CN113793471A - Detection device and method based on image recognition - Google Patents
Detection device and method based on image recognition Download PDFInfo
- Publication number
- CN113793471A CN113793471A CN202110934312.XA CN202110934312A CN113793471A CN 113793471 A CN113793471 A CN 113793471A CN 202110934312 A CN202110934312 A CN 202110934312A CN 113793471 A CN113793471 A CN 113793471A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- module
- images
- recognition
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims description 11
- 238000012545 processing Methods 0.000 claims abstract description 44
- 230000003068 static effect Effects 0.000 claims abstract description 21
- 230000004927 fusion Effects 0.000 claims description 32
- 239000000779 smoke Substances 0.000 claims description 20
- 238000010191 image analysis Methods 0.000 claims description 12
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 239000007921 spray Substances 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 230000001012 protector Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000005253 cladding Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000002209 hydrophobic effect Effects 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000000007 visual effect 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fire-Detection Mechanisms (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a detection device based on image recognition, which comprises a shell and a camera, wherein the camera is fixedly arranged at one end of the shell and comprises a first camera and a second camera which are arranged in parallel, the first camera and the second camera respectively collect static images and dynamic images in a detection area, the detection areas of the first camera and the second camera have the same detection area, the input ends of the first camera and the second camera are electrically connected with an image recognition module, the image recognition module is used for recognizing moving targets in the detection areas of the first camera and the second camera, and the output ends of the first camera and the second camera are electrically connected with an image processing module which is used for recognizing, memorizing, learning, fusing, storing and the collected images, The invention has the effects of reducing the false alarm probability and more accurately identifying.
Description
Technical Field
The invention relates to the technical field of detection devices, in particular to a detection device and a detection method based on image recognition.
Background
The visual fire detection technology can be divided into a flame image detection technology and a smoke image detection technology according to different detection objects and different identification algorithms. The smoke image recognition detection technology can discover fire earlier and realize early fire detection, and the existing smoke detection modes mainly comprise the following modes: compared with the first three modes, the detection mode based on the video has the main advantages of low cost and wide coverage area, but due to the fact that various interferences exist in a video scene, the detection method based on the video often has more false alarm conditions, and therefore image recognition in the video needs to be further enhanced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a detection device and a detection method based on image recognition, which have the advantages of reducing the false alarm probability and more accurate recognition.
The above object of the present invention is achieved by the following technical solutions: a detection device based on image recognition comprises a shell and a camera, wherein the camera is fixedly arranged at one end of the shell, the camera comprises a first camera and a second camera which are arranged in parallel, the first camera and the second camera respectively collect static images and dynamic images in the detection area, and the detection areas of the first camera and the second camera have the same detection area, the input ends of the first camera and the second camera are electrically connected with an image recognition module which is used for recognizing movable targets in the detection areas of the first camera and the second camera, and the output ends of the first camera and the second camera are electrically connected with an image processing module, the system is used for carrying out recognition, memory learning, fusion, storage and alarm processing on the collected images.
Preferably, the image processing module includes: the image acquisition module is electrically connected with the first camera and the second camera to recognize and acquire images acquired by the first camera and the second camera, and is electrically connected with the image storage module, and the image acquisition module memorizes and learns the acquired images through a built-in memory algorithm;
the input end of the image fusion module is electrically connected with the image acquisition module, receives the acquired image transmitted by the image acquisition module, and fuses the dynamic image and the static image to form a first image, wherein the frame number of the first image is the same as that of the dynamic image;
the image storage module is in bidirectional electrical connection with the image fusion module, a plurality of first images are conveyed into the image storage module through the image fusion module, then conveyed to the image fusion module through the image storage module to be fused for the second time to form second images, and then the second images are input into the image storage module to be stored, a database is arranged in the image storage module, and the second images are stored in the database;
the image analysis module is electrically connected with the image storage module and is used for analyzing and comparing the second image with the data in the database;
the wireless sending module is electrically connected with the image analysis module, and when the second image meets the smoke alarm standard, the wireless sending module sends an alarm instruction.
An image recognition-based detection method, which is adopted by the image recognition-based detection device, comprises the following steps:
the method comprises the following steps: the method comprises the steps that moving targets in detection areas of a first camera and a second camera are identified through an image identification module, the first camera collects dynamic images of the moving targets, the second camera collects static images outside the moving targets, and the collected images are conveyed to an image processing module through the first camera and the second camera;
step two: the image processing module receives the images transmitted by the first camera and the second camera, and carries out recognition, memory learning, fusion, storage and alarm processing on the images.
Preferably, in the second step, the image processing module specifically performs recognition, memory learning, fusion, storage and alarm processing on the image as follows:
identification: identifying the image through an image acquisition module in an image processing module, and distinguishing the grey component and the outline of a moving target in the image;
memory and learning: the recognition state of the moving target is memorized and learned through an algorithm program in the image processing module;
fusing: the image fusion module in the image processing module receives the dynamic image and the static image transmitted by the image acquisition module and fuses the dynamic image and the static image to form a first image, wherein the frame number of the first image is the same as that of the dynamic image;
and (3) storage: storing multiple groups of first images through an image storage module in the image processing module, and conveying the multiple groups of first images to the image fusion module for secondary fusion to form a second image;
and (4) alarming: the second image is analyzed through the cooperation between the image analysis module and the wireless sending module in the image processing module, and when the second image meets the smoke alarm standard, the wireless sending module sends out an alarm instruction.
In summary, the invention includes at least one of the following beneficial technical effects: according to the invention, the image acquisition module, the image fusion module, the image storage module, the image analysis module and the wireless transmission module in the image processing module are matched with the first camera and the second camera, so that the acquired images are identified, memorized, learned, fused and stored to judge whether to alarm or not, the false alarm probability of the device is reduced, and the accurate monitoring of the fire is realized.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic view showing a configuration of a camera according to the present invention;
FIG. 3 is a schematic structural diagram showing the connection relationship between the camera and the image recognition module and the image processing module;
FIG. 4 is a schematic structural diagram showing a connection relationship between a camera and an image processing module according to the present invention;
FIG. 5 is a schematic view of a first embodiment of the present invention;
FIG. 6 is a schematic view of a second embodiment of the present invention;
fig. 7 is a schematic view showing the structure of a third protection device according to the present invention.
Reference numerals: 1. a housing; 11. a flashing board; 2. a camera; 21. a first camera; 22. a second camera; 3. an image recognition module; 4. an image processing module; 41. an image acquisition module; 42. an image fusion module; 43. an image storage module; 44. an image analysis module; 45. a wireless transmission module; 5. a demisting module; 6. a guard; 61. a shower head; 62. a temperature sensor; 63. a controller; 7. a distance sensor.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the application without any inventive step, are within the scope of protection of the application.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" or "an" and the like in the description and in the claims of the present application do not denote a limitation of quantity, but rather denote the presence of at least one.
In the description of the present application and claims, the terms "upper", "lower", "horizontal", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or unit must have a specific direction, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present application.
The present invention will be described in further detail with reference to the accompanying drawings.
Fig. 1-7 show a specific embodiment of the detection device based on image recognition according to the present invention, which includes a housing 1 and a camera 2, wherein the camera 2 is fixedly disposed at one end of the housing 1, and a rain-proof plate 11 is fixedly disposed at the top of the housing 1, and the rain-proof plate 11 is disposed at an end of the housing 1 close to the camera 2, and is used for protecting the camera from normally maintaining the definition of the lens in rainy days.
Wherein, the camera 2 comprises a first camera 21 and a second camera 22 which are arranged in parallel, the first camera 21 and the second camera 22 respectively collect static images and dynamic images in the detection area, and the detection areas of the first camera 21 and the second camera 22 have the same detection area, so that when the collected dynamic image and the static image are fused in the later period, the dynamic image and the static image can be fused perfectly, moreover, the first camera 21 and the second camera 22 are used for respectively collecting static images and dynamic images, and can also be used for processing the monitored targets in the same detection area in a labor-sharing way, thereby reducing the use frequency of the cameras, prolonging the service life of the cameras, and moreover, through the dynamic picture and the static picture, the moving target can be accurately identified, the characteristics of the moving target can be accurately monitored, so that the fire can be accurately monitored, and the probability of misinformation is reduced.
Specifically, the input ends of the first camera 21 and the second camera 22 are electrically connected to the image recognition module 3, and the image recognition module 3 is configured to recognize moving objects in the detection areas of the first camera 21 and the second camera 22, where in this embodiment, the moving object mainly refers to one of smoke and flame or a combination thereof, and when smoke and flame occur, the moving object is recognized according to the change motion of image pixels, or recognized through color features of smoke, open fire, and the like, and further recognized through texture features of smoke, open fire, and the like, and a dense optical flow method may also be used to extract reliable dynamic features of smoke and fire.
Certainly, in order to improve the recognition capability of the image recognition module 3, in the present invention, the four recognition modes may be combined to perform sorting and screening, so as to filter out an obvious non-smoke color region, an obvious non-smoke texture region, a motion region which cannot be matched with the previous and subsequent frames, and morphological characteristics and change mutation thereof, so as to improve the recognition capability of the image recognition module 3.
In this embodiment, the output ends of the first camera 21 and the second camera 22 are electrically connected to the image processing module 4, and are used for performing recognition, memory learning, fusion, storage, and alarm processing on the collected images, so as to improve the definition of the images, and facilitate monitoring in the detection area.
Specifically, the image processing module 4 includes: the image acquisition module 41, the image fusion module 42, the image storage module 43, the image analysis module 44 and the wireless transmission module 45, wherein the image acquisition module 41 is electrically connected with the output ends of the first camera 21 and the second camera 22 to realize the identification and acquisition of the images acquired by the first camera 21 and the second camera 22, and in this embodiment, the image acquisition module 41 is electrically connected with the image storage module 43, the image acquisition module 41 performs memory learning on the acquired images through a written memory algorithm and stores the learned results into the image storage module 43 to form a memory bank, so as to improve the image acquisition, the identification capability of the module, facilitate the filtering of non-smoke areas and realize the accurate identification of moving targets;
the input end of the image fusion module 42 is electrically connected to the image acquisition module 41, receives the acquired image transmitted by the image acquisition module 41, fuses the dynamic image and the static image to form a first image, and the frame number of the first image is the same as the frame number of the dynamic image.
In the present application, the image storage module 43 and the image fusion module 42 are electrically connected in a bidirectional manner, wherein the dynamic image and the static image collected by each camera 2 are fused by the image fusion module 42 to generate a first image, and the number of frames between the generated plurality of first images is ensured to be distributed in integer multiples.
The plurality of first images are transmitted into the image storage module 43 through the image fusion module 42, and then transmitted to the image fusion module 42 through the image storage module 43 to be fused for the second time to form a second image, and then the second image is input into the image storage module 43 to be stored, and the image storage module 43 is provided with a database, and the second image is stored in the database.
Of course, due to the electrical connection between the image storage module 43 and the image capturing module 41, the storage of the second image by the image storage module 43 provides a memory learning condition for the memory learning of the image capturing module 41, so as to improve the recognition capability of the image capturing module 41.
In the application, the image analysis module 44 is electrically connected with the image storage module 43, the wireless transmission module 45 is electrically connected with the image analysis module 44, the second image is analyzed and compared with data in the database, and when the second image meets the smoke alarm standard, the wireless transmission module 45 sends out an alarm instruction and prompts a detector to check the detection area through the arranged alarm device.
Of course, the alarm mode includes any one or combination of sound alarm, warning light alarm, information sending alarm and mobile terminal vibration alarm, and the alarm mode can also carry out early warning prompt by screen split flashing of a screen.
When the detection device is in colder weather, because the device gives off heat in the use, it is vaporific to receive cold formation in front of the camera lens of camera 2 very easily, influence the definition of camera 2 camera lens, therefore, be provided with defogging module 5 before the camera lens of camera 2, through being connected defogging module 5 and image recognition module 3 electricity, discern the image that first camera 21 and second camera 22 gathered through image recognition module 3, when the image that image recognition module 3 discerned is in the fuzzy state, start defogging module 5, blow cold air through defogging module 5 control wherein defogging head to the camera lens of camera 2, in order to reach the camera lens defogging effect to camera 2.
In this embodiment, can also be through setting up protector 6 outside detection device's casing 1, when the condition of a fire appears, protector 6 can be fine protect detection device, wherein, protector 6 includes shower head 61, temperature sensor 62, controller 63 respectively with temperature sensor 62, be connected electrically between shower head 61, when temperature sensor 62 detects when equipment ambient temperature is greater than the settlement threshold value, send the temperature signal of telecommunication to controller 63, controller 63 turns into the signal of telecommunication and sprays the instruction, and transmit in shower head 61, realize that shower head 61 puts out a fire to cooling around the device.
Wherein, the effect of lowering the temperature and putting out a fire around the detection device is being realized to shower head 61, the mode that adopts is as follows:
firstly, the orientation of the spray headers 61 is set, specifically, a plurality of spray headers 61 are fixedly arranged around the shell 1, the spray headers 61 around are used for spraying water to form a protective cover, the fire around the equipment is temporarily controlled through the cooling and inactivation of water, so that the detection personnel can conveniently monitor the fire in real time, and the water sprayed by the spray headers 61 cools the detection device to prevent the detection equipment from being burnt by high temperature;
secondly, in order to further protect detecting device, therefore, carry out the cladding setting around along detecting device through the conduit that will connect shower head 61, make conduit at the in-process of water delivery, can cool down equipment, and set up the temperature measurement piece in hydrophobic pipeline, through the temperature of inclining in-real time supervision conduit, when the temperature is greater than or equal to the settlement threshold value, through the velocity of flow of the water in the increase conduit, improve the radiating efficiency of conduit, further protect detecting device, of course, in this embodiment, the temperature threshold value can set up the cascaded, it is corresponding with cascaded velocity of flow respectively to set for the threshold value through the cascaded, in order to realize the rational utilization to rivers, and can realize carrying out long-term water-cooling heat dissipation to detecting device, extension detecting device's life.
In addition, in the embodiment, a part of the shower head 61 is disposed in the housing 1 near the camera 2 and electrically connected to the image recognition module 3 through the controller 63, and when the image recognition module 3 recognizes the images captured by the first camera 21 and the second camera 22 and the image recognized by the image recognition module 3 is in a blurred state, the controller 63 controls the shower head 61 to spray and clean the lens of the camera 2 through the shower head 61, so that the defogging module 5 can be replaced, and the structure is simpler.
Certainly, in this application, can also realize regularly wasing the camera lens of camera 2 through setting for the frequency that sprays of shower head 61, more do benefit to camera 2 when gathering the image, can reduce because camera 2's camera lens filth causes the fuzzy probability of image gathered.
In this embodiment, the temperature sensor 62 may be replaced by the distance sensor 7, the distance sensor 7 is electrically connected to the camera 2, when the camera 2 takes an image in the detection area, the distance sensor 7 senses the distance between the device and the moving object and transmits the real-time distance to the controller 63, and when the distance is smaller than or equal to the set distance threshold, the controller 63 sends a spraying instruction to open the pair of spray heads 61.
Certainly, in this embodiment, can also cooperate between temperature sensor 62 and the distance sensor 7, when the distance sensor 7 does not detect movable target, temperature sensor 62 can carry out real-time control to detecting device's ambient temperature, guarantee that detecting device does not receive the damage, of course temperature sensor 62 can also pass through controller 63 with alarm device and be connected electrically, when temperature sensor 62 detects that the temperature around the detecting device is higher than normal temperature, temperature sensor 62 gives controller 63 with signal transmission, controller 63 sends alarm command and transmits in alarm device, the angle of measurement personnel accessible adjustment camera is looked over, in order to guarantee in time to look over the environment around the detecting device.
The invention also discloses a detection method based on image recognition, which comprises the following steps:
the method comprises the following steps: the method comprises the steps that moving targets in detection areas of a first camera 21 and a second camera 22 are identified through an image identification module 3, the first camera 21 collects dynamic images of the moving targets, the second camera 22 collects static images outside the moving targets, the collected images are conveyed to an image processing module 4 through the first camera 21 and the second camera 22, the moving targets are identified mainly according to the change motion of image pixels, or the moving targets are identified through color features of smoke, open fire and the like, and the texture features of the smoke, the open fire and the like are identified, and reliable smoke dynamic features can also be extracted through an intensive optical flow method;
step two: the image processing module 4 receives the images transmitted by the first camera 21 and the second camera 22, and performs recognition, memory learning, fusion, storage and alarm processing on the images.
In the second step, the image processing module 4 sequentially identifies, learns, fuses, stores and alarms the image, and specifically comprises:
identification: the image is identified through an image acquisition module 41 in the image processing module 4, and the grey component and the outline of the moving target in the image are distinguished so as to realize accurate identification of the moving target;
memory and learning: the recognition state of the moving target is memorized and learned through a memory algorithm program in the image processing module 4, so that the capability of the later-stage image recognition module 3 for recognizing the moving target can be improved, and the false alarm probability is reduced;
fusing: the image fusion module 42 in the image processing module 4 receives the dynamic image and the static image transmitted by the image acquisition module 41, and fuses the dynamic image and the static image to form a first image, and the frame number of the first image is ensured to be the same as that of the dynamic image;
and (3) storage: the image storage module 43 in the image processing module 4 stores multiple groups of first images, ensures that the number of frames of the multiple groups of first images is set to be integral multiple, and transmits the multiple groups of first images to the image fusion module 42 for secondary fusion to form a second image, so that the number of frames of the multiple first images are superposed to improve the image cleaning degree and facilitate the monitoring of a moving target;
the alarm is performed by matching the image analysis module 44 and the wireless transmission module 45 in the image processing module 4 to analyze the second image, and when the second image meets the smoke alarm standard, the wireless transmission module 45 sends an alarm instruction to control the alarm device to send an alarm prompt so as to prompt a monitoring person to check the real-time situation in the detection area.
The embodiments of the present invention are preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (4)
1. The utility model provides a detection device based on image recognition, includes casing, camera, the camera fixed set up in the one end of casing, its characterized in that, the camera is including first camera, the second camera that sets up side by side, first camera with the detection area is gathered respectively to the second camera in static image and dynamic image, just first camera with the detection area of second camera has the same detection area, first camera with second camera input electricity is connected with image recognition module, image recognition module is used for discerning the moving object in the detection area of first camera, second camera, just first camera with second camera output electricity is connected with image processing module for right it discerns, memory study, fuses, stores, And (6) alarm processing.
2. The image recognition-based detection device according to claim 1, wherein the image processing module comprises: the image acquisition module is electrically connected with the first camera and the second camera to recognize and acquire images acquired by the first camera and the second camera, and is electrically connected with the image storage module, and the image acquisition module memorizes and learns the acquired images through a built-in memory algorithm;
the input end of the image fusion module is electrically connected with the image acquisition module, receives the acquired image transmitted by the image acquisition module, and fuses the dynamic image and the static image to form a first image, wherein the frame number of the first image is the same as that of the dynamic image;
the image storage module is in bidirectional electrical connection with the image fusion module, a plurality of first images are conveyed into the image storage module through the image fusion module, then conveyed to the image fusion module through the image storage module to be fused for the second time to form second images, and then the second images are input into the image storage module to be stored, a database is arranged in the image storage module, and the second images are stored in the database;
the image analysis module is electrically connected with the image storage module and is used for analyzing and comparing the second image with the data in the database;
the wireless sending module is electrically connected with the image analysis module, and when the second image meets the smoke alarm standard, the wireless sending module sends an alarm instruction.
3. An image recognition-based detection method, which adopts the image recognition-based detection device of claim 1, and is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that moving targets in detection areas of a first camera and a second camera are identified through an image identification module, the first camera collects dynamic images of the moving targets, the second camera collects static images outside the moving targets, and the collected images are conveyed to an image processing module through the first camera and the second camera;
step two: the image processing module receives the images transmitted by the first camera and the second camera, and carries out recognition, memory learning, fusion, storage and alarm processing on the images.
4. The image recognition-based detection method according to claim 3, wherein in the second step, the image processing module performs recognition, memory learning, fusion, storage and alarm processing on the image specifically:
identification: identifying the image through an image acquisition module in an image processing module, and distinguishing the grey component and the outline of a moving target in the image;
memory and learning: the recognition state of the moving target is memorized and learned through an algorithm program in the image processing module;
fusing: the image fusion module in the image processing module receives the dynamic image and the static image transmitted by the image acquisition module and fuses the dynamic image and the static image to form a first image, wherein the frame number of the first image is the same as that of the dynamic image;
and (3) storage: storing multiple groups of first images through an image storage module in the image processing module, and conveying the multiple groups of first images to the image fusion module for secondary fusion to form a second image;
and (4) alarming: the second image is analyzed through the cooperation between the image analysis module and the wireless sending module in the image processing module, and when the second image meets the smoke alarm standard, the wireless sending module sends out an alarm instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110934312.XA CN113793471A (en) | 2021-08-16 | 2021-08-16 | Detection device and method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110934312.XA CN113793471A (en) | 2021-08-16 | 2021-08-16 | Detection device and method based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113793471A true CN113793471A (en) | 2021-12-14 |
Family
ID=79181693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110934312.XA Pending CN113793471A (en) | 2021-08-16 | 2021-08-16 | Detection device and method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793471A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU3201101A (en) * | 2000-02-07 | 2001-08-14 | Intelligent Security Limited | Smoke and flame detection |
| CN103150856A (en) * | 2013-02-28 | 2013-06-12 | 江苏润仪仪表有限公司 | Fire flame video monitoring and early warning system and fire flame detection method |
| CN108201671A (en) * | 2018-01-05 | 2018-06-26 | 安徽清启***集成有限公司 | Fire control shower nozzle of self-interacting water spray volume |
| CN109493561A (en) * | 2018-11-19 | 2019-03-19 | 杭州湛川智能技术有限公司 | A kind of fire monitoring system based on image procossing |
| CN111726543A (en) * | 2020-06-30 | 2020-09-29 | 杭州萤石软件有限公司 | Method and camera for improving dynamic range of image |
-
2021
- 2021-08-16 CN CN202110934312.XA patent/CN113793471A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU3201101A (en) * | 2000-02-07 | 2001-08-14 | Intelligent Security Limited | Smoke and flame detection |
| CN103150856A (en) * | 2013-02-28 | 2013-06-12 | 江苏润仪仪表有限公司 | Fire flame video monitoring and early warning system and fire flame detection method |
| CN108201671A (en) * | 2018-01-05 | 2018-06-26 | 安徽清启***集成有限公司 | Fire control shower nozzle of self-interacting water spray volume |
| CN109493561A (en) * | 2018-11-19 | 2019-03-19 | 杭州湛川智能技术有限公司 | A kind of fire monitoring system based on image procossing |
| CN111726543A (en) * | 2020-06-30 | 2020-09-29 | 杭州萤石软件有限公司 | Method and camera for improving dynamic range of image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021253961A1 (en) | Intelligent visual perception system | |
| CN104079874B (en) | A kind of security protection integral system and method based on technology of Internet of things | |
| CN104966375B (en) | A kind of safety defense monitoring system | |
| CN112288984A (en) | Three-dimensional visual unattended substation intelligent linkage system based on video fusion | |
| CN109887221A (en) | A kind of fire disaster intelligently detection system and its control method | |
| CN210899299U (en) | Tunnel monitoring system | |
| CN101609589A (en) | Multi-frequency image fire detection system | |
| CN112184678A (en) | Image recognition method, image recognition device, computer-readable storage medium and processor | |
| CN102176270A (en) | Safety monitoring and fire alarming integrated system and method | |
| CN101458865A (en) | Fire disaster probe system and method | |
| CN206805660U (en) | Archive office's Intelligent gate inhibition monitoring device | |
| CN201259717Y (en) | Fire disaster probe system | |
| CN105607617A (en) | Security fault diagnosis system and method based on Internet of Things | |
| CN106003040A (en) | Transformer substation inspection robot system with obstacle avoidance function | |
| CN101699531A (en) | Infrared correlation identification alarm system and identification method thereof | |
| KR102233679B1 (en) | Apparatus and method for detecting invader and fire for energy storage system | |
| CN111429681A (en) | Comprehensive perimeter security system with infrared thermal image verification and method | |
| CN109544870A (en) | Alarm decision method and intelligent monitor system for intelligent monitor system | |
| CN112263803A (en) | Unmanned vehicle intelligent security system based on real-time scene inspection and automatic detection fire extinguishing and control method | |
| CN204650694U (en) | A kind of picture control equipment antitheft for base station area | |
| KR20230080522A (en) | Fire monitoring system using artificial intelligence and method thereof | |
| CN111486537B (en) | Air conditioner with security and monitoring functions | |
| CN113793471A (en) | Detection device and method based on image recognition | |
| CN115620479A (en) | Intelligent building monitoring system based on alarm linkage | |
| CN213545078U (en) | Comprehensive intelligent supervision system for transformer substation environment |
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: 20211214 |
|
| RJ01 | Rejection of invention patent application after publication |