corresponding law-executor's terminal in the geographical location.
7. a kind of readable storage medium storing program for executing, which is characterized in that be stored with the illegal incidents based on video on the readable storage medium storing program for executing
Monitoring programme is realized when the illegal incidents monitoring programme based on video is executed by processor as any in claims 1 to 3
The step of illegal incidents monitoring method based on video described in item.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910464895.7A CN110245696A (en) | 2019-05-30 | 2019-05-30 | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910464895.7A CN110245696A (en) | 2019-05-30 | 2019-05-30 | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110245696A true CN110245696A (en) | 2019-09-17 |
Family
ID=67885478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910464895.7A Pending CN110245696A (en) | 2019-05-30 | 2019-05-30 | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245696A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091098A (en) * | 2019-12-20 | 2020-05-01 | 浙江大华技术股份有限公司 | Training method and detection method of detection model and related device |
| CN111126252A (en) * | 2019-12-20 | 2020-05-08 | 浙江大华技术股份有限公司 | Stall behavior detection method and related device |
| CN112712002A (en) * | 2020-12-24 | 2021-04-27 | 深圳力维智联技术有限公司 | CGAN-based environment monitoring method, device, system and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160074786A (en) * | 2014-12-18 | 2016-06-29 | 주식회사 다이나맥스 | Real time control system for illegal parking using led electric bulletin board and voice notice and method thereof |
| CN106407903A (en) * | 2016-08-31 | 2017-02-15 | 四川瞳知科技有限公司 | Multiple dimensioned convolution neural network-based real time human body abnormal behavior identification method |
-
2019
- 2019-05-30 CN CN201910464895.7A patent/CN110245696A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160074786A (en) * | 2014-12-18 | 2016-06-29 | 주식회사 다이나맥스 | Real time control system for illegal parking using led electric bulletin board and voice notice and method thereof |
| CN106407903A (en) * | 2016-08-31 | 2017-02-15 | 四川瞳知科技有限公司 | Multiple dimensioned convolution neural network-based real time human body abnormal behavior identification method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091098A (en) * | 2019-12-20 | 2020-05-01 | 浙江大华技术股份有限公司 | Training method and detection method of detection model and related device |
| CN111126252A (en) * | 2019-12-20 | 2020-05-08 | 浙江大华技术股份有限公司 | Stall behavior detection method and related device |
| CN111091098B (en) * | 2019-12-20 | 2023-08-15 | 浙江大华技术股份有限公司 | Training method of detection model, detection method and related device |
| CN111126252B (en) * | 2019-12-20 | 2023-08-18 | 浙江大华技术股份有限公司 | Swing behavior detection method and related device |
| CN112712002A (en) * | 2020-12-24 | 2021-04-27 | 深圳力维智联技术有限公司 | CGAN-based environment monitoring method, device, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11176418B2 (en) | Model test methods and apparatuses | |
| CN109756746A (en) | Video reviewing method, device, server and storage medium | |
| CN110245696A (en) | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video | |
| CN110674790B (en) | Abnormal scene processing method and system in video monitoring | |
| CN110427265A (en) | Method, apparatus, computer equipment and the storage medium of recognition of face | |
| CN109472193A (en) | Method for detecting human face and device | |
| CN110717058B (en) | Information recommendation method and device and storage medium | |
| CN107153584A (en) | Method for detecting abnormality and device | |
| CN112163468A (en) | Image processing method and device based on multiple threads | |
| CN110188717A (en) | Image acquiring method and device | |
| CN105791674A (en) | Electronic device and focusing method | |
| CN110147469A (en) | A kind of data processing method, equipment and storage medium | |
| CN109960969A (en) | The method, apparatus and system that mobile route generates | |
| CN110852224B (en) | Expression recognition method and related device | |
| CN112306829A (en) | Method and device for determining performance information, storage medium and terminal | |
| CN113420871B (en) | Image quality evaluation method, image quality evaluation device, storage medium, and electronic device | |
| CN111586432A (en) | Method and device for determining air-broadcast live broadcast room, server and storage medium | |
| CN109376981B (en) | Data processing mode determining method and device, server and data processing method | |
| CN108446688B (en) | Face image gender judgment method and device, computer equipment and storage medium | |
| CN110427998A (en) | Model training, object detection method and device, electronic equipment, storage medium | |
| CN110536087A (en) | Electronic equipment and its motion profile picture synthesis method, device and embedded equipment | |
| CN109889776A (en) | Method for processing video frequency, device, computer installation and computer readable storage medium | |
| CN113627334A (en) | Object behavior identification method and device | |
| CN105472405B (en) | Remind generation method and device | |
| CN113194297A (en) | Intelligent monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |