CN110378300A - A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus - Google Patents
A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus Download PDFInfo
- Publication number
- CN110378300A CN110378300A CN201910671707.8A CN201910671707A CN110378300A CN 110378300 A CN110378300 A CN 110378300A CN 201910671707 A CN201910671707 A CN 201910671707A CN 110378300 A CN110378300 A CN 110378300A
- Authority
- CN
- China
- Prior art keywords
- material elevator
- people
- target video
- video
- hybrid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 40
- 238000013136 deep learning model Methods 0.000 claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010276 construction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/3415—Control system configuration and the data transmission or communication within the control system
- B66B1/3423—Control system configuration, i.e. lay-out
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0012—Devices monitoring the users of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/02—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
A kind of hybrid recognition methods of material elevator people goods provided herein is applied to GPU calculation server, comprising: obtains target video；Wherein, target video is the video in preset alarm region where video capture device acquires material elevator in real time；Visual identity is carried out to target video using preset deep learning model to judge in material elevator with the presence or absence of people；If there are people in material elevator, warning operation and dump operation are executed.This method carries out visual identity to target video to judge accurately carry out the hybrid identification of material elevator people's goods, and then avoid the occurrence of safety accident with the presence or absence of people in material elevator using preset deep learning model.The application also provides a kind of hybrid identifying system of material elevator people goods, GPU calculation server and computer readable storage medium, all has above-mentioned beneficial effect.
Description
Technical field
This application involves the hybrid identification field of material elevator people's goods, in particular to a kind of hybrid knowledge of material elevator people goods
Other method, system, GPU calculation server and computer readable storage medium.
Background technique
Before the monitoring and safety accident generation of the personnel's unsafe acts occurred in infrastructure project process of construction
Early warning and precautionary measures are particularly important in infrastructure project process of construction.
Infrastructure project civil construction process often uses material elevator, occurs the hybrid situation of people's goods often, easily occurs
Safety accident.Currently, identification mainly hybrid using infrared emission technology progress material elevator people goods, but the standard identified
Exactness is lower.
Therefore, the hybrid identification of material elevator people's goods how is accurately carried out, and then avoiding the occurrence of safety accident is this
The technical issues of field technical staff's urgent need to resolve.
Summary of the invention
The purpose of the application be to provide a kind of hybrid recognition methods of material elevator people goods, system, GPU calculation server and
Computer readable storage medium can accurately carry out the hybrid identification of material elevator people's goods, and then avoid the occurrence of safe thing
Therefore.
In order to solve the above technical problems, the application provides a kind of hybrid recognition methods of material elevator people goods, it is applied to GPU
Calculation server, comprising:
Obtain target video；Wherein, the target video is that video capture device acquires material elevator place in advance in real time
If the video of alarm region；
Visual identity is carried out to judge the material elevator to the target video using preset deep learning model
In whether there is people；
If there are the people in the material elevator, warning operation and dump operation are executed.
Preferably, the acquisition target video, comprising:
Receive the target video of camera shooting overhead pass.
Preferably, the hybrid recognition methods of material elevator people's goods further include:
Receive the alarm command for preliminary recognition result that the camera is sent；Wherein, the preliminary recognition result
For the camera based on edge calculations to the recognition result of the target video, the alarm command is according to the preliminary knowledge
The instruction generated in material elevator described in other result judgement there are the people；
Alarm is triggered according to the alarm command to alarm, and executes the dump operation.
Preferably, after the execution warning operation and dump operate, further includes:
Screenshot and/or video clip are obtained from the target video, and the screenshot and/or the video clip are sent out
It is sent to operation system.
Preferably, the hybrid recognition methods of material elevator people's goods further include:
Filter out target screenshot or target video segment respectively from the screenshot or the video clip；
Model training is carried out using the target screenshot or the target video segment, and using the model after training as institute
State deep learning model.
Preferably, further includes:
According to the demand of input, the preset alarm region is reset.
Preferably, the hybrid recognition methods of material elevator people's goods includes:
The GPU calculation server, the camera and the alarm are in same local area network.
The application also provides a kind of hybrid identifying system of material elevator people goods, is applied to GPU calculation server, comprising:
Target video obtains module, for obtaining target video；Wherein, the target video is that video capture device is real-time
The video in preset alarm region where acquiring material elevator；
Visual identity module, for carrying out visual identity to the target video using preset deep learning model to sentence
Break in the material elevator with the presence or absence of people；
Operation executing module, if for, there are the people, executing warning operation in the material elevator and power supply being cut
Disconnected operation.
The application also provides a kind of GPU calculation server, comprising:
Memory and processor；Wherein, the memory is for storing computer program, and the processor is for executing institute
The step of material elevator people's goods described above hybrid recognition methods is realized when stating computer program.
The application also provides a kind of computer readable storage medium, and the computer-readable recording medium storage has computer
Program, the computer program realize the step of the hybrid recognition methods of material elevator people's goods described above when being executed by processor
Suddenly.
A kind of hybrid recognition methods of material elevator people goods provided herein is applied to GPU calculation server, packet
It includes: obtaining target video；Wherein, the target video is that video capture device acquires preset alarm where material elevator in real time
The video in region；Visual identity is carried out to judge the material lifting to the target video using preset deep learning model
It whether there is people in machine；If there are the people in the material elevator, warning operation and dump operation are executed.
This method carries out visual identity to the target video using preset deep learning model to judge the material
It whether there is people in elevator, can accurately carry out the hybrid identification of material elevator people's goods, and then avoid the occurrence of safe thing
Therefore.The application also provides a kind of hybrid identifying system of material elevator people goods, GPU calculation server and computer-readable storage medium
Matter all has above-mentioned beneficial effect, and details are not described herein.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of application for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of the hybrid recognition methods of material elevator people goods provided by the embodiment of the present application；
Fig. 2 is a kind of optimum embodiment flow diagram provided by the embodiment of the present application；
Fig. 3 is a kind of structural block diagram of the hybrid identifying system of material elevator people goods provided by the embodiment of the present application.
Specific embodiment
The core of the application is to provide a kind of hybrid recognition methods of material elevator people goods, can accurately carry out material and mention
The hybrid identification of machine people goods is risen, and then avoids the occurrence of safety accident.Another core of the application is to provide a kind of material elevator
The hybrid identifying system of people's goods, GPU calculation server and computer readable storage medium.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Before the monitoring and safety accident generation of the personnel's unsafe acts occurred in infrastructure project process of construction
Early warning and precautionary measures are particularly important in infrastructure project process of construction.
Infrastructure project civil construction process often uses material elevator, occurs the hybrid situation of people's goods often, easily occurs
Safety accident.Currently, identification mainly hybrid using infrared emission technology progress material elevator people goods, but the standard identified
Exactness is lower.A kind of hybrid recognition methods of material elevator people goods provided by the present application, can accurately carry out material elevator
The hybrid identification of people's goods, and then avoid the occurrence of safety accident.Specifically referring to FIG. 1, Fig. 1 is one provided by the embodiment of the present application
The flow chart of the kind hybrid recognition methods of material elevator people goods, the hybrid recognition methods of material elevator people's goods specifically include:
S101, target video is obtained；Wherein, target video is that video capture device acquires material elevator place in advance in real time
If the video of alarm region；
The executing subject of the present embodiment is GPU calculation server, and GPU calculation server obtains target video, target view
Frequency is the video in preset alarm region where video capture device acquires material elevator in real time, and the duration of the target video is herein
It is not especially limited, corresponding setting should be made according to the actual situation by those skilled in the art.Video acquisition is set herein
Standby to be not especially limited, in some embodiments, which is specially camera.Herein for preset alarm region
Also it is not especially limited, which is the danger zone where preset material elevator.
S102, visual identity is carried out to judge to be in material elevator to target video using preset deep learning model
It is no that there are people；
If there are people in S103, material elevator, warning operation and dump operation are executed.
Visual identity is carried out to judge material lifting to target video using preset deep learning model in the present embodiment
It whether there is people in machine；Wherein, deep learning model is obtained by model training.Since the present embodiment is for target video
In content be not construed as limiting, therefore recognition result is also not especially limited, as long as meeting the actual needs.For example, identification
As a result can be for there are people in material elevator, it can also be for there is no people in material elevator.If existing in material elevator
People then executes warning operation and dump operation.
This method carries out visual identity to the target video using preset deep learning model to judge the material
It whether there is people in elevator, can accurately carry out the hybrid identification of material elevator people's goods, and then avoid the occurrence of safe thing
Therefore.
Based on the above embodiment, above-mentioned acquisition target video in the present embodiment, comprising: receive the target view of camera shooting overhead pass
Frequently.Embodiment defines the video capture device of target video be camera, and the camera shooting overhead pass target video to GPU count
Calculate server.The camera usually acquires video in real time, and frequency acquisition is not especially limited, should by those skilled in the art according to
Actual conditions make corresponding setting.
Based on the above embodiment, in the present embodiment further include: receive the report for preliminary recognition result that camera is sent
Alert instruction；Wherein, preliminary recognition result be camera based on edge calculations to the recognition result of target video, alarm command be according to
The instruction generated in material elevator there are people is determined according to preliminary recognition result；Alarm is triggered according to alarm command to be reported
It is alert, and execute dump operation.Specifically, camera acquires video in real time, and knowledge preliminary in real time is carried out based on edge calculations
Not, it if material elevator someone, sends alarm command and gives GPU server, reported by GPU server triggers alarm
It is alert, and the power supply of intelligent power cutting material elevator is controlled, it prevents from being accidentally.Camera carries out preliminary analysis to video
Later, video can also return to GPU calculation server in real time, be will do it herein than more complete visual identity, if identification
To material elevator someone, alarm can be equally triggered, and controls the power supply of intelligent power cutting material elevator, is prevented by accident
Starting.
Based on the above embodiment, after above-mentioned execution warning operation and dump operate in the present embodiment, further includes: from
Screenshot and/or video clip are obtained in target video, and send operation system for screenshot and/or video clip.Herein for
Screenshot, video clip quantity be not especially limited, the duration of each video clip is also not especially limited, should be by this field
Technical staff makes corresponding setting according to the actual situation.Specifically, it if personnel overstay in material elevator, removes
It lasting alarm and cuts off the power outer, while operation system can be sent by network by corresponding screenshot or segment video
In, perhaps business personnel can check in small routine or examine etc. to personnel administrative staff.It is understood that
It is that the present embodiment can identify personnel by screenshot, video clip, can identifies specific identity information.
Based on the above embodiment, danger zone is crossed the border recognition methods in the present embodiment further include: from screenshot or video clip
It is middle to filter out target screenshot or target video segment respectively；Model training is carried out using target screenshot or target video segment, and
Using the model after training as deep learning model.Herein the screening criteria for target screenshot or target video segment and respectively
The quantity filtered out is not especially limited, and corresponding setting should be made according to the actual situation by those skilled in the art.This reality
It applies example and carries out model training using target screenshot or target video segment, and using the model after training as deep learning model,
Namely the deep learning model being deployed on GPU calculation server is updated.Specifically, problematic in operation system
Screenshot or small video, can be labeled offline, and carry out the training of deep learning model, trained model can be with
It updates in GPU calculation server, identification subsequent in this way can enable new identification model.
Based on the above embodiment, danger zone is crossed the border recognition methods in the present embodiment further include: according to the demand of input, weight
New setting preset alarm region.It is understood that the present embodiment can be based on demand, setting preset alarm region is updated.?
This is not especially limited the input mode of demand, should be made according to the actual situation by those skilled in the art and be set accordingly
It is fixed.Specifically, alarm region can be arranged in management backstage in administrator, and operation system can be sent to GPU by network for being arranged
In the edge calculations module of calculation server and camera.
Based on the above embodiment, in the present embodiment danger zone cross the border recognition methods include: GPU calculation server, camera shooting
Head and alarm are in same local area network.Specifically, GPU calculation server, camera, intelligent power and alarm all exist
In the same local area network, network delay is reduced to greatest extent.In addition, passing through public network between GPU calculation server and operation system
It is linked, using coded communication, avoids information leakage.
It is illustrated below with an optimum embodiment, it is specific referring to FIG. 2, Fig. 2 is provided by the embodiment of the present application
A kind of optimum embodiment flow diagram, as shown in Fig. 2, left side maximum dotted line frame indicates that all the components form a material in frame
Elevator people's goods identifying system, have in the maximum dotted line frame a lesser dotted line frame indicate the alarm in the dotted line frame,
Intelligent power, camera and GPU calculation server are in same local area network.Video or instruction are sent to GPU meter by camera
Server is calculated, GPU calculation server can alarm according to instruction triggers alarm, while control intelligent power cutting material
The power supply of elevator.Other than lasting alarm and cutting off the power, GPU calculation server simultaneously can regard corresponding picture or segment
Frequency or instruction are sent in operation system by network, and perhaps business personnel can check or right leader in small routine
Personnel examine etc..Alarm region can be arranged in management backstage in administrator or relevant people, and operation system can pass through setting
Network is sent in the edge calculations module of GPU calculation server and camera.Operation system is by problematic picture or view
Frequency exports, and can carry out offline sample mark, and carry out deep learning on offline GPU server and model training server
The training of model, trained model, which can update, to be deployed in GPU calculation server, and identification subsequent in this way can enable
New identification model.
Below to a kind of hybrid identifying system of material elevator people goods provided by the embodiments of the present application, GPU calculation server
And computer readable storage medium is introduced, the hybrid identifying system of material elevator people goods described below, GPU calculate service
Device and computer readable storage medium can correspond to each other reference with the above-described hybrid recognition methods of material elevator people goods.
Referring to FIG. 3, Fig. 3 is a kind of knot of the hybrid identifying system of material elevator people goods provided by the embodiment of the present application
Structure block diagram；The hybrid identifying system of material elevator people's goods includes:
Target video obtains module 301, for obtaining target video；Wherein, target video is that video capture device is real-time
The video in preset alarm region where acquiring material elevator；
Visual identity module 302, for carrying out visual identity to target video using preset deep learning model to sentence
It whether there is people in disconnected material elevator；
Operation executing module 303, if executing warning operation and dump behaviour for there are people in material elevator
Make.
Based on the above embodiment, target video described in the present embodiment obtains module 301, comprising:
Target video acquiring unit, for receiving the target video of camera shooting overhead pass.
Based on the above embodiment, in the present embodiment further include:
Alarm command receiving module, the alarm command for preliminary recognition result sent for receiving the camera；
Wherein, the preliminary recognition result be the camera based on edge calculations to the recognition result of the target video, the report
Alert instruction is to determine the instruction generated in the material elevator there are the people according to the preliminary recognition result；
Alarm triggering module alarms for triggering alarm according to the alarm command, and executes the power supply and cut
Disconnected operation.
Based on the above embodiment, the hybrid identifying system of material elevator people goods in the present embodiment, further includes:
Screenshot and/or video clip obtain module, for obtaining screenshot and/or video clip from the target video,
And operation system is sent by the screenshot and/or the video clip.
Based on the above embodiment, in the present embodiment further include:
Screening module, for filtering out target screenshot or target video piece respectively from the screenshot or the video clip
Section；
Model training module, for carrying out model training using the target screenshot or the target video segment, and will
Model after training is as the deep learning model.
Based on the above embodiment, in the present embodiment further include:
Alarm region setup module resets the preset alarm region for the demand according to input.
The application also provides a kind of GPU calculation server, comprising:
Memory and processor；Wherein, memory is for storing computer program, and processor is for executing computer program
The step of material elevator people's goods of the above-mentioned any embodiment of Shi Shixian hybrid recognition methods.
The application also provides a kind of computer readable storage medium, and computer-readable recording medium storage has computer journey
Sequence realizes the step of the hybrid recognition methods of material elevator people's goods of above-mentioned any embodiment when computer program is executed by processor
Suddenly.
The computer readable storage medium may include: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For embodiment provide system and
Speech, since it is corresponding with the method that embodiment provides, so being described relatively simple, related place is referring to method part illustration
?.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to the hybrid recognition methods of a kind of material elevator people goods provided herein, system, GPU calculation server
And computer readable storage medium is described in detail.Used herein principle and embodiment party of the specific case to the application
Formula is expounded, the description of the example is only used to help understand the method for the present application and its core ideas.It should refer to
It out, for those skilled in the art, can also be to the application under the premise of not departing from the application principle
Some improvement and modification can also be carried out, these improvement and modification are also fallen into the protection scope of the claim of this application.
Claims (10)
1. a kind of hybrid recognition methods of material elevator people goods, which is characterized in that be applied to GPU calculation server, comprising:
Obtain target video；Wherein, the target video is that video capture device acquires default report where material elevator in real time
The video in police region domain；
Visual identity is carried out to judge to be in the material elevator to the target video using preset deep learning model
It is no that there are people；
If there are the people in the material elevator, warning operation and dump operation are executed.
2. the hybrid recognition methods of material elevator people goods according to claim 1, which is characterized in that the acquisition target view
Frequently, comprising:
Receive the target video of camera shooting overhead pass.
3. the hybrid recognition methods of material elevator people goods according to claim 2, which is characterized in that further include:
Receive the alarm command for preliminary recognition result that the camera is sent；Wherein, the preliminary recognition result is institute
Recognition result of the camera based on edge calculations to the target video is stated, the alarm command is to tie according to the preliminary identification
Fruit determines the instruction generated in the material elevator there are the people；
Alarm is triggered according to the alarm command to alarm, and executes the dump operation.
4. the hybrid recognition methods of material elevator people goods according to claim 3, which is characterized in that the execution warning behaviour
Make after being operated with dump, further includes:
Screenshot and/or video clip are obtained from the target video, and send the screenshot and/or the video clip to
Operation system.
5. the hybrid recognition methods of material elevator people goods according to claim 4, which is characterized in that further include:
Filter out target screenshot or target video segment respectively from the screenshot or the video clip；
Model training is carried out using the target screenshot or the target video segment, and using the model after training as the depth
Spend learning model.
6. the hybrid recognition methods of material elevator people goods according to claim 5, which is characterized in that further include:
According to the demand of input, the preset alarm region is reset.
7. the hybrid recognition methods of material elevator people goods according to claim 6 characterized by comprising
The GPU calculation server, the camera and the alarm are in same local area network.
8. a kind of hybrid identifying system of material elevator people goods, which is characterized in that be applied to GPU calculation server, comprising:
Target video obtains module, for obtaining target video；Wherein, the target video is that video capture device acquires in real time
The video in preset alarm region where material elevator；
Visual identity module, for carrying out visual identity to the target video using preset deep learning model to judge
It states in material elevator with the presence or absence of people；
Operation executing module, if executing warning operation and dump behaviour for there are the people in the material elevator
Make.
9. a kind of GPU calculation server characterized by comprising
Memory and processor；Wherein, the memory is for storing computer program, the processor by execute it is described based on
The step of material elevator people goods as described in any one of claim 1 to 7 hybrid recognition methods is realized when calculation machine program.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program realize that material elevator people goods as described in any one of claim 1 to 7 is mixed when being executed by processor
The step of carrying recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671707.8A CN110378300A (en) | 2019-07-24 | 2019-07-24 | A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671707.8A CN110378300A (en) | 2019-07-24 | 2019-07-24 | A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110378300A true CN110378300A (en) | 2019-10-25 |
Family
ID=68255559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910671707.8A Pending CN110378300A (en) | 2019-07-24 | 2019-07-24 | A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378300A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112794174A (en) * | 2019-11-13 | 2021-05-14 | 深圳市赛特尔信息技术有限公司 | Real-time video judgment elevator door opening and closing abnormity scheme based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201332488Y (en) * | 2009-01-07 | 2009-10-21 | 上海国际港务(集团)股份有限公司龙吴分公司 | Mobile wireless monitoring system |
| CN106338944A (en) * | 2016-09-29 | 2017-01-18 | 山东华旗新能源科技有限公司 | Safe and intelligent control system for construction hoist |
| CN109052092A (en) * | 2018-09-12 | 2018-12-21 | 南通星云智能科技有限公司 | A kind of distribution elevator safety management system and management method |
| CN109410496A (en) * | 2018-10-25 | 2019-03-01 | 北京交通大学 | Attack early warning method, apparatus and electronic equipment |
| CN109712360A (en) * | 2018-12-24 | 2019-05-03 | 衢州市林森消防设备有限公司 | A kind of positioning and tracking type alarming device and method |
-
2019
- 2019-07-24 CN CN201910671707.8A patent/CN110378300A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201332488Y (en) * | 2009-01-07 | 2009-10-21 | 上海国际港务(集团)股份有限公司龙吴分公司 | Mobile wireless monitoring system |
| CN106338944A (en) * | 2016-09-29 | 2017-01-18 | 山东华旗新能源科技有限公司 | Safe and intelligent control system for construction hoist |
| CN109052092A (en) * | 2018-09-12 | 2018-12-21 | 南通星云智能科技有限公司 | A kind of distribution elevator safety management system and management method |
| CN109410496A (en) * | 2018-10-25 | 2019-03-01 | 北京交通大学 | Attack early warning method, apparatus and electronic equipment |
| CN109712360A (en) * | 2018-12-24 | 2019-05-03 | 衢州市林森消防设备有限公司 | A kind of positioning and tracking type alarming device and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112794174A (en) * | 2019-11-13 | 2021-05-14 | 深圳市赛特尔信息技术有限公司 | Real-time video judgment elevator door opening and closing abnormity scheme based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110379125A (en) | Cross the border recognition methods, system and relevant apparatus for a kind of danger zone | |
| CN103617699A (en) | Intelligent safety monitor system of electric power working site | |
| CN109558301A (en) | A kind of distributed system data monitoring method, device and relevant device | |
| CN108046073A (en) | A kind of elevator network monitoring system for things | |
| CN106408901A (en) | Fire early warning system and method based on building display screen | |
| CN110378300A (en) | A kind of hybrid recognition methods of material elevator people goods, system and relevant apparatus | |
| CN104317263B (en) | Concrete construction is vibrated method for controlling trajectory | |
| CN111612422B (en) | Emergency response method, device, storage medium and equipment | |
| CN108175995A (en) | Treadmill safety monitoring method, device and treadmill | |
| CN105988886B (en) | Fault handling method and device during a kind of O＆M | |
| CN105992188B (en) | A kind of application update method and device | |
| CN110806924B (en) | Network processing method and device based on CPU occupancy rate | |
| CN110188731A (en) | A kind of alarm method and relevant apparatus violating the regulations of operation field | |
| CN106744124A (en) | A kind of city lift management system and method based on Internet of Things | |
| CN110457101B (en) | Information processing method, electronic equipment and computer readable storage medium | |
| CN202218244U (en) | Information technology (IT) operation and maintenance system for business system monitoring | |
| CN109981338A (en) | Alarm method, device and the storage medium that code pulls | |
| CN109245937A (en) | A kind of alarm method and device of PIM platform | |
| CN109063856B (en) | Method and device for generating security fence | |
| CN104898535B (en) | Monitoring method, apparatus and system | |
| CN106744125A (en) | A kind of elevator faults warning system and method based on big data | |
| CN110675604A (en) | Intelligent early warning system and method for safety production | |
| CN106744106A (en) | A kind of city elevator management method and system based on robot | |
| CN112530148A (en) | Information pushing method and device and fire fighting system | |
| Lochmann | Engineering quality requirements using quality models |
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 |
Application publication date: 20191025 |
|
| RJ01 | Rejection of invention patent application after publication |