CN112525348A - Industrial waste gas monitoring method, device and system - Google Patents
Industrial waste gas monitoring method, device and system Download PDFInfo
- Publication number
- CN112525348A CN112525348A CN201910884692.3A CN201910884692A CN112525348A CN 112525348 A CN112525348 A CN 112525348A CN 201910884692 A CN201910884692 A CN 201910884692A CN 112525348 A CN112525348 A CN 112525348A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- image
- thermal imaging
- exhaust gas
- waste gas
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 286
- 239000007789 gas Substances 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 71
- 239000002440 industrial waste Substances 0.000 title claims abstract description 45
- 238000001931 thermography Methods 0.000 claims abstract description 88
- 238000012806 monitoring device Methods 0.000 claims description 41
- 239000002912 waste gas Substances 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 15
- 238000002372 labelling Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000005286 illumination Methods 0.000 abstract description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0014—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation from gases, flames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a method, a device and a system for monitoring industrial waste gas. The monitoring method comprises the following steps: and acquiring a thermal imaging image of the current monitoring scene, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, and outputting the image monitoring result. The exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image. By the monitoring method, all-weather real-time monitoring and automatic alarming can be realized within 24 hours, and the labor cost is saved; due to the adoption of the infrared thermal imaging technology, the monitoring method is not influenced by low illumination of the environment, and the monitoring effect on the night exhaust gas stealing behavior is obviously improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of environmental protection, in particular to a method, a device and a system for monitoring industrial waste gas.
Background
Monitoring the emission of industrial waste gas is one of important works of environmental protection departments, and partial enterprises often steal the waste gas for the benefit of themselves, and the monitoring on the steal emission of the waste gas cannot be effectively realized at present due to the limitation of the prior art.
The existing non-contact industrial waste gas emission monitoring technology mainly relies on visible light camera monitoring and is identified by manual means, and due to limited manpower, the scheme has the advantages of low monitoring coverage rate, low effectiveness and higher cost. In some new schemes, the image recognition technology can be utilized to recognize smoke in the visible light image, the scheme can realize the effect of instant alarm, but under low-illumination environments such as night and the like, the visible light camera has limited effect, and all-weather monitoring for 24 hours is difficult to realize. In addition, most of similar schemes analyze and recognize the visible light images by a central server at the back end, but do not directly complete recognition by a front-end camera, and the cost is higher because the central server needs to be additionally configured.
Disclosure of Invention
The invention provides a method, a device and a system for monitoring industrial waste gas, which realize all-weather real-time monitoring and automatic alarm for 24 hours and save the labor cost.
A first aspect of the present invention provides a method for monitoring industrial waste gas, comprising:
acquiring a thermal imaging image of a current monitoring scene;
inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, wherein the exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image;
and outputting the image monitoring result.
In one possible implementation, the training process of the exhaust gas monitoring model includes:
establishing an initial waste gas monitoring model;
acquiring positive and negative image samples of thermal imaging waste gas and labeling results of the positive and negative image samples; the marking result comprises a mark for representing the exhaust emission level and the position information of the exhaust;
and training the initial waste gas monitoring model by taking the positive and negative image samples as the input of the waste gas monitoring model and taking the labeling results of the positive and negative image samples as the output of the waste gas monitoring model to obtain the waste gas monitoring model.
Optionally, the image monitoring result includes a tag value representing an exhaust emission level, the tag value includes 0-n, n is a positive integer greater than or equal to 1, 0 represents no exhaust, 1-n represents different exhaust emission levels, and the outputting the image monitoring result includes:
and outputting the label value of the current monitoring scene.
In one possible implementation, the image monitoring result further includes a two-dimensional coordinate position of the exhaust gas in the image, and the outputting the image monitoring result further includes:
and outputting the two-dimensional coordinate position of the exhaust gas in the current monitoring scene.
In one possible implementation, after outputting the image monitoring result, the method further includes:
determining the exhaust emission level in the thermal imaging image according to the image monitoring result;
and if the exhaust emission level reaches an early warning level, sending warning information, wherein the early warning level is related to pre-configured user information.
In a possible implementation manner, the sending the alarm information includes:
and sending alarm information including image information marked with the exhaust gas target frame and/or position information of the exhaust gas.
In one possible implementation, the method further includes:
acquiring timer information, wherein the timer information is used for indicating the monitoring time of the current monitoring scene;
and after the timer is overtime, sending a monitoring scene switching instruction to the controllable cloud deck, wherein the monitoring scene switching instruction is used for indicating the controllable cloud deck to rotate to the next monitoring scene according to a preset rotation angle.
In one possible implementation, after outputting the image monitoring result, the method further includes:
and sending a rotation instruction to the controllable holder, wherein the rotation instruction is used for indicating the controllable holder to automatically cruise by 360 degrees, and outputting image monitoring results of thermal imaging images of different monitoring scenes in real time.
A second aspect of the present invention provides an apparatus for monitoring industrial waste gas, comprising:
the acquisition module is used for acquiring a thermal imaging image of a current monitoring scene;
the processing module is used for inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, and the exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image;
and the processing module is used for outputting the image monitoring result.
A third aspect of the present invention provides an apparatus for monitoring industrial waste gas, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of the first aspect of the invention.
A fourth aspect of the present invention provides an industrial waste gas monitoring system, comprising: a thermal imaging detector, a monitoring device for industrial waste gas and a controllable holder according to the third aspect of the invention;
the monitoring device is respectively connected with the thermal imaging detector and the controllable holder, the thermal imaging detector and the monitoring device are arranged on the controllable holder, and the monitoring device controls the controllable holder to rotate in the horizontal or vertical direction so as to realize multi-scene monitoring.
A fifth aspect of the invention provides a computer readable storage medium having stored thereon a computer program for execution by a processor to perform the method according to any one of the first aspect of the invention.
The embodiment of the invention provides a method, a device and a system for monitoring industrial waste gas. The monitoring method comprises the following steps: and acquiring a thermal imaging image of the current monitoring scene, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, and outputting the image monitoring result. The exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image. By the monitoring method, all-weather real-time monitoring and automatic alarming can be realized within 24 hours, and the labor cost is saved; due to the adoption of the infrared thermal imaging technology, the monitoring method is not influenced by low illumination of the environment, and the monitoring effect on the night exhaust gas stealing behavior is obviously improved.
Drawings
FIG. 1 is a schematic flow chart of a method for monitoring industrial waste gas according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for monitoring industrial waste gas according to another embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a method for monitoring industrial waste gas according to still another embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating a method for monitoring industrial waste gas according to still another embodiment of the present invention;
FIG. 5 is a functional block diagram of an industrial waste gas monitoring device according to an embodiment of the present invention;
fig. 6 is a schematic hardware structure diagram of an industrial waste gas monitoring device according to an embodiment of the present invention;
fig. 7 is a schematic view of a monitoring system for industrial waste gas according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terms "comprising" and "having," and any variations thereof, in the description and claims of this invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference throughout this specification to "one embodiment" or "another embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in some embodiments" or "in this embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic flow chart of a monitoring method for industrial waste gas according to an embodiment of the present invention. The monitoring method provided by the embodiment can be executed by any device for executing the method, and the device can be an image acquisition end device, such as a thermal imaging camera, and also can be a service end, such as an industrial waste gas monitoring platform. The apparatus may be implemented by software and/or hardware.
As shown in fig. 1, the monitoring method provided in this embodiment includes:
Specifically, a thermal imaging image of the currently monitored scene sent by the thermal imaging detector is acquired.
The thermal imaging detector is a device which detects infrared radiation of a target object by using an infrared thermal imaging technology, converts the detected infrared radiation into an electric signal after accurately quantifying, and finally converts the infrared radiation of the target object into a visible image through preprocessing processes such as automatic gain control AGC processing, 3D noise reduction processing, detail enhancement processing and the like. Since any object whose temperature exceeds absolute zero will radiate infrared outwards, the thermal imaging detector can accurately image the scene.
And 102, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result.
In this embodiment, the exhaust gas monitoring model is used to distinguish whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image, and the deep learning model can be trained by using positive and negative image samples of the thermal imaging exhaust gas. Specifically, the training process of the exhaust gas monitoring model comprises the following steps:
A. and establishing an initial exhaust gas monitoring model.
B. And acquiring positive and negative image samples of the thermal imaging waste gas and labeling results of the positive and negative image samples.
The labeling result includes a mark for indicating the exhaust emission level and the position information of the exhaust.
The positive image sample refers to pictures of exhaust gas emission in various scenes, and the scenes can include factory areas, pipeline scenes, sky scenes, forest scenes and the like. The negative image sample refers to a picture without exhaust gas emission in the above-described various scenes. Optionally, an interference sample may be added, where the interference sample includes a picture of a rainy or foggy day, a picture of smoke generated by combustion, a horizontal reflective picture, a white wall surface or a building picture, and the like. The labeling work of the image sample is completed by a labeling team; or roughly labeling by using a picture identification method, and then manually correcting; the pictures can be classified, and then the classified image samples are labeled uniformly. The above noted tasks may be employed individually or in combination.
The flag indicating the exhaust emission level in the above noted labeling result may be a tag value, and the tag value may include 0 and 1, where 0 indicates no exhaust emission and 1 indicates no exhaust emission. Alternatively, the tag values may include 0-n, where n is a positive integer greater than or equal to 1, 0 representing no exhaust, and 1-n representing different exhaust emission levels. Wherein, the larger the value of n, the higher the exhaust emission level, which indicates the more serious the exhaust emission.
The mark for indicating the exhaust emission level in the above noted labeled result may also be an icon indicating the exhaust emission level. For example, a black-white-gray icon represents no exhaust emission, a gray icon represents exhaust emission and low emission concentration, and a black icon represents exhaust emission and high emission concentration; for another example, the green icon indicates no exhaust emission, the yellow icon indicates exhaust emission and low exhaust concentration, and the red icon indicates exhaust emission and high exhaust concentration.
The position information of the exhaust gas in the labeling result may be a two-dimensional coordinate position of the exhaust gas in the image, or may be a coordinate position of the exhaust gas mapped in a three-dimensional space. It will be appreciated that two thermographic images of the same monitored scene taken from different angles, in combination with the camera spatial position, can determine the three-dimensional spatial coordinate position of the exhaust.
C. The method comprises the steps of taking positive and negative image samples as input of an exhaust gas monitoring model, taking the labeling result of the positive and negative image samples as output of the exhaust gas monitoring model, and training an initial exhaust gas monitoring model to obtain the exhaust gas monitoring model.
As an example, the exhaust gas monitoring model in the embodiment of the application can be obtained by inputting positive and negative image samples into a deep learning model through a selected target classification algorithm for training. Optionally, in this embodiment, the target classification algorithm may adopt an RCNN algorithm, a Fast RCNN algorithm, or a Fast RCNN algorithm.
Performing feature extraction on the image input into the exhaust gas monitoring model by using any algorithm, predicting whether image features corresponding to different exhaust gas emission levels trained in advance exist in the feature map, and further determining a label value of the exhaust gas emission level corresponding to the image feature and position information of the exhaust gas if the corresponding image features exist; and if the corresponding image characteristics do not exist, directly outputting an exhaust emission level label value of 0.
In the present embodiment, the image monitoring result includes a tag value representing an exhaust emission level, wherein the tag value may include 0 and 1, 0 represents no exhaust emission, and 1 represents no exhaust emission. Alternatively, the tag values may include 0-n, where n is a positive integer greater than or equal to 1, 0 representing no exhaust, and 1-n representing different exhaust emission levels. Wherein, the larger the value of n, the higher the exhaust emission level, which indicates the more serious the exhaust emission.
Optionally, when industrial waste gas exists in the input thermal imaging image, the image monitoring result output by the waste gas monitoring model can also comprise a two-dimensional coordinate position of the waste gas in the image besides the label value of the waste gas emission level. The two-dimensional coordinate position of the exhaust gas in the image may be a central coordinate position of the exhaust gas target frame, or may also be a coordinate position of any vertex angle of the exhaust gas target frame, which is not limited in this embodiment.
And step 103, outputting an image monitoring result.
The embodiment of the invention provides a method for monitoring industrial waste gas, which comprises the following steps: and acquiring a thermal imaging image of the current monitoring scene, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, and outputting the image monitoring result. The exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image. By the monitoring method, all-weather real-time monitoring and automatic alarming can be realized within 24 hours, and the labor cost is saved; due to the adoption of the infrared thermal imaging technology, the monitoring method is not influenced by low illumination of the environment, and the monitoring effect on the night exhaust gas stealing behavior is obviously improved.
Fig. 2 is a schematic flow chart of a monitoring method for industrial waste gas according to another embodiment of the present invention. As shown in fig. 2, the monitoring method provided in this embodiment includes:
Step 201 and step 202 of this embodiment are the same as step 101 and step 102 of the above embodiment, and reference may be made to the above embodiment specifically, and details are not repeated here.
And step 203, outputting an image monitoring result.
And 204, determining the exhaust emission level in the thermal imaging image according to the image monitoring result, and sending alarm information if the exhaust emission level reaches an early warning level.
The monitoring device can determine the exhaust emission level in the thermal imaging image according to the label value in the image monitoring result. The label value 0 represents no exhaust and the label values 1-n represent exhaust. Generally, the larger the tag value, the higher the exhaust emission level, i.e., the greater the amount or concentration of exhaust emissions.
In this embodiment, the alert level is associated with preconfigured user information. The preconfigured user information may be understood as a tag value corresponding to an early warning level preset by a user through a client, for example, the tag value corresponding to the image monitoring result including the exhaust emission level is 0-5, and the tag value corresponding to the early warning level preconfigured by the user is 3, then if the tag value in the image monitoring result output by the model is 4, the monitoring device sends an alarm message. That is to say, when the tag value of the exhaust emission level is greater than or equal to the tag value corresponding to the pre-warning level preset by the user, the monitoring device sends alarm information. And when the tag value of the exhaust emission level is smaller than the tag value corresponding to the pre-set early warning level of the user, the monitoring device does not send alarm information.
Alternatively, the exhaust emission level may be divided into three levels. For example, label value n is set to 9, label values 1-3 are set to a low density level, label values 4-6 are set to a medium density level, and label values 7-9 are set to a high density level. The user can set the early warning level as the medium concentration level, and send alarm information when the monitoring result is the medium concentration level or the high concentration level.
In other embodiments, step 204 may further include: and determining the exhaust emission level in the thermal imaging image according to the image monitoring result, and if the tag value of the exhaust emission level of the image monitoring result is any one of 1-n, determining that industrial exhaust gas exists in the input thermal imaging image, and sending alarm information. And if the label value of the exhaust emission level of the image monitoring result is 0, determining that no industrial exhaust gas exists in the input thermal imaging image, and not sending alarm information. It can be seen that in this example the monitoring device sends an alarm message as soon as it is determined that there is industrial waste gas.
In this embodiment, sending the alarm information may include: and sending alarm information including image information marked with the exhaust gas target frame and/or position information of the exhaust gas. Wherein the position information of the exhaust gas comprises a two-dimensional coordinate position of the exhaust gas in the image, or a coordinate position of the exhaust gas in a three-dimensional space.
Optionally, the user may also configure at the client: the time period and the alarming mode of alarming, a plurality of monitoring scenes, a monitoring area under each monitoring scene and the like. For example, the user may set the alert time periods to 9:00-12:00 and 14:00-17:00 on monday through friday; the alarm mode can be a mode of sending short messages, WeChat, multimedia messages, mails and the like; the user can also select 3 monitoring scenes from the 5 monitoring scenes according to the requirement for monitoring (the multiple monitoring scenes respectively correspond to a set of monitoring equipment installed at different positions); the user can also set a specific monitoring area for each monitoring scene (i.e. a set of monitoring equipment installed at a certain position) when necessary, for example, the monitoring device only monitors the area of the controllable pan/tilt head in the range of 0-180 degrees in the horizontal direction. Correspondingly, the monitoring device can send corresponding alarm information according to the user-defined configuration of different users.
In some embodiments, sending alert information may include: and sending alarm information to the monitoring center platform, the client and the webpage end.
According to the industrial waste gas monitoring method provided by the embodiment, the thermal imaging image of the current monitoring scene is obtained, the thermal imaging image is input into the waste gas monitoring model trained in advance to obtain the image monitoring result, the image monitoring result is output, the waste gas emission level in the thermal imaging image is determined according to the image monitoring result, if the waste gas emission level reaches the early warning level, alarm information is sent, and monitoring personnel can see the alarm information through the mobile terminal or the fixed terminal. The monitoring and reporting process realizes all-weather real-time monitoring and automatic alarming for 24 hours, and saves the labor cost; due to the adoption of the infrared thermal imaging technology, the monitoring method is not influenced by low illumination of the environment, and the monitoring effect on the night exhaust gas stealing behavior is obviously improved.
Fig. 3 is a schematic flow chart illustrating a monitoring method for industrial waste gas according to still another embodiment of the present invention. As shown in fig. 3, the monitoring method provided in this embodiment includes:
And step 302, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result.
Step 301 and step 302 of this embodiment are the same as step 101 and step 102 of the above embodiment, and reference may be made to the above embodiment specifically, and details are not repeated here.
And step 303, outputting an image monitoring result.
And 304, acquiring timer information, wherein the timer information is used for indicating the monitoring time of the current monitoring scene.
And 305, after the timer is overtime, sending a monitoring scene switching instruction to the controllable holder, wherein the monitoring scene switching instruction is used for indicating the controllable holder to rotate to the next monitoring scene according to a preset rotation angle.
In this embodiment, monitoring devices and thermal imaging detector all set up on a controllable cloud platform, and 360 degrees cruises can be realized to controllable cloud platform, realize the round trip monitoring to a plurality of monitoring scenes.
In order to realize the automatic polling monitoring function, two monitoring parameters can be preset on the monitoring device: time and angle of rotation are monitored. The monitoring time refers to the staying time of the monitoring device in the same monitoring scene. The rotation angle refers to a rotation angle of the controllable holder which is controlled by the monitoring device when the monitoring scene is switched every time, and the rotation angle includes a horizontal rotation angle and/or a vertical rotation angle.
The monitoring device determines the monitoring time (namely the retention time) of the current monitoring scene by acquiring the information of the timer, and sends a monitoring scene switching instruction to the controllable holder after the timer is overtime.
According to the monitoring method for the industrial waste gas, the thermal imaging image of the monitoring scene sent by the thermal imaging detector is obtained, the thermal imaging image is input into the waste gas monitoring model trained in advance, an image monitoring result is obtained, and the image monitoring result is output. In the monitoring process, the monitoring device acquires timer information, and sends a monitoring scene switching instruction to the controllable holder after the timer is overtime, so as to instruct the controllable holder to rotate to the next monitoring scene according to a preset rotation angle. The monitoring method provided by the embodiment can realize all-weather real-time monitoring and automatic alarming for 24 hours, and saves the labor cost; due to the adoption of the infrared thermal imaging technology, the monitoring method is not influenced by low illumination of the environment, and the monitoring effect on the night exhaust gas stealing behavior is obviously improved; under the cooperation with controllable platform, monitoring devices can monitor according to predetermined monitoring time and rotation angle automatic switch scene, realizes many scenes monitoring function.
Fig. 4 is a schematic flow chart illustrating a monitoring method for industrial waste gas according to still another embodiment of the present invention. As shown in fig. 4, the monitoring method provided in this embodiment includes:
And step 402, inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result.
Step 401 and step 402 of this embodiment are the same as step 101 and step 102 of the above embodiment, and reference may be made to the above embodiment specifically, and details are not described here again.
And step 403, outputting an image monitoring result.
And step 404, sending a rotation instruction to the controllable holder, wherein the rotation instruction is used for instructing the controllable holder to perform 360-degree automatic cruise, and outputting image monitoring results of thermal imaging images of different monitoring scenes in real time.
It should be noted that step 404 in this embodiment is different from step 305 in the above embodiment, the monitoring device rotates to the next monitoring scene after staying for the preset time in each monitoring scene, but the monitoring device does not stay in each monitoring scene in this embodiment, and is monitored in real time, that is, after the monitoring device obtains the thermal imaging image of the current monitoring scene, or after obtaining the image monitoring result of the current monitoring scene, or after outputting the image monitoring result of the current monitoring scene, it is not necessary to perform a timer judgment, and directly sends a rotation instruction to the controllable pan-tilt, so as to implement 360-degree automatic cruise.
According to the monitoring method for the industrial waste gas, the thermal imaging image of the monitoring scene sent by the thermal imaging detector is obtained, the thermal imaging image is input into the waste gas monitoring model trained in advance, an image monitoring result is obtained, and the image monitoring result is output. After a thermal imaging image of the current monitoring scene is obtained, or an image monitoring result of the current monitoring scene is output, a rotation instruction is sent to the controllable holder, 360-degree automatic cruise is achieved, and the exhaust emission behavior of the whole area is automatically monitored in the cruise process.
Fig. 5 is a functional structure diagram of an industrial waste gas monitoring device according to an embodiment of the present invention. As shown in fig. 5, the monitoring apparatus 500 for industrial waste gas provided in this embodiment includes:
an obtaining module 501, configured to obtain a thermal imaging image of a current monitoring scene;
the processing module 502 is configured to input the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, where the exhaust gas monitoring model is configured to distinguish whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image;
the processing module 502 is further configured to output the image monitoring result.
The monitoring device for industrial waste gas provided by the embodiment comprises an acquisition module and a processing module. The acquisition module is used for acquiring a thermal imaging image of a current monitoring scene; the processing module is used for inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result; the processing module is also used for outputting an image monitoring result. The monitoring device can realize all-weather real-time monitoring and automatic alarming for 24 hours, and saves the labor cost; because of adopting the infrared thermal imaging technology, the device is not influenced by environmental low illumination, and the monitoring effect on the behavior of stealing and exhausting waste gas at night is obviously improved.
Optionally, the training process of the exhaust gas monitoring model includes:
establishing an initial waste gas monitoring model;
acquiring positive and negative image samples of thermal imaging waste gas and labeling results of the positive and negative image samples; the marking result comprises a mark for representing the exhaust emission level and the position information of the exhaust;
and training the initial waste gas monitoring model by taking the positive and negative image samples as the input of the waste gas monitoring model and taking the labeling results of the positive and negative image samples as the output of the waste gas monitoring model to obtain the waste gas monitoring model.
Optionally, the image monitoring result includes a tag value representing an exhaust emission level, the tag value includes 0-n, n is a positive integer greater than or equal to 1, 0 represents no exhaust, 1-n represents different exhaust emission levels, and the outputting the image monitoring result includes:
and outputting the label value of the current monitoring scene.
Optionally, the image monitoring result further includes a two-dimensional coordinate position of the exhaust gas in the image, and the processing module 502 is further configured to:
and outputting the two-dimensional coordinate position of the exhaust gas in the current monitoring scene.
Optionally, the monitoring apparatus 500 further includes: a sending module 503.
After outputting the image monitoring result, the processing module 502 is further configured to:
determining the exhaust emission level in the thermal imaging image according to the image monitoring result;
if the exhaust emission level reaches an early warning level, the sending module 503 is configured to send an alarm message, where the early warning level is related to pre-configured user information.
Optionally, the sending module 503 is specifically configured to:
and sending alarm information including image information marked with the exhaust gas target frame and/or position information of the exhaust gas.
Optionally, the obtaining module 501 is further configured to:
acquiring timer information, wherein the timer information is used for indicating the monitoring time of the current monitoring scene;
the sending module 503 is further configured to send a monitoring scene switching instruction to the controllable cloud deck after the timer is overtime, where the monitoring scene switching instruction is used to instruct the controllable cloud deck to rotate to a next monitoring scene according to a preset rotation angle.
Optionally, after outputting the image monitoring result, the sending module 503 is further configured to:
and sending a rotation instruction to the controllable holder, wherein the rotation instruction is used for indicating the controllable holder to automatically cruise by 360 degrees, and outputting image monitoring results of thermal imaging images of different monitoring scenes in real time.
The monitoring device provided in this embodiment may implement the technical solutions of the above method embodiments, and the implementation principles and technical effects thereof are similar, and are not described herein again.
Fig. 6 is a schematic hardware structure diagram of a monitoring device for industrial waste gas according to an embodiment of the present invention. As shown in fig. 6, the monitoring apparatus 600 for industrial waste gas provided in this embodiment includes:
a memory 601;
a processor 602; and
a computer program;
wherein the computer program is stored in the memory 601 and configured to be executed by the processor 602 to implement the technical solution of any one of the foregoing method embodiments, and the implementation principle and technical effect thereof are similar, and are not described herein again.
Alternatively, the memory 601 may be separate or integrated with the processor 602.
When the memory 601 is a device independent from the processor 602, the monitoring apparatus 600 further includes:
a bus 603 for connecting the memory 601 and the processor 602.
Fig. 7 is a schematic view of a monitoring system for industrial waste gas according to an embodiment of the present invention. As shown in fig. 7, the monitoring system provided in this embodiment includes:
a thermal imaging detector, a monitoring device for industrial waste gas and a controllable cloud deck in the embodiment shown in fig. 6. The monitoring device is respectively connected with the thermal imaging detector and the controllable holder, and the thermal imaging detector and the monitoring device are both arranged on the controllable holder.
The monitoring device controls the controllable holder to rotate in the horizontal or vertical direction so as to realize multi-scene monitoring.
It should be noted that the thermal imaging detector, the monitoring device and the controllable pan-tilt head can be integrated into a front-end device, such as a thermal imaging camera, to achieve the image acquisition, the image recognition of exhaust emission and the alarm function.
Optionally, the monitoring system provided in this embodiment may further include: exhaust monitoring center platform and other end devices as shown in fig. 7. When the industrial waste gas monitoring device determines that industrial waste gas emission exists in the image of the current monitoring scene, alarm information is sent to a waste gas monitoring center platform or other terminal equipment through a wireless network.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by the processor 602 to implement the steps performed by the monitoring apparatus 600 in the above method embodiments.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in the monitoring device.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (12)
1. A method for monitoring industrial waste gas, comprising:
acquiring a thermal imaging image of a current monitoring scene;
inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, wherein the exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image;
and outputting the image monitoring result.
2. The method of claim 1, wherein the training process of the exhaust gas monitoring model comprises:
establishing an initial waste gas monitoring model;
acquiring positive and negative image samples of thermal imaging waste gas and labeling results of the positive and negative image samples; the marking result comprises a mark for representing the exhaust emission level and the position information of the exhaust;
and training the initial waste gas monitoring model by taking the positive and negative image samples as the input of the waste gas monitoring model and taking the labeling results of the positive and negative image samples as the output of the waste gas monitoring model to obtain the waste gas monitoring model.
3. The method of claim 1, wherein the image monitoring result includes a tag value representing an exhaust emission level, the tag value including 0-n, n being a positive integer greater than or equal to 1, 0 representing no exhaust, 1-n representing different exhaust emission levels, the outputting the image monitoring result including:
and outputting the label value of the current monitoring scene.
4. The method of claim 3, wherein the image monitoring result further includes a two-dimensional coordinate position of the exhaust gas in the image, the outputting the image monitoring result further includes:
and outputting the two-dimensional coordinate position of the exhaust gas in the current monitoring scene.
5. The method of claim 1, wherein after outputting the image monitoring result, the method further comprises:
determining the exhaust emission level in the thermal imaging image according to the image monitoring result;
and if the exhaust emission level reaches an early warning level, sending warning information, wherein the early warning level is related to pre-configured user information.
6. The method of claim 5, wherein the sending alert information comprises:
and sending alarm information including image information marked with the exhaust gas target frame and/or position information of the exhaust gas.
7. The method of claim 1, further comprising:
acquiring timer information, wherein the timer information is used for indicating the monitoring time of the current monitoring scene;
and after the timer is overtime, sending a monitoring scene switching instruction to the controllable cloud deck, wherein the monitoring scene switching instruction is used for indicating the controllable cloud deck to rotate to the next monitoring scene according to a preset rotation angle.
8. The method of claim 1, wherein after outputting the image monitoring result, the method further comprises:
and sending a rotation instruction to the controllable holder, wherein the rotation instruction is used for indicating the controllable holder to automatically cruise by 360 degrees, and outputting image monitoring results of thermal imaging images of different monitoring scenes in real time.
9. An industrial waste gas monitoring device, comprising:
the acquisition module is used for acquiring a thermal imaging image of a current monitoring scene;
the processing module is used for inputting the thermal imaging image into a pre-trained exhaust gas monitoring model to obtain an image monitoring result, and the exhaust gas monitoring model is used for distinguishing whether exhaust gas emission exists in a current monitoring scene corresponding to the thermal imaging image;
and the processing module is used for outputting the image monitoring result.
10. An industrial waste gas monitoring device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-8.
11. An industrial waste gas monitoring system, comprising: a thermal imaging detector, the industrial waste gas monitoring device and the controllable cloud deck according to claim 10;
the monitoring device is respectively connected with the thermal imaging detector and the controllable holder, the thermal imaging detector and the monitoring device are arranged on the controllable holder, and the monitoring device controls the controllable holder to rotate in the horizontal or vertical direction so as to realize multi-scene monitoring.
12. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884692.3A CN112525348A (en) | 2019-09-19 | 2019-09-19 | Industrial waste gas monitoring method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884692.3A CN112525348A (en) | 2019-09-19 | 2019-09-19 | Industrial waste gas monitoring method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112525348A true CN112525348A (en) | 2021-03-19 |
Family
ID=74975268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910884692.3A Pending CN112525348A (en) | 2019-09-19 | 2019-09-19 | Industrial waste gas monitoring method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112525348A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920471A (en) * | 2021-10-13 | 2022-01-11 | 平安国际智慧城市科技股份有限公司 | Remote monitoring method and device for production waste, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101262490A (en) * | 2008-02-29 | 2008-09-10 | 中兴通讯股份有限公司 | Monitoring system |
| CN103197498A (en) * | 2013-03-11 | 2013-07-10 | 哈尔滨工程大学 | Panoramic vision system with synchronous shot parameter adjusting function |
| CN105203465A (en) * | 2015-09-16 | 2015-12-30 | 湖北久之洋红外系统股份有限公司 | Hyperspectral infrared imaging gas monitoring device and monitoring method thereof |
| CN106941535A (en) * | 2017-04-24 | 2017-07-11 | 华东交通大学 | A kind of method of collection orchard environmental information |
| CN107545281A (en) * | 2017-09-29 | 2018-01-05 | 浙江工商大学 | A kind of single pernicious gas infrared image classifying identification method based on deep learning |
| CN109164057A (en) * | 2018-10-12 | 2019-01-08 | 北京环境特性研究所 | The infrared multi-spectral imaging remote sense monitoring system of chemical gas, device and method |
| CN111862541A (en) * | 2020-06-28 | 2020-10-30 | 安徽旭帆信息科技有限公司 | Poisonous and harmful gas monitoring system based on infrared imaging technology |
-
2019
- 2019-09-19 CN CN201910884692.3A patent/CN112525348A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101262490A (en) * | 2008-02-29 | 2008-09-10 | 中兴通讯股份有限公司 | Monitoring system |
| CN103197498A (en) * | 2013-03-11 | 2013-07-10 | 哈尔滨工程大学 | Panoramic vision system with synchronous shot parameter adjusting function |
| CN105203465A (en) * | 2015-09-16 | 2015-12-30 | 湖北久之洋红外系统股份有限公司 | Hyperspectral infrared imaging gas monitoring device and monitoring method thereof |
| CN106941535A (en) * | 2017-04-24 | 2017-07-11 | 华东交通大学 | A kind of method of collection orchard environmental information |
| CN107545281A (en) * | 2017-09-29 | 2018-01-05 | 浙江工商大学 | A kind of single pernicious gas infrared image classifying identification method based on deep learning |
| CN109164057A (en) * | 2018-10-12 | 2019-01-08 | 北京环境特性研究所 | The infrared multi-spectral imaging remote sense monitoring system of chemical gas, device and method |
| CN111862541A (en) * | 2020-06-28 | 2020-10-30 | 安徽旭帆信息科技有限公司 | Poisonous and harmful gas monitoring system based on infrared imaging technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920471A (en) * | 2021-10-13 | 2022-01-11 | 平安国际智慧城市科技股份有限公司 | Remote monitoring method and device for production waste, computer equipment and storage medium |
| CN113920471B (en) * | 2021-10-13 | 2024-07-19 | 平安国际智慧城市科技股份有限公司 | Remote monitoring method and device for production waste, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11218628B2 (en) | Method and system for identifying light source and application thereof | |
| KR101825045B1 (en) | Alarm method and device | |
| US10956751B2 (en) | Vessel monitoring apparatus | |
| US10354386B1 (en) | Remote sensing of structure damage | |
| US20190287297A1 (en) | Three-dimensional environment modeling based on a multi-camera convolver system | |
| US12094310B2 (en) | Method and system for detecting fire and smoke | |
| CN107729850B (en) | Internet of things outdoor advertisement monitoring and broadcasting system | |
| US10887507B2 (en) | Intelligent self-powered camera | |
| KR20070028813A (en) | Method and system for monitoring forest fire | |
| EP3909424A1 (en) | Fish monitoring system and camera unit | |
| US9208555B1 (en) | Method for inspection of electrical equipment | |
| CN108734684B (en) | Image background subtraction for dynamic illumination scene | |
| CN111489342A (en) | Video-based flame detection method and system and readable storage medium | |
| CN111354024A (en) | Behavior prediction method for key target, AI server and storage medium | |
| CN113240880A (en) | Fire detection method and device, electronic equipment and storage medium | |
| US20200250945A1 (en) | Intrusion detection methods and devices | |
| Hasan et al. | An automatic fire detection and warning system under home video surveillance | |
| JPWO2018158823A1 (en) | Anomaly detection system, anomaly detection method and program | |
| CN113705332A (en) | Method and device for detecting shielding of camera of vehicle-mounted terminal, vehicle-mounted terminal and vehicle | |
| CN112525348A (en) | Industrial waste gas monitoring method, device and system | |
| CN110263619A (en) | Image processing method and device, electronic equipment and computer storage medium | |
| CN114187327A (en) | Target identification tracking method and device, computer readable medium and electronic equipment | |
| CN109191748A (en) | Campus security alarm method, device, storage medium and equipment | |
| KR102316875B1 (en) | A method for measuring fine dust concentration using a terminal having a camera and a light emitting unit, a method for sharing measured fine dust concentration information, and a server for the method | |
| CN113808117A (en) | Lamp detection method, device, equipment and storage medium |
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: 20210319 |