CN113628410A - Smog identification camera based on embedded system - Google Patents
Smog identification camera based on embedded system Download PDFInfo
- Publication number
- CN113628410A CN113628410A CN202010378820.XA CN202010378820A CN113628410A CN 113628410 A CN113628410 A CN 113628410A CN 202010378820 A CN202010378820 A CN 202010378820A CN 113628410 A CN113628410 A CN 113628410A
- Authority
- CN
- China
- Prior art keywords
- smoke
- card
- camera
- card type
- type computer
- 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
- 239000000779 smoke Substances 0.000 claims abstract description 48
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 10
- 230000009286 beneficial effect Effects 0.000 claims description 4
- 235000002566 Capsicum Nutrition 0.000 claims description 3
- 239000006002 Pepper Substances 0.000 claims description 3
- 235000016761 Piper aduncum Nutrition 0.000 claims description 3
- 235000017804 Piper guineense Nutrition 0.000 claims description 3
- 235000008184 Piper nigrum Nutrition 0.000 claims description 3
- 240000007651 Rubus glaucus Species 0.000 claims description 3
- 235000011034 Rubus glaucus Nutrition 0.000 claims description 3
- 235000009122 Rubus idaeus Nutrition 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000002203 pretreatment Methods 0.000 claims description 3
- 150000003839 salts Chemical class 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 claims 1
- 238000004891 communication Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 3
- 241000722363 Piper Species 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to the technical field of fire safety, in particular to a smoke identification camera based on an embedded system; the intelligent card type computer comprises a card type computer and a USB camera, wherein the USB camera is connected with an input port of the card type computer through a USB line, an embedded Linux system is installed on the card type computer, the USB camera is controlled through the embedded Linux system to acquire images through programming, then the images are preprocessed, then smoke target area extraction, smoke characteristic extraction and smoke image identification are sequentially carried out, and once smoke is identified, early warning information is issued to an upper computer in a wired or wireless mode. Because the early warning information only comprises the data of eleven bytes, no matter which network is selected, the network speed cannot be influenced, and the condition that the early warning delay is caused by the problems of network traffic jam and the like is avoided.
Description
Technical Field
The invention relates to the technical field of fire safety, in particular to a smoke identification camera based on an embedded system.
Background
Cameras are required to be installed in many occasions and used for security protection, public security, fire protection and the like. Most cameras are a vertical interactive video data mode, namely the cameras do not process images and directly transmit the images to an upper computer in real time in a wired or wireless mode, all operations are performed on the upper computer, and early warning is possibly delayed due to the fact that the network speed is influenced by various objective factors.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the embedded smoke recognition camera which can process and recognize smoke in real time on site, generate an early warning signal and greatly improve the early warning sending efficiency.
The technical scheme of the invention is as follows:
smog discernment camera based on embedded system, its characterized in that:
the intelligent card type computer comprises a card type computer and a USB camera, wherein the USB camera is connected with an input port of the card type computer through a USB line, an embedded Linux system is installed on the card type computer, the USB camera is controlled through the embedded Linux system to acquire images through programming, then the images are preprocessed, then smoke target area extraction, smoke characteristic extraction and smoke image identification are sequentially carried out, and once smoke is identified, early warning information is issued to an upper computer in a wired or wireless mode. Because the early warning information only comprises the data of eleven bytes, no matter which network is selected, the network speed cannot be influenced, and the condition that the early warning delay is caused by the problems of network traffic jam and the like is avoided.
Furthermore, card formula computer is for its installation corresponding Motion software after starting the USB camera, and the managers can carry out remote monitoring through this procedure when needing, and the managers of being convenient for patrols and examines regularly.
Further, the card type computer is provided with an SD card and is used for storing data and an embedded Linux system, wherein the method for storing the embedded Linux system comprises the steps of sleeving the SD card into a card reader and inserting the SD card into a USB interface of a common desktop computer, writing a mirror image tool of the embedded Linux system into the SD card, writing an operating system into the SD card by using a win32disk image, and finally inserting the SD card into an SD card slot of the card type computer.
Further, the card computer is a raspberry pie.
Further, the pretreatment method comprises the following steps:
removing salt and pepper noise by median filtering and reserving edge details;
and then carrying out image enhancement by histogram equalization.
Further, the method for extracting the smoke target area comprises the following steps:
background modeling, wherein for observation data of random variables as samples of pixels at moments, a single sampling point of the observation data obeys a Gaussian mixture distribution probability density function;
updating parameters, namely updating two parameters of the Gaussian function and the weight of each Gaussian distribution, wherein the updating rule is as follows: comparing the pixel values of each point of the current frame with the current plurality of models until a distribution model matching the new pixel values is found;
extracting targets, arranging Gaussian distributions in a descending order according to omega/mu values, and taking a plurality of distributions arranged at the forefront as background models of the Gaussian distributions;
and during target detection, judging the foreground point, performing image difference operation on the current frame and the previous frame, giving a threshold value, giving a larger learning rate if the threshold value is exceeded, and giving a normal learning rate if the threshold value is not exceeded.
Further, the method for extracting the smoke features comprises the following steps:
reflecting the texture feature degree of the image through the contrast;
and calculating the movement direction of the smoke region by extracting and comparing the positions of the central point of the minimum peripheral rectangle at the edge of the smoke region in the front frame and the rear frame, thereby extracting the characteristics of the movement direction.
Further, the method for identifying the smoke image comprises the following steps:
the smoke feature fusion and judgment are carried out based on the SVM, specifically, an RBF kernel function is adopted, and a cross validation method is used for selecting preferred model parameters.
In some embodiments, the network cable port of the card computer is connected with a local area network through an intelligent gateway, and the local area network is connected with the internet. The camera is beneficial to large-scale arrangement.
Considering that WiFi adopts TCP/IP communication, and the requirement for the processor is high by using such a complex protocol stack, and in addition, the power consumption is high, so that in the case of slow wireless communication, other relatively simple wireless communication can be adopted, and this embodiment adopts: the card type computers are firstly interconnected through a ZigBee network and then the switchboard is connected with the WiFi.
The invention has the beneficial effects that: the camera is transformed by cheap embedded hardware and software, so that the camera has the function of detecting and analyzing fire smoke in real time on the spot, and because the uploading information of the camera usually only comprises early warning information and does not contain a large amount of video information, the network requirement is greatly reduced, the arrangement of the camera in a large range is facilitated, and the occurrence of network congestion in a monitoring network is reduced.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
In the figure, 1, a USB camera; 2. a card computer; 3. a ZigBee network; 21. a network cable port; 22. an SD card.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
example 1
As shown in fig. 1, the smoke recognition camera based on the embedded system is characterized in that:
the intelligent card type computer comprises a card type computer and a USB camera, wherein the USB camera is connected with an input port of the card type computer through a USB line, an embedded Linux system is installed on the card type computer, the USB camera is controlled through the embedded Linux system to acquire images through programming, then the images are preprocessed, then smoke target area extraction, smoke characteristic extraction and smoke image identification are sequentially carried out, and once smoke is identified, early warning information is issued to an upper computer in a wired or wireless mode. Because the early warning information only comprises the data of eleven bytes, no matter which network is selected, the network speed cannot be influenced, and the condition that the early warning delay is caused by the problems of network traffic jam and the like is avoided.
Furthermore, card formula computer is for its installation corresponding Motion software after starting the USB camera, and the managers can carry out remote monitoring through this procedure when needing, and the managers of being convenient for patrols and examines regularly.
Further, the card type computer is provided with an SD card and is used for storing data and an embedded Linux system, wherein the method for storing the embedded Linux system comprises the steps of sleeving the SD card into a card reader and inserting the SD card into a USB interface of a common desktop computer, writing a mirror image tool of the embedded Linux system into the SD card, writing an operating system into the SD card by using a win32disk image, and finally inserting the SD card into an SD card slot of the card type computer.
Further, the card computer is a raspberry pie.
Further, the pretreatment method comprises the following steps:
removing salt and pepper noise by median filtering and reserving edge details;
and then carrying out image enhancement by histogram equalization.
Further, the method for extracting the smoke target area comprises the following steps:
background modeling, wherein for observation data of random variables as samples of pixels at moments, a single sampling point of the observation data obeys a Gaussian mixture distribution probability density function;
updating parameters, namely updating two parameters of the Gaussian function and the weight of each Gaussian distribution, wherein the updating rule is as follows: comparing the pixel values of each point of the current frame with the current plurality of models until a distribution model matching the new pixel values is found;
extracting targets, arranging Gaussian distributions in a descending order according to omega/mu values, and taking a plurality of distributions arranged at the forefront as background models of the Gaussian distributions;
and during target detection, judging the foreground point, performing image difference operation on the current frame and the previous frame, giving a threshold value, giving a larger learning rate if the threshold value is exceeded, and giving a normal learning rate if the threshold value is not exceeded.
Further, the method for extracting the smoke features comprises the following steps:
reflecting the texture feature degree of the image through the contrast;
and calculating the movement direction of the smoke region by extracting and comparing the positions of the central point of the minimum peripheral rectangle at the edge of the smoke region in the front frame and the rear frame, thereby extracting the characteristics of the movement direction.
Further, the method for identifying the smoke image comprises the following steps:
the smoke feature fusion and judgment are carried out based on the SVM, specifically, an RBF kernel function is adopted, and a cross validation method is used for selecting preferred model parameters.
Example 2
And the network cable port of the card computer is connected with a local area network through an intelligent gateway, and the local area network is connected with the Internet. The camera is beneficial to large-scale arrangement.
Considering that WiFi adopts TCP/IP communication, and the requirement for the processor is high by using such a complex protocol stack, and in addition, the power consumption is high, so that in the case of slow wireless communication, other relatively simple wireless communication can be adopted, and this embodiment adopts: the card type computers are firstly interconnected through a ZigBee network and then the switchboard is connected with the WiFi.
The other structure of this embodiment is the same as embodiment 1.
The foregoing embodiments and description have been presented only to illustrate the principles and preferred embodiments of the invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention as hereinafter claimed.
Claims (9)
1. Smog discernment camera based on embedded system, its characterized in that: the intelligent card type computer comprises a card type computer and a USB camera, wherein the USB camera is connected with an input port of the card type computer through a USB line, an embedded Linux system is installed on the card type computer, the USB camera is controlled through the embedded Linux system to acquire images through programming, then the images are preprocessed, then smoke target area extraction, smoke characteristic extraction and smoke image identification are sequentially carried out, and once smoke is identified, early warning information is issued to an upper computer in a wired or wireless mode.
2. The embedded system based smoke recognition camera of claim 1, wherein: and the card type computer installs corresponding Motion software for the USB camera after the USB camera is started.
3. The embedded system based smoke recognition camera of claim 2, wherein: the card type computer is provided with an SD card and is used for storing data and an embedded Linux system, wherein the method for storing the embedded Linux system comprises the steps of sleeving the SD card into a card reader and inserting the SD card into a USB interface of a common desktop computer, writing a mirror image tool of the embedded Linux system into the SD card, writing an operating system into the SD card by using a win32disk image, and finally inserting the SD card into an SD card slot of the card type computer.
4. The embedded system based smoke recognition camera of claim 3, wherein: the card type computer is a raspberry pie.
5. The embedded system based smoke recognition camera of claim 4, wherein: the pretreatment method comprises the following steps:
removing salt and pepper noise by median filtering and reserving edge details;
and then carrying out image enhancement by histogram equalization.
Further, the method for extracting the smoke target area comprises the following steps:
background modeling, wherein for observation data of random variables as samples of pixels at moments, a single sampling point of the observation data obeys a Gaussian mixture distribution probability density function;
updating parameters, namely updating two parameters of the Gaussian function and the weight of each Gaussian distribution, wherein the updating rule is as follows: comparing the pixel values of each point of the current frame with the current plurality of models until a distribution model matching the new pixel values is found;
extracting targets, arranging Gaussian distributions in a descending order according to omega/mu values, and taking a plurality of distributions arranged at the forefront as background models of the Gaussian distributions;
and during target detection, judging the foreground point, performing image difference operation on the current frame and the previous frame, giving a threshold value, giving a larger learning rate if the threshold value is exceeded, and giving a normal learning rate if the threshold value is not exceeded.
6. The embedded system based smoke recognition camera of claim 5, wherein: the method for extracting the smoke features comprises the following steps:
reflecting the texture feature degree of the image through the contrast;
and calculating the movement direction of the smoke region by extracting and comparing the positions of the central point of the minimum peripheral rectangle at the edge of the smoke region in the front frame and the rear frame, thereby extracting the characteristics of the movement direction.
7. The embedded system based smoke recognition camera of claim 6, wherein: the method for identifying the smoke image comprises the following steps:
the smoke feature fusion and judgment are carried out based on the SVM, specifically, an RBF kernel function is adopted, and a cross validation method is used for selecting preferred model parameters.
8. The embedded system based smoke recognition camera of claim 7, wherein: and the network cable port of the card computer is connected with a local area network through an intelligent gateway, and the local area network is connected with the Internet. The camera is beneficial to large-scale arrangement.
9. The embedded system based smoke recognition camera of claim 8, wherein: the card type computers are firstly interconnected through a ZigBee network and then the switchboard is connected with the WiFi.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010378820.XA CN113628410A (en) | 2020-05-07 | 2020-05-07 | Smog identification camera based on embedded system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010378820.XA CN113628410A (en) | 2020-05-07 | 2020-05-07 | Smog identification camera based on embedded system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113628410A true CN113628410A (en) | 2021-11-09 |
Family
ID=78376978
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010378820.XA Pending CN113628410A (en) | 2020-05-07 | 2020-05-07 | Smog identification camera based on embedded system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113628410A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050478A (en) * | 2014-07-09 | 2014-09-17 | 湖南大学 | Smog detection method and system |
US9288458B1 (en) * | 2015-01-31 | 2016-03-15 | Hrl Laboratories, Llc | Fast digital image de-hazing methods for real-time video processing |
CN105528581A (en) * | 2015-12-10 | 2016-04-27 | 华南理工大学 | Video smoke event detection method based on bionic color sensing model |
CN108023952A (en) * | 2017-12-04 | 2018-05-11 | 西安电子科技大学 | A kind of modularization Internet of Things application rapid build platform combined based on cloud and mist |
CN108521556A (en) * | 2018-03-30 | 2018-09-11 | 北京林业大学 | Intelligent-tracking monitoring camera based on embedded system |
CN108874609A (en) * | 2018-08-31 | 2018-11-23 | 佰电科技(苏州)有限公司 | Magnetic tape storage controls board function testing station |
CN108932814A (en) * | 2018-07-18 | 2018-12-04 | 东华大学 | A kind of embedded image type cooking fire warning device |
CN209785104U (en) * | 2019-06-24 | 2019-12-13 | 上海工程技术大学 | Dormitory entrance guard bedding checking system based on face recognition |
-
2020
- 2020-05-07 CN CN202010378820.XA patent/CN113628410A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050478A (en) * | 2014-07-09 | 2014-09-17 | 湖南大学 | Smog detection method and system |
US9288458B1 (en) * | 2015-01-31 | 2016-03-15 | Hrl Laboratories, Llc | Fast digital image de-hazing methods for real-time video processing |
CN105528581A (en) * | 2015-12-10 | 2016-04-27 | 华南理工大学 | Video smoke event detection method based on bionic color sensing model |
CN108023952A (en) * | 2017-12-04 | 2018-05-11 | 西安电子科技大学 | A kind of modularization Internet of Things application rapid build platform combined based on cloud and mist |
CN108521556A (en) * | 2018-03-30 | 2018-09-11 | 北京林业大学 | Intelligent-tracking monitoring camera based on embedded system |
CN108932814A (en) * | 2018-07-18 | 2018-12-04 | 东华大学 | A kind of embedded image type cooking fire warning device |
CN108874609A (en) * | 2018-08-31 | 2018-11-23 | 佰电科技(苏州)有限公司 | Magnetic tape storage controls board function testing station |
CN209785104U (en) * | 2019-06-24 | 2019-12-13 | 上海工程技术大学 | Dormitory entrance guard bedding checking system based on face recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109714322B (en) | Method and system for detecting network abnormal flow | |
CN110097109B (en) | Road environment obstacle detection system and method based on deep learning | |
US10706330B2 (en) | Methods and systems for accurately recognizing vehicle license plates | |
CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
CN107105207A (en) | Target monitoring method, target monitoring device and video camera | |
US9323991B2 (en) | Method and system for video-based vehicle tracking adaptable to traffic conditions | |
CN102332092B (en) | Flame detection method based on video analysis | |
WO2021114866A1 (en) | Method and apparatus for detecting occluded image, electronic device, and storage medium | |
CN109389185B (en) | Video smoke identification method using three-dimensional convolutional neural network | |
CN110414376B (en) | Method for updating face recognition model, face recognition camera and server | |
WO2023273011A9 (en) | Method, apparatus and device for detecting object thrown from height, and computer storage medium | |
Toreyin et al. | Wildfire detection using LMS based active learning | |
CN111800430A (en) | Attack group identification method, device, equipment and medium | |
CN116563762A (en) | Fire detection method, system, medium, equipment and terminal for oil and gas station | |
CN111695493A (en) | Method and system for detecting hidden danger of power transmission line | |
CN112883782A (en) | Method, device, equipment and storage medium for identifying putting behaviors | |
US11688200B2 (en) | Joint facial feature extraction and facial image quality estimation using a deep neural network (DNN) trained with a custom-labeled training dataset and having a common DNN backbone | |
CN113628410A (en) | Smog identification camera based on embedded system | |
US11881053B2 (en) | Systems and methods for hierarchical facial image clustering | |
CN114979497B (en) | Unmanned aerial vehicle linkage tracking method and system based on pole loading and cloud platform | |
CN113361455B (en) | Training method of face counterfeit identification model, related device and computer program product | |
WO2022198507A1 (en) | Obstacle detection method, apparatus, and device, and computer storage medium | |
CN113420631A (en) | Safety alarm method and device based on image recognition | |
CN112418055A (en) | Scheduling method based on video analysis and personnel trajectory tracking method | |
CN112837471A (en) | Security monitoring method and device for internet contract room |
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: 20211109 |
|
RJ01 | Rejection of invention patent application after publication |