CN112311852A - Appearance defect detection method based on machine vision and deep learning - Google Patents
Appearance defect detection method based on machine vision and deep learning Download PDFInfo
- Publication number
- CN112311852A CN112311852A CN202011026650.5A CN202011026650A CN112311852A CN 112311852 A CN112311852 A CN 112311852A CN 202011026650 A CN202011026650 A CN 202011026650A CN 112311852 A CN112311852 A CN 112311852A
- Authority
- CN
- China
- Prior art keywords
- sensor
- information access
- access point
- output end
- detection method
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to an appearance defect detection method based on machine vision and deep learning, which comprises a network video recorder, a video management server, a network memory, a parking system, an entrance guard management integrated server, an alarm system workstation, a plurality of codecs and a field controller which are connected with a local area network, wherein the input end of each codec is respectively connected with a spherical camera and a monitor wall, the input end of the network video recorder is connected with a plurality of monitors, the alarm system workstation comprises a portable remote controller connected with a home security display, and the input end of the home security display is respectively connected with a smoke monitor, a wireless door magnetic control device, a concentration sensor connected with a gas valve and a wireless infrared device. Has the advantages that: the invention has high safety performance, can timely and effectively mobilize police force and fire-fighting equipment to a community, ensures normal rest of family life, realizes integration of data transmission and is convenient for parking and life management.
Description
Technical Field
The invention relates to the technical field of appearance defect monitoring systems, in particular to an appearance defect detection method based on machine vision and deep learning.
Background
The existing appearance defect monitoring system mainly carries out effective photographing and contact operation on external images and each construction unit, but the existing monitoring system is single in functionality, cannot carry out comprehensive and effective monitoring on the safety of construction, gives clear and real-time warning and transmits data to a monitoring center, and meanwhile, for places with large building construction, the data cannot be effectively processed in a centralized mode, and meanwhile, an independent area network cannot be formed.
Disclosure of Invention
The invention aims to provide a processing system which has strong control performance and can integrate regional information to obtain a complete processing system and an appearance defect detection method based on machine vision and deep learning and can ensure safe and stable construction operation, which is realized by the following scheme.
In order to achieve the above purpose, the invention adopts the technical scheme that: an appearance defect detection method based on machine vision and deep learning comprises indoor information access points positioned in the periphery of a fence, the input end of the indoor information access point is provided with an outdoor information access point matched with the indoor information access point, the outdoor information access point and the indoor information access point transmit data to the computer center in a wireless transmission mode, a tower crane monitoring terminal connected with the computer center is arranged between the indoor information access point and the outdoor information access point, wherein, the information access ends are all provided with an IP camera and a monitoring system, the IP camera is connected with a switch in a wireless network bridging way, one end of the output end of the switch is connected with a display in a network connection mode, the other end of the output end of the switch is connected with a wide area network through an optical fiber, the output end of the wide area network is connected with a headquarter monitoring center through a wireless video management platform;
the monitoring system comprises a dust sensor, a noise sensor, a temperature sensor, a humidity sensor, a wind speed sensor, a wind direction sensor, an air pressure sensor and a concentration sensor which are connected with a data acquisition unit, wherein the output end of the data acquisition unit is respectively connected with a voice player, an alarm and a data transmission system, and the output end of the data transmission system is respectively connected with a mobile phone, a computer and a monitoring center through a cloud platform.
The system further comprises a field video recorder connected with the switch, a storage, a feedback unit and a screen capture device are respectively arranged in the field video recorder, an image regulator connected with the field video recorder is arranged at the output end of the feedback unit, and the image regulator is used for regulating the resolution of external images and the adaptive change illuminance.
Furthermore, an adjusting camera ball is installed on the tower crane monitoring end, a voice beeper matched with the adjusting camera ball is arranged at the input end of the adjusting camera ball, and the output ends of the adjusting camera ball and the voice beeper are connected with a computer center through a signal amplifier.
Furthermore, the data acquisition unit input still includes the contrast unit who is connected with raise dust sensor, noise transducer, temperature sensor, humidity transducer, air velocity transducer, wind direction sensor, baroceptor and concentration sensor, wherein, contrast unit is used for with carry out data check and handle the analysis before between the information.
Furthermore, one end of the cloud platform output is fixedly connected with a traffic pipe platform.
Compared with the prior art, the invention has the technical effects that:
1. the indoor information access point, the outdoor information access point and the tower crane monitoring end are adopted, comprehensive acquisition of information can be effectively guaranteed, not only is information of a building construction site acquired, but also real-time monitoring can be carried out on images outside the enclosing wall, and the tower crane monitoring end conducts the images when the tower crane works high above the ground, collision between materials and personnel is prevented, and timely butt joint of the materials in a construction site can be guaranteed.
2. The wireless bridging technology on the information access end is a local area network wireless connection technology, is a product combining a wireless radio frequency technology and a traditional wired network bridge technology, can seamlessly connect local area networks separated by dozens of kilometers together to create a unified enterprise or metropolitan area network system, can perform regional management integration on the information of a construction site to form independent regional information, avoids mutual interference during data transmission, and then transmits the regional information to a comprehensive management platform for observation under the action of a wide area network.
3. The monitoring system is internally provided with various sensors, corresponding environment tests are carried out on construction sites respectively, if the corresponding standard values are exceeded, warning operation can be carried out through the alarm, data are transmitted to a computer, a mobile phone and a monitoring center through the cloud platform to be displayed and observed, and meanwhile, the output end of the data acquisition unit adopts a field voice broadcast device, so that the environment information of a construction worker on the field can be well known to a certain extent.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a schematic diagram of the connection of the information access terminal according to the present invention;
fig. 3 is a schematic connection diagram of the monitoring system of the present invention.
Detailed Description
Referring to fig. 1-3, an appearance defect detection method based on machine vision and deep learning includes indoor information access points located in the periphery of a fence, the input end of the indoor information access point is provided with an outdoor information access point matched with the indoor information access point, the outdoor information access point and the indoor information access point transmit data to the computer center in a wireless transmission mode, a tower crane monitoring terminal connected with the computer center is arranged between the indoor information access point and the outdoor information access point, wherein, the information access ends are all provided with an IP camera and a monitoring system, the IP camera is connected with a switch in a wireless network bridging way, one end of the output end of the switch is connected with a display in a network connection mode, the other end of the output end of the switch is connected with a wide area network through an optical fiber, the output end of the wide area network is connected with a headquarter monitoring center through a wireless video management platform;
the monitoring system comprises a dust sensor, a noise sensor, a temperature sensor, a humidity sensor, a wind speed sensor, a wind direction sensor, an air pressure sensor and a concentration sensor which are connected with a data acquisition unit, wherein the output end of the data acquisition unit is respectively connected with a voice player, an alarm and a data transmission system, and the output end of the data transmission system is respectively connected with a mobile phone, a computer and a monitoring center through a cloud platform.
The specific embodiment of the scheme is that the system further comprises a field video recorder connected with the switch, a memory, a feedback unit and a screen capture device are respectively arranged in the field video recorder, an image regulator connected with the field video recorder is arranged at the output end of the feedback unit, the image regulator is used for regulating the resolution of external images and the adaptive change illuminance, the memory in the field video recorder mainly stores data, and the memory in the field video recorder mainly stores the data
The concrete embodiment of this scheme does, install the ball of making a video recording of regulation on the tower crane control end, the ball input of making a video recording of regulation is equipped with the pronunciation calling set rather than the looks adaptation, ball and the pronunciation calling set output of making a video recording of regulation all are connected with the computer center through signal amplifier.
The specific embodiment of this scheme does, the data collection station input still includes the contrast unit who is connected with raise dust sensor, noise sensor, temperature sensor, humidity transducer, air velocity transducer, wind direction sensor, baroceptor and concentration sensor, wherein, contrast unit is used for with before carry out data check and handle the analysis between the information.
The concrete embodiment of this scheme does, cloud platform output one end fixedly connected with traffic pipe platform, the setting of traffic pipe platform is mainly in order to with information transmission to the platform to the transportation operation of material.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are merely illustrative of the principles of the invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. An appearance defect detection method based on machine vision and deep learning comprises indoor information access points positioned in the periphery of a fence, the input end of the indoor information access point is provided with an outdoor information access point matched with the indoor information access point, the outdoor information access point and the indoor information access point transmit data to the computer center in a wireless transmission mode, a tower crane monitoring terminal connected with the computer center is arranged between the indoor information access point and the outdoor information access point, wherein, the information access ends are all provided with an IP camera and a monitoring system, the IP camera is connected with a switch in a wireless network bridging way, one end of the output end of the switch is connected with a display in a network connection mode, the other end of the output end of the switch is connected with a wide area network through an optical fiber, the output end of the wide area network is connected with a headquarter monitoring center through a wireless video management platform;
the monitoring system comprises a dust sensor, a noise sensor, a temperature sensor, a humidity sensor, a wind speed sensor, a wind direction sensor, an air pressure sensor and a concentration sensor which are connected with a data acquisition unit, wherein the output end of the data acquisition unit is respectively connected with a voice player, an alarm and a data transmission system, and the output end of the data transmission system is respectively connected with a mobile phone, a computer and a monitoring center through a cloud platform.
2. The method as claimed in claim 1, further comprising a live video recorder connected to the switch, wherein the live video recorder is respectively provided with a memory, a feedback unit and a screen capture, and the output end of the feedback unit is provided with an image adjuster connected to the live video recorder, wherein the image adjuster is used for adjusting the resolution of the external image and adaptively changing the illumination.
3. The machine vision and deep learning-based appearance defect detection method according to claim 1, wherein an adjusting camera ball is mounted on the tower crane monitoring end, a voice pager matched with the adjusting camera ball is arranged at the input end of the adjusting camera ball, and the output ends of the adjusting camera ball and the voice pager are connected with a computer center through a signal amplifier.
4. The appearance defect detection method based on machine vision and deep learning of claim 1, wherein the input end of the data collector further comprises a comparison unit connected with a dust sensor, a noise sensor, a temperature sensor, a humidity sensor, a wind speed sensor, a wind direction sensor, an air pressure sensor and a concentration sensor, wherein the comparison unit is used for checking data with previous information and processing and analyzing the data.
5. The machine vision and deep learning-based appearance defect detection method according to claim 1, wherein a traffic management platform is fixedly connected to one output end of the cloud platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011026650.5A CN112311852A (en) | 2020-09-25 | 2020-09-25 | Appearance defect detection method based on machine vision and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011026650.5A CN112311852A (en) | 2020-09-25 | 2020-09-25 | Appearance defect detection method based on machine vision and deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112311852A true CN112311852A (en) | 2021-02-02 |
Family
ID=74489187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011026650.5A Pending CN112311852A (en) | 2020-09-25 | 2020-09-25 | Appearance defect detection method based on machine vision and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112311852A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103723641A (en) * | 2013-12-29 | 2014-04-16 | 天津市安维康家科技发展有限公司 | Remote monitoring system for video supervision tower cranes based on 4G wireless communication |
| CN103745579A (en) * | 2014-01-15 | 2014-04-23 | 武汉科技大学 | Security and protection monitoring system |
| CN107135263A (en) * | 2017-05-11 | 2017-09-05 | 深圳市柘叶红实业有限公司 | Dust from construction sites remote control administrative system and management method |
| US20190277822A1 (en) * | 2018-03-06 | 2019-09-12 | Applied Particle Technology, Inc. | Wireless exposure monitor |
-
2020
- 2020-09-25 CN CN202011026650.5A patent/CN112311852A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103723641A (en) * | 2013-12-29 | 2014-04-16 | 天津市安维康家科技发展有限公司 | Remote monitoring system for video supervision tower cranes based on 4G wireless communication |
| CN103745579A (en) * | 2014-01-15 | 2014-04-23 | 武汉科技大学 | Security and protection monitoring system |
| CN107135263A (en) * | 2017-05-11 | 2017-09-05 | 深圳市柘叶红实业有限公司 | Dust from construction sites remote control administrative system and management method |
| US20190277822A1 (en) * | 2018-03-06 | 2019-09-12 | Applied Particle Technology, Inc. | Wireless exposure monitor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104581087B (en) | A kind of power transmission line intelligent remote monitoring system based on Internet of Things | |
| CN112288984A (en) | Three-dimensional visual unattended substation intelligent linkage system based on video fusion | |
| US20090122143A1 (en) | Security system and network | |
| CN110888402A (en) | Intelligent building site environment comprehensive monitoring system based on SAAS platform | |
| CN103745579A (en) | Security and protection monitoring system | |
| CN106003040A (en) | Transformer substation inspection robot system with obstacle avoidance function | |
| CN103309323B (en) | Inspection device method for supervising and the system of tunnel environment | |
| CN205388766U (en) | Building engineering safety construction informatization monitoring system | |
| CN106003075A (en) | Transformer substation inspection robot system with speech communication function | |
| CN207304762U (en) | The network transmission system of the video monitoring of power grid wisdom building site control platform | |
| CN205540176U (en) | Communication tower remote monitering system | |
| CN105427513A (en) | Fire-proof video infrared monitoring system for large-area remote sensing forest | |
| KR102012657B1 (en) | System, server and method for monitoring environment | |
| CN107798805A (en) | A kind of safety monitoring system based on information technology | |
| CN108847985A (en) | Power transmission line intelligent remote monitoring system suitable for Internet of Things | |
| CN204388922U (en) | Micro-climate monitoring and early warning system | |
| CN113709350A (en) | AI intelligence dust fall system | |
| CN113163178A (en) | Intelligent security and linkage control system based on Internet of things | |
| CN211878460U (en) | Intelligent comprehensive monitoring system for distribution transformer environment | |
| CN112311852A (en) | Appearance defect detection method based on machine vision and deep learning | |
| CN110312102A (en) | A kind of construction site personnel monitoring system | |
| CN107180513A (en) | Environment airborne dust noise monitoring early warning system | |
| CN108646690A (en) | A kind of distribution room monitoring system | |
| CN202266962U (en) | Lighting equipment of integrated intelligent safety and protection system | |
| CN105988444A (en) | Iron tower remote control monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210202 |