CN112396121B - Smoke image classification method based on neural network - Google Patents
Smoke image classification method based on neural network Download PDFInfo
- Publication number
- CN112396121B CN112396121B CN202011377912.2A CN202011377912A CN112396121B CN 112396121 B CN112396121 B CN 112396121B CN 202011377912 A CN202011377912 A CN 202011377912A CN 112396121 B CN112396121 B CN 112396121B
- Authority
- CN
- China
- Prior art keywords
- image
- smoke
- target
- smoke image
- noise
- 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.)
- Active
Links
- 239000000779 smoke Substances 0.000 title claims abstract description 340
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003062 neural network model Methods 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a smoke image classification method based on a neural network, and belongs to the technical field of image processing. The method comprises the steps of obtaining a smoke image to be classified; extracting pixel values corresponding to image points on the smoke image to be classified; processing the smoke image to be classified according to the pixel value to obtain a target smoke image; acquiring characteristic parameters corresponding to each image point on a target smoke image; constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point; acquiring reference characteristic parameters of a characteristic parameter set; determining a target feature class corresponding to the reference feature parameter through a preset neural network model; and the target feature class is used as a classification result of the smoke image to be classified, the smoke image to be classified is processed through the pixel value of the image point, the target smoke image obtained after the processing is classified, and the smoke image is classified more comprehensively, so that the accuracy of classifying the smoke image is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a smoke image classification method based on a neural network.
Background
Fire detection tasks are critical to personnel safety. Because the smoke diffusion speed is high and the sensor is not arranged at a proper position in the open environment, the traditional detection mode based on the sensor cannot accurately detect the fire smoke, and the smoke images of the fire are classified according to texture features, so that the purpose of smoke detection is achieved. However, due to the wide variety of smoke shapes, colors and textures, the classification mode adopted by the target is limited, so that the classification accuracy of smoke images is low.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a smoke image classification method based on a neural network, and aims to solve the technical problem of low accuracy of smoke image classification in the prior art.
In order to achieve the above object, the present invention provides a smoke image classification method based on a neural network, which is characterized in that the smoke image classification method based on the neural network includes:
acquiring a smoke image to be classified;
extracting pixel values corresponding to image points on the smoke image to be classified;
Processing the smoke image to be classified according to the pixel value to obtain a target smoke image;
acquiring characteristic parameters corresponding to each image point on the target smoke image;
constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point;
acquiring reference characteristic parameters of the characteristic parameter set;
determining a target feature class corresponding to the reference feature parameter through a preset neural network model;
and taking the target characteristic category as a classification result of the smoke image to be classified.
Optionally, the step of acquiring the image of smoke to be classified comprises:
acquiring an original smoke image and a preset noise sample corresponding to the original smoke image;
inputting the preset noise sample into the original smoke image to obtain a noise smoke image;
processing the noise smoke image to obtain a processed noise smoke image;
and taking the processed noise smoke image as a smoke image to be classified.
Optionally, the step of processing the noise smoke image to obtain a processed noise smoke image includes:
acquiring a gray noise smoke image corresponding to the noise smoke image;
Dividing the gray noise smoke image into areas to obtain a plurality of noise areas corresponding to the gray noise smoke image;
and filtering the noise area according to a preset two-dimensional template to obtain a processed noise smoke image.
Optionally, the step of filtering the noise area according to a preset two-dimensional template to obtain a processed noise smoke image includes:
acquiring a template center point of a preset two-dimensional template and a region center point of the noise region;
sequentially moving the preset two-dimensional templates on the noise area;
when the template center point is overlapped with the region center point, acquiring a current noise region corresponding to the region center point and a plurality of image points corresponding to the current noise region;
acquiring gray values corresponding to all the image points;
sequencing the gray values corresponding to the image points, and adjusting the gray values of the center points of the areas according to the sequencing result to obtain a target area;
and taking the image formed by the target area as a processed noise smoke image.
Optionally, the step of processing the smoke image to be classified according to the pixel value to obtain a target smoke image includes:
Detecting the pixel value according to a first preset pixel threshold, taking an image point corresponding to the pixel value larger than the first preset pixel threshold as a target image point, and taking an image point corresponding to the pixel value smaller than or equal to the first preset pixel threshold as a background image point;
and respectively adjusting the pixel value of the target image point and the pixel value of the background image point to obtain a target smoke image.
Optionally, after the step of detecting the pixel value according to the first preset pixel threshold, taking an image point corresponding to a pixel value greater than the first preset pixel threshold as a target image point and taking an image point corresponding to a pixel value less than or equal to the first preset pixel threshold as a background image point, the method further includes:
detecting the target image point;
if the target image point has a second preset pixel threshold, taking the target image point corresponding to the pixel value which is larger than the first preset pixel threshold and smaller than or equal to the second preset pixel threshold as a first target image point, and taking the target image point corresponding to the pixel value which is larger than the second preset pixel threshold as a second target image point, wherein the second preset pixel threshold is larger than the first preset pixel threshold;
Correspondingly, the step of adjusting the pixel value of the target image point and the pixel value of the background image point respectively to obtain the target smoke image comprises the following steps:
and respectively adjusting the pixel value of the first target image point, the pixel value of the second target image point and the pixel value of the background image point based on a preset function so as to obtain a target smoke image.
Optionally, the step of obtaining the reference feature parameter of the feature parameter set includes:
acquiring characteristic parameters in each characteristic parameter set, and dividing the same characteristic parameters into a group to acquire a plurality of parameter groups;
and acquiring the number of the characteristic parameters in each parameter set, and taking the characteristic parameter with the largest number in each parameter set as the reference characteristic parameter of the characteristic parameter set.
In addition, in order to achieve the above object, the present invention also proposes a smoke image classification device based on a neural network, the smoke image classification device based on a neural network comprising:
the acquisition module is used for acquiring the smoke images to be classified;
the extraction module is used for extracting pixel values corresponding to all image points on the smoke image to be classified;
the processing module is used for processing the smoke images to be classified according to the pixel values to obtain target smoke images;
The classification module is used for acquiring characteristic parameters corresponding to each image point on the target smoke image;
the classification module is further configured to construct a feature parameter set corresponding to the target smoke image according to feature parameters corresponding to the image points;
the classification module is further used for acquiring reference characteristic parameters of the characteristic parameter set;
the classification module is further used for determining a target feature class corresponding to the reference feature parameter through a preset neural network model;
the classification module is further used for taking the target feature class as a classification result of the smoke image to be classified.
In addition, in order to achieve the above object, the present invention also proposes a neural network-based smoke image classification apparatus, including: a memory, a processor, and a neural network-based smoke image classification program stored on the memory and executable on the processor, the neural network-based smoke image classification program configured to implement the steps of the neural network-based smoke image classification method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a neural network-based smoke image classification program which, when executed by a processor, implements the steps of the neural network-based smoke image classification method as described above.
The method comprises the steps of obtaining a smoke image to be classified; extracting pixel values corresponding to image points on the smoke image to be classified; processing the smoke image to be classified according to the pixel value to obtain a target smoke image; acquiring characteristic parameters corresponding to each image point on a target smoke image; constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point; acquiring reference characteristic parameters of a characteristic parameter set; determining a target feature class corresponding to the reference feature parameter through a preset neural network model; and the target feature class is used as a classification result of the smoke image to be classified, the smoke image to be classified is processed through the pixel value of the image point, the target smoke image obtained after the processing is classified, and the smoke image is classified more comprehensively, so that the accuracy of classifying the smoke image is improved.
Drawings
Fig. 1 is a schematic structural diagram of a smoke image classification device based on a neural network in a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a first embodiment of a smoke image classification method based on a neural network according to the present invention;
fig. 3 is a schematic flow chart of a second embodiment of a smoke image classification method based on a neural network according to the present invention;
FIG. 4 is a schematic diagram of noise region filtering in a neural network-based smoke image classification method of the present invention;
fig. 5 is a schematic flow chart of a third embodiment of a smoke image classification method based on a neural network according to the present invention;
fig. 6 is a block diagram of a first embodiment of a smoke image classifying device based on neural network according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a smoke image classification device based on a neural network in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the neural network-based smoke image classifying device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the neural network-based smoke image classification device, and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a neural network-based smoke image classification program may be included in the memory 1005 as one storage medium.
In the smoke image classification device based on a neural network shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the neural network-based smoke image classification apparatus of the present invention may be disposed in the neural network-based smoke image classification apparatus, which invokes the neural network-based smoke image classification program stored in the memory 1005 through the processor 1001, and executes the neural network-based smoke image classification method provided by the embodiment of the present invention.
The embodiment of the invention provides a smoke image classification method based on a neural network, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the smoke image classification method based on the neural network.
In this embodiment, the method for classifying smoke images based on the neural network includes the following steps:
step S10: and acquiring a smoke image to be classified.
It should be noted that, in this embodiment, the execution subject may be a computer, which is used for acquiring an image and processing an image, or may be another terminal device, which is not limited in this embodiment.
It should be noted that, because the structure and composition of the smoke image are complex, and the influence of the factors such as the image texture definition and the image resolution on the digitized smoke image is large, the original smoke image needs to be screened and processed, so as to obtain the smoke image with clear and prominent characteristics, in this embodiment, the smoke image to be classified is the smoke image after being screened and processed, so that the classification of the smoke image is more accurate and comprehensive, in this embodiment, the image classification is performed according to the smoke image to be classified after the whole processing instead of the image segmentation and interception.
Step S20: and extracting pixel values corresponding to all image points on the smoke image to be classified.
In this embodiment, the image is composed of a plurality of image points, and after the smoke image to be classified is acquired, the pixel values of the respective image points on the smoke image to be classified are extracted.
In a specific implementation, the pixel values may be extracted, for example, by comparing the similarity between the smoke image to be classified and the image formed by the red, green and blue channels, and determining the pixel value of each image point on the smoke image to be classified according to the similarity comparison result, for example, the similarity between the image point a on the smoke image to be classified and the image point B on the image formed by the red, green and blue channels is 90%, and the pixel value of the image point B is X, so that the pixel value of the image point a may be 90% X.
Step S30: and processing the smoke image to be classified according to the pixel value to obtain a target smoke image.
It should be noted that, the features displayed by the different pixel values of the image points on the image are different, but not all the image points on the smoke image to be classified contain effective features, so that in order to make the classification more accurate, the image points containing the effective features need to be distinguished from the image points not containing the effective features, in this embodiment, the smoke image to be classified is processed according to the pixel values of the image points, so that the features of the image points containing the effective features are more prominent, and the smoke image to be classified after the processing is the target smoke image.
Step S40: and acquiring characteristic parameters corresponding to each image point on the target smoke image.
In this embodiment, after the target smoke image is obtained, the classification result of the smoke image to be classified can be obtained by classifying the target smoke image, and in this embodiment, the classification of the smoke image to be classified is determined by obtaining the features corresponding to the image points on the target smoke image and according to the weight values corresponding to the features of the image points.
In a specific implementation, firstly, the pixel value of each image point on the target smoke image is acquired, after the pixel value of each image point is acquired, one image point is arbitrarily selected as the current image point, other image points are acquired within the preset range of the current image point, the pixel value of the current image point is compared with the pixel values of other image points, corresponding binary codes are allocated to the current image point according to the comparison result, for example, the binary codes allocated to the current image point are A if the pixel value of the current image point is larger than the pixel value of the other image points, the binary codes allocated to the current image point are B if the pixel values of the other image points are larger than the pixel value of the current image point, the binary codes allocated to the current image point are C and the like, and the specific binary code allocation conditions are set by themselves according to actual conditions, after the binary codes of the current image point are obtained, the feature parameters corresponding to the binary codes can be found from the mapping relation table, and thus the feature parameters of each image point can be obtained.
Step S50: and constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point.
In a specific implementation, the number of feature parameter selections is not less than one, and a feature parameter set can be obtained by each selection, and the number of feature parameter selections is the same, and the same feature parameters can be repeatedly selected in one selection, for example, the feature parameters selected for the first time are B, C, B, S and A, and the feature parameters selected for the second time are G, F, U, W and E, so that two feature parameter sets of X, Y can be obtained, wherein X= (B, C, B, S, A), Y= (G, F, U, W, E).
Step S60: and acquiring the reference characteristic parameters of the characteristic parameter set.
It should be noted that, in the practical application, the representative characteristic parameter is used as the characteristic parameter of the whole characteristic parameter set to perform operations such as operation and classification, in this embodiment, the reference characteristic parameter is a characteristic parameter capable of representing the whole characteristic parameter set, for example, the characteristic parameter set g= (a, B, C), the characteristic parameter C is a reference characteristic parameter of the characteristic parameter set G, and specifically, the process of obtaining the characteristic parameter and the reference characteristic parameter is specifically as follows: acquiring characteristic parameters in each characteristic parameter set, and dividing the same characteristic parameters into a group to acquire a plurality of parameter groups; acquiring the number of characteristic parameters in each parameter group, and taking the characteristic parameter with the largest number in each parameter group as Is a reference feature parameter of the feature parameter set. For example, the feature parameter set z= (a, D, E), the feature parameter set is divided into T 1 、T 2 T is as follows 3 Three groups, T 1 ＝(A，A，A)、T 2 = (D) and T 3 = (E), let T be known 1 The number of the characteristic parameters is 3, T 2 And T 3 The number of the characteristic parameters is 1, T 1 The number of characteristic parameters is the largest, so T is 1 The characteristic parameter in the characteristic parameter set Z is used as a reference characteristic parameter of the characteristic parameter set Z, namely the characteristic parameter of the characteristic parameter set Z is A.
Step S70: and determining the target feature category corresponding to the reference feature parameter through a preset neural network model.
In a specific implementation, after the reference feature parameters of each feature parameter set are obtained, the target feature types corresponding to each reference feature parameter can be determined through a preset neural network model, and the preset neural network model can adopt a forward neural network model or a generalized regression neural network model, which is not limited in this embodiment. The preset weight value corresponding to each reference feature parameter can be obtained through a preset neural network model, the preset weight value can be set according to actual conditions, the limitation is not imposed in the embodiment, the reference feature parameter is calculated according to the preset weight value, the target feature parameter can be obtained, for example, the preset weight value of the reference feature parameter O is 0.2, the preset weight value of the reference feature parameter P is 0.5, the preset weight value of the reference feature parameter Q is 0.3, the target feature parameter S=0.2O+0.5P+0.3Q can be obtained, then the target feature category corresponding to the target feature parameter S is searched from the preset mapping relation table, the preset mapping relation table can be changed according to requirements, and the limitation is not imposed in the embodiment.
Step S80: and taking the target characteristic category as a classification result of the smoke image to be classified.
It is easy to understand that the classifying essence of the image is to identify the category corresponding to the image feature, and the target feature category is the classifying result of the smoke image to be classified.
In the embodiment, a smoke image to be classified is obtained; extracting pixel values corresponding to image points on the smoke image to be classified; processing the smoke image to be classified according to the pixel value to obtain a target smoke image; acquiring characteristic parameters corresponding to each image point on a target smoke image; constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point; acquiring reference characteristic parameters of a characteristic parameter set; determining a target feature class corresponding to the reference feature parameter through a preset neural network model; and the target feature class is used as a classification result of the smoke image to be classified, the smoke image to be classified is processed through the pixel value of the image point, the target smoke image obtained after the processing is classified, and the smoke image is classified more comprehensively, so that the accuracy of classifying the smoke image is improved.
Referring to fig. 3, fig. 3 is a flowchart of a second embodiment of a smoke image classification method based on a neural network according to the present invention.
Based on the first embodiment, the step S10 in the smoke image classification method based on the neural network according to the present embodiment includes:
step S101: and acquiring an original smoke image and a preset noise sample corresponding to the original smoke image.
It should be noted that, the original smoke image is an unprocessed smoke image, the image types corresponding to different original smoke images are different, the preset noise sample corresponding to the original pathological smoke image can be determined according to the specific image type corresponding to the original smoke image, the preset noise sample can be gaussian white noise or rayleigh noise, the noise added in the embodiment is noise with known intensity, and the noise added in the embodiment provides basis for image denoising by adding the applicable noise into the original smoke image, so that the original smoke image can be denoised better.
Step S102: and inputting the preset noise sample into the original smoke image to obtain a noise smoke image.
In a specific implementation, after a preset noise smoke image corresponding to an original smoke image is obtained, a preset noise sample is input into the original smoke image, namely the preset noise sample is fused with the original smoke image, so that a noise smoke image containing the preset noise sample is obtained.
Step S103: and processing the noise smoke image to obtain a processed noise smoke image.
It will be readily appreciated that after the noisy smoke image is obtained, the image noise in the noisy smoke image needs to be removed, thereby obtaining a smoke image that does not contain image noise, i.e. a processed noisy smoke image.
In a specific implementation, the step of processing the noise smoke image to obtain a processed noise smoke image includes: acquiring a gray noise smoke image corresponding to the noise smoke image; dividing the gray noise smoke image into areas to obtain a plurality of noise areas corresponding to the gray noise smoke image; and filtering the noise area according to a preset two-dimensional template to obtain a processed noise smoke image.
The method includes that a gray noise smoke image corresponding to the noise smoke image is firstly acquired in the processing of the noise smoke image, the gray noise smoke image is obtained after gray processing is carried out on the noise smoke image, then the gray noise smoke image is subjected to region division to obtain a plurality of noise regions, the noise smoke image can be subjected to region division in an equal division mode, the noise smoke image can be subjected to region division according to random area size, the noise smoke image can be self-set according to actual conditions, the limitation is not carried out in the embodiment, and the embodiment only carries out the equal division of the noise smoke image.
In this embodiment, after obtaining a plurality of noise regions, filtering is sequentially performed on each noise region according to a preset two-dimensional template, and image noise in each noise region may be removed by filtering, so as to obtain a processed noise smoke image, where the size of the preset two-dimensional template may be the same as that of the noise region, for example, 4×4 or 7×7.
In a specific implementation, the step of filtering the noise region according to a preset two-dimensional template to obtain a processed noise smoke image includes: acquiring a template center point of a preset two-dimensional template and a region center point of the noise region; sequentially moving the preset two-dimensional templates on the noise area; when the template center point is overlapped with the region center point, acquiring a current noise region corresponding to the region center point and a plurality of image points corresponding to the current noise region; acquiring gray values corresponding to all the image points; sequencing the gray values corresponding to the image points, and adjusting the gray values of the center points of the areas according to the sequencing result to obtain a target area; and taking the image formed by the target area as a processed noise smoke image.
In a specific implementation, respectively acquiring a template center point of a preset two-dimensional template and an area center point of each noise area, sequentially moving the preset two-dimensional template on each noise area, and easily understanding that filtering the next noise area after filtering the current noise area by the preset two-dimensional template, detecting the position of the template center point in real time in the moving process of the preset two-dimensional template, stopping moving the preset two-dimensional template when detecting that the template center point is coincident with the area center of the noise area, acquiring the current noise area corresponding to the area center point at the moment and a plurality of image points corresponding to the current noise area, acquiring gray values corresponding to each image point, and sequencing the acquired gray values according to the size sequence, for the sake of convenience in understanding, taking fig. 4 as an example for explanation, as shown in fig. 4, the gray values of each image point in the current noise area are respectively 12, 33, 30, 2, 5, 6, 9, 1 and 22, after the gray values are arranged according to the size order, the median value of the gray value is obtained, the gray value of the area center point in the current noise area is adjusted from 5 to 12, and the target area can be obtained.
Step S104: and taking the processed noise smoke image as a smoke image to be classified.
In this embodiment, the processed noise smoke image does not include the input preset noise sample and the noise existing in the original smoke image, and the processed noise smoke image is the smoke image to be classified.
In this embodiment, an original smoke image and a preset noise sample corresponding to the original smoke image are obtained; inputting the preset noise sample into the original smoke image to obtain a noise smoke image; processing the noise smoke image to obtain a processed noise smoke image; the processed noise smoke image is used as a smoke image to be classified, a noise smoke image is obtained by inputting a preset noise sample into an original smoke image, and the noise smoke image is processed, so that the obtained smoke image to be classified does not contain image noise, and the classification of the smoke image is more accurate.
Referring to fig. 5, fig. 5 is a flowchart of a third embodiment of a smoke image classification method based on a neural network according to the present invention.
Based on the first embodiment or the second embodiment, a third embodiment of the smoke image classification method based on a neural network according to the present invention is proposed.
Taking the first embodiment as an example, the step S30 includes:
step S301: detecting the pixel value according to a first preset pixel threshold, taking an image point corresponding to the pixel value larger than the first preset pixel threshold as a target image point, and taking an image point corresponding to the pixel value smaller than or equal to the first preset pixel threshold as a background image point.
In this embodiment, the first preset pixel threshold may be set by itself according to the situation, the first preset pixel threshold is used as a pixel value detection criterion of the image point, an image point corresponding to a pixel value greater than the first preset pixel threshold and an image point corresponding to a pixel value less than or equal to the first preset pixel threshold may be obtained, in this example, an image point corresponding to a pixel value greater than the first preset pixel threshold is used as a target image point, an image point corresponding to a pixel value less than or equal to the first preset pixel threshold is used as a background image point, the target image point is an image point related to the effective feature, the background image point is an image point unrelated to the effective feature, and whether the effective feature is related to whether the image point includes the effective feature or not and whether the effective feature included in the image point reaches a certain amount or not may be defined by itself according to the situation.
In the actual situation, a second preset pixel threshold value exists in a part of target image points, the target image points need to be secondarily screened according to the second preset pixel threshold value, specifically, after the target image points are obtained, the target image points continue to be detected, if the second preset pixel threshold value exists in the target image points, the target image points corresponding to the pixel values which are larger than the first preset pixel threshold value and smaller than or equal to the second preset pixel threshold value are used as the first target image points, the target image points corresponding to the pixel values which are larger than the second preset pixel threshold value are used as the second target image points, the second preset pixel threshold value is larger than the first preset pixel threshold value, the first target image points and the second target image points are all image points related to effective features, and the number of the effective features in the first target image points is smaller than the number of the effective features in the second target image points.
Step S302: and respectively adjusting the pixel value of the target image point and the pixel value of the background image point to obtain a target smoke image.
In this embodiment, the pixel values of the target image point and the background image point are respectively adjusted based on a preset function, where the target image point includes a first image point and a second image point, and the preset function in this embodiment is as shown in formula 1.
Wherein H is a preset value corresponding to the pixel valueFunction X is the pixel value of the image point, T 1 For a first preset pixel threshold, T 2 The specific values of a > B > C, A, B and C can be set according to the actual situation by itself, and the target smoke image can be obtained by adjusting the pixel values of the image points according to the above formula 1.
In this embodiment, the pixel value is detected according to a first preset pixel threshold, an image point corresponding to a pixel value greater than the first preset pixel threshold is used as a target image point, an image point corresponding to a pixel value less than or equal to the first preset pixel threshold is used as a background image point, a first target image point and a second target image point are determined from the target image points according to a second preset pixel threshold, and the pixel value of the first target image point, the pixel value of the second target image point and the pixel value of the background image point are respectively adjusted based on a preset function so as to obtain a target smoke image, so that the effective feature of the target smoke image is more prominent, and the accuracy of classifying the smoke image based on the neural network is improved.
Referring to fig. 6, fig. 6 is a block diagram showing the construction of a first embodiment of a neural network-based smoke image classifying apparatus according to the present invention.
As shown in fig. 6, a smoke image classifying device based on a neural network according to an embodiment of the present invention includes:
an acquisition module 10 for acquiring an image of smoke to be classified.
It should be noted that, because the structure and composition of the smoke image are complex, and the influence of the factors such as the image texture definition and the image resolution on the digitized smoke image is large, the original smoke image needs to be screened and processed, so as to obtain the smoke image with clear and prominent characteristics, in this embodiment, the smoke image to be classified is the smoke image after being screened and processed, so that the classification of the smoke image is more accurate and comprehensive, in this embodiment, the image classification is performed according to the smoke image to be classified after the whole processing instead of the image segmentation and interception.
And the extracting module 20 is used for extracting pixel values corresponding to each image point on the smoke image to be classified.
In this embodiment, the image is composed of a plurality of image points, and after the smoke image to be classified is acquired, the pixel values of the respective image points on the smoke image to be classified are extracted.
In a specific implementation, the pixel values may be extracted, for example, by comparing the similarity between the smoke image to be classified and the image formed by the red, green and blue channels, and determining the pixel value of each image point on the smoke image to be classified according to the similarity comparison result, for example, the similarity between the image point a on the smoke image to be classified and the image point B on the image formed by the red, green and blue channels is 90%, and the pixel value of the image point B is X, so that the pixel value of the image point a may be 90% X.
And the processing module 30 is configured to process the smoke image to be classified according to the pixel value, so as to obtain a target smoke image.
It should be noted that, the features displayed by the different pixel values of the image points on the image are different, but not all the image points on the smoke image to be classified contain effective features, so that in order to make the classification more accurate, the image points containing the effective features need to be distinguished from the image points not containing the effective features, in this embodiment, the smoke image to be classified is processed according to the pixel values of the image points, so that the features of the image points containing the effective features are more prominent, and the smoke image to be classified after the processing is the target smoke image.
The classifying module 40 is configured to obtain feature parameters corresponding to each image point on the target smoke image.
In this embodiment, after the target smoke image is obtained, the classification result of the smoke image to be classified can be obtained by classifying the target smoke image, and in this embodiment, the classification of the smoke image to be classified is determined by obtaining the features corresponding to the image points on the target smoke image and according to the weight values corresponding to the features of the image points.
In a specific implementation, firstly, the pixel value of each image point on the target smoke image is acquired, after the pixel value of each image point is acquired, one image point is arbitrarily selected as the current image point, other image points are acquired within the preset range of the current image point, the pixel value of the current image point is compared with the pixel values of other image points, corresponding binary codes are allocated to the current image point according to the comparison result, for example, the binary codes allocated to the current image point are A if the pixel value of the current image point is larger than the pixel value of the other image points, the binary codes allocated to the current image point are B if the pixel values of the other image points are larger than the pixel value of the current image point, the binary codes allocated to the current image point are C and the like, and the specific binary code allocation conditions are set by themselves according to actual conditions, after the binary codes of the current image point are obtained, the feature parameters corresponding to the binary codes can be found from the mapping relation table, and thus the feature parameters of each image point can be obtained.
The classification module 40 is further configured to construct a feature parameter set corresponding to the target smoke image according to the feature parameters corresponding to the image points.
In a specific implementation, the number of feature parameter selections is not less than one, and a feature parameter set can be obtained by each selection, and the number of feature parameter selections is the same, and the same feature parameters can be repeatedly selected in one selection, for example, the feature parameters selected for the first time are B, C, B, S and A, and the feature parameters selected for the second time are G, F, U, W and E, so that two feature parameter sets of X, Y can be obtained, wherein X= (B, C, B, S, A), Y= (G, F, U, W, E).
The classification module 40 is further configured to obtain a reference feature parameter of the feature parameter set.
It should be noted that, the feature parameter set has a plurality of different feature parameters,in practical application, the representative characteristic parameter is used as the characteristic parameter of the whole characteristic parameter set to perform operations such as operation and classification, in this embodiment, the reference characteristic parameter is a characteristic parameter capable of representing the whole characteristic parameter set, for example, a characteristic parameter set g= (a, B, C), and the characteristic parameter C is a reference characteristic parameter of the characteristic parameter set G, specifically, the process of obtaining the characteristic parameter and the reference characteristic parameter is as follows: acquiring characteristic parameters in each characteristic parameter set, and dividing the same characteristic parameters into a group to acquire a plurality of parameter groups; and acquiring the number of the characteristic parameters in each parameter set, and taking the characteristic parameter with the largest number in each parameter set as the reference characteristic parameter of the characteristic parameter set. For example, the feature parameter set z= (a, D, E), the feature parameter set is divided into T 1 、T 2 T is as follows 3 Three groups, T 1 ＝(A，A，A)、T 2 = (D) and T 3 = (E), let T be known 1 The number of the characteristic parameters is 3, T 2 And T 3 The number of the characteristic parameters is 1, T 1 The number of characteristic parameters is the largest, so T is 1 The characteristic parameter in the characteristic parameter set Z is used as a reference characteristic parameter of the characteristic parameter set Z, namely the characteristic parameter of the characteristic parameter set Z is A.
The classification module 40 is further configured to determine a target feature class corresponding to the reference feature parameter through a preset neural network model.
In a specific implementation, after the reference feature parameters of each feature parameter set are obtained, the target feature types corresponding to each reference feature parameter can be determined through a preset neural network model, and the preset neural network model can adopt a forward neural network model or a generalized regression neural network model, which is not limited in this embodiment. The preset weight value corresponding to each reference feature parameter can be obtained through a preset neural network model, the preset weight value can be set according to actual conditions, the limitation is not imposed in the embodiment, the reference feature parameter is calculated according to the preset weight value, the target feature parameter can be obtained, for example, the preset weight value of the reference feature parameter O is 0.2, the preset weight value of the reference feature parameter P is 0.5, the preset weight value of the reference feature parameter Q is 0.3, the target feature parameter S=0.2O+0.5P+0.3Q can be obtained, then the target feature category corresponding to the target feature parameter S is searched from the preset mapping relation table, the preset mapping relation table can be changed according to requirements, and the limitation is not imposed in the embodiment.
The classification module 40 is further configured to take the target feature class as a classification result of the smoke image to be classified.
It is easy to understand that the classifying essence of the image is to identify the category corresponding to the image feature, and the target feature category is the classifying result of the smoke image to be classified.
In the embodiment, a smoke image to be classified is obtained; extracting pixel values corresponding to image points on the smoke image to be classified; processing the smoke image to be classified according to the pixel value to obtain a target smoke image; acquiring characteristic parameters corresponding to each image point on a target smoke image; constructing a characteristic parameter set corresponding to the target smoke image according to the characteristic parameters corresponding to each image point; acquiring reference characteristic parameters of a characteristic parameter set; determining a target feature class corresponding to the reference feature parameter through a preset neural network model; and the target feature class is used as a classification result of the smoke image to be classified, the smoke image to be classified is processed through the pixel value of the image point, the target smoke image obtained after the processing is classified, and the smoke image is classified more comprehensively, so that the accuracy of classifying the smoke image is improved.
In an embodiment, the neural network-based smoke image classification further includes a denoising module, configured to obtain an original smoke image and a preset noise sample corresponding to the original smoke image; inputting the preset noise sample into the original smoke image to obtain a noise smoke image; processing the noise smoke image to obtain a processed noise smoke image; and taking the processed noise smoke image as a smoke image to be classified.
In an embodiment, the denoising module is further configured to obtain a gray noise smoke image corresponding to the noise smoke image; dividing the gray noise smoke image into areas to obtain a plurality of noise areas corresponding to the gray noise smoke image; and filtering the noise area according to a preset two-dimensional template to obtain a processed noise smoke image.
In an embodiment, the denoising module is further configured to obtain a template center point of a preset two-dimensional template and a region center point of the noise region; sequentially moving the preset two-dimensional templates on the noise area; when the template center point is overlapped with the region center point, acquiring a current noise region corresponding to the region center point and a plurality of image points corresponding to the current noise region; acquiring gray values corresponding to all the image points; sequencing the gray values corresponding to the image points, and adjusting the gray values of the center points of the areas according to the sequencing result to obtain a target area; and taking the image formed by the target area as a processed noise smoke image.
In an embodiment, the processing module 30 is further configured to detect the pixel value according to a first preset pixel threshold, take an image point corresponding to a pixel value greater than the first preset pixel threshold as a target image point, and take an image point corresponding to a pixel value less than or equal to the first preset pixel threshold as a background image point; and respectively adjusting the pixel value of the target image point and the pixel value of the background image point to obtain a target smoke image.
In an embodiment, the processing module 30 is further configured to detect the target image point; if the target image point has a second preset pixel threshold, taking the target image point corresponding to the pixel value which is larger than the first preset pixel threshold and smaller than or equal to the second preset pixel threshold as a first target image point, and taking the target image point corresponding to the pixel value which is larger than the second preset pixel threshold as a second target image point, wherein the second preset pixel threshold is larger than the first preset pixel threshold; and respectively adjusting the pixel value of the first target image point, the pixel value of the second target image point and the pixel value of the background image point based on a preset function so as to obtain a target smoke image.
In an embodiment, the classification module 40 is further configured to obtain feature parameters in each feature parameter set, and divide the same feature parameters into a group to obtain a plurality of parameter groups; and acquiring the number of the characteristic parameters in each parameter set, and taking the characteristic parameter with the largest number in each parameter set as the reference characteristic parameter of the characteristic parameter set.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the smoke image classification method based on the neural network provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. The smoke image classification method based on the neural network is characterized by comprising the following steps of:
acquiring a smoke image to be classified;
extracting pixel values corresponding to image points on the smoke image to be classified;
processing the smoke image to be classified according to the pixel value to obtain a target smoke image;
acquiring characteristic parameters corresponding to each image point on the target smoke image, wherein the acquiring the characteristic parameters corresponding to each image point on the target smoke image comprises: acquiring pixel values of all image points on the target smoke image, after acquiring the pixel values of all the image points, arbitrarily selecting one image point as a current image point, acquiring other image points in a preset range of the current image point, comparing the pixel values of the current image point with the pixel values of other image points, distributing corresponding binary codes for the current image point according to a comparison result, and searching feature parameters corresponding to the binary codes from a mapping relation table;
constructing a feature parameter set corresponding to the target smoke image according to the feature parameters corresponding to the image points, wherein the constructing the feature parameter set corresponding to the target smoke image according to the feature parameters corresponding to the image points comprises: setting the selection times and the selection quantity of the characteristic parameters corresponding to each image point, and carrying out random selection on the characteristic parameters of the image points for a plurality of times according to the selection times and the selection quantity to obtain a characteristic parameter set corresponding to the target smoke image;
Acquiring reference characteristic parameters of the characteristic parameter set, wherein the acquiring the reference characteristic parameters of the characteristic parameter set comprises acquiring characteristic parameters of each characteristic parameter set, and dividing the same characteristic parameters into a group to acquire a plurality of parameter groups; acquiring the number of the characteristic parameters in each parameter set, and taking the characteristic parameter with the largest number in each parameter set as the reference characteristic parameter of the characteristic parameter set;
determining a target feature class corresponding to the reference feature parameter through a preset neural network model;
and taking the target characteristic category as a classification result of the smoke image to be classified.
2. The neural network-based smoke image classification method of claim 1, wherein the step of acquiring the smoke image to be classified comprises:
acquiring an original smoke image and a preset noise sample corresponding to the original smoke image;
inputting the preset noise sample into the original smoke image to obtain a noise smoke image;
processing the noise smoke image to obtain a processed noise smoke image;
and taking the processed noise smoke image as a smoke image to be classified.
3. The neural network-based smoke image classification method of claim 2, wherein the step of processing the noise smoke image to obtain a processed noise smoke image comprises:
acquiring a gray noise smoke image corresponding to the noise smoke image;
dividing the gray noise smoke image into areas to obtain a plurality of noise areas corresponding to the gray noise smoke image;
and filtering the noise area according to a preset two-dimensional template to obtain a processed noise smoke image.
4. A smoke image classifying method based on a neural network as claimed in claim 3, wherein said step of filtering said noise region according to a preset two-dimensional template to obtain a processed noise smoke image comprises:
acquiring a template center point of a preset two-dimensional template and a region center point of the noise region;
sequentially moving the preset two-dimensional templates on the noise area;
when the template center point is overlapped with the region center point, acquiring a current noise region corresponding to the region center point and a plurality of image points corresponding to the current noise region;
Acquiring gray values corresponding to all the image points;
sequencing the gray values corresponding to the image points, and adjusting the gray values of the center points of the areas according to the sequencing result to obtain a target area;
and taking the image formed by the target area as a processed noise smoke image.
5. The method for classifying a smoke image based on a neural network according to any one of claims 1 to 4, wherein the step of processing the smoke image to be classified according to the pixel values to obtain a target smoke image comprises:
detecting the pixel value according to a first preset pixel threshold, taking an image point corresponding to the pixel value larger than the first preset pixel threshold as a target image point, and taking an image point corresponding to the pixel value smaller than or equal to the first preset pixel threshold as a background image point;
and respectively adjusting the pixel value of the target image point and the pixel value of the background image point to obtain a target smoke image.
6. The smoke image classification method according to claim 5, wherein the step of detecting the pixel value according to a first preset pixel threshold, taking an image point corresponding to a pixel value greater than the first preset pixel threshold as a target image point, and taking an image point corresponding to a pixel value less than or equal to the first preset pixel threshold as a background image point further comprises:
Detecting the target image point;
if the target image point has a second preset pixel threshold, taking the target image point corresponding to the pixel value which is larger than the first preset pixel threshold and smaller than or equal to the second preset pixel threshold as a first target image point, and taking the target image point corresponding to the pixel value which is larger than the second preset pixel threshold as a second target image point, wherein the second preset pixel threshold is larger than the first preset pixel threshold;
correspondingly, the step of adjusting the pixel value of the target image point and the pixel value of the background image point respectively to obtain the target smoke image comprises the following steps:
and respectively adjusting the pixel value of the first target image point, the pixel value of the second target image point and the pixel value of the background image point based on a preset function so as to obtain a target smoke image.
7. A neural network-based smoke image classification device, characterized in that the neural network-based smoke image classification device comprises:
the acquisition module is used for acquiring the smoke images to be classified;
the extraction module is used for extracting pixel values corresponding to all image points on the smoke image to be classified;
The processing module is used for processing the smoke images to be classified according to the pixel values to obtain target smoke images;
the classification module is configured to obtain feature parameters corresponding to each image point on the target smoke image, where the obtaining the feature parameters corresponding to each image point on the target smoke image includes: acquiring pixel values of all image points on the target smoke image, after acquiring the pixel values of all the image points, arbitrarily selecting one image point as a current image point, acquiring other image points in a preset range of the current image point, comparing the pixel values of the current image point with the pixel values of other image points, distributing corresponding binary codes for the current image point according to a comparison result, and searching feature parameters corresponding to the binary codes from a mapping relation table;
the classification module is further configured to construct a feature parameter set corresponding to the target smoke image according to the feature parameters corresponding to the image points, where the constructing the feature parameter set corresponding to the target smoke image according to the feature parameters corresponding to the image points includes: setting the selection times and the selection quantity of the characteristic parameters corresponding to each image point, and carrying out random selection on the characteristic parameters of the image points for a plurality of times according to the selection times and the selection quantity to obtain a characteristic parameter set corresponding to the target smoke image;
The classification module is further configured to obtain reference feature parameters of the feature parameter set, where the obtaining the reference feature parameters of the feature parameter set includes obtaining feature parameters in each feature parameter set, and dividing the same feature parameters into a group to obtain a plurality of parameter sets; acquiring the number of the characteristic parameters in each parameter set, and taking the characteristic parameter with the largest number in each parameter set as the reference characteristic parameter of the characteristic parameter set;
the classification module is further used for determining a target feature class corresponding to the reference feature parameter through a preset neural network model;
the classification module is further used for taking the target feature class as a classification result of the smoke image to be classified.
8. The neural network-based smoke image classification device of claim 7, further comprising: a denoising module;
the denoising module is used for acquiring an original smoke image and a preset noise sample corresponding to the original smoke image;
the denoising module is further used for inputting the preset noise sample into the original smoke image to obtain a noise smoke image;
The denoising module is also used for processing the noise smoke image to obtain a processed noise smoke image;
the denoising module is further used for taking the processed noise smoke image as a smoke image to be classified.
9. A neural network-based smoke image classification device, the neural network-based smoke image classification device comprising: a memory, a processor and a neural network based smoke image classification program stored on the memory and executable on the processor, the neural network based smoke image classification program configured to implement the steps of the neural network based smoke image classification method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377912.2A CN112396121B (en) | 2020-11-30 | 2020-11-30 | Smoke image classification method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377912.2A CN112396121B (en) | 2020-11-30 | 2020-11-30 | Smoke image classification method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112396121A CN112396121A (en) | 2021-02-23 |
| CN112396121B true CN112396121B (en) | 2024-02-02 |
Family
ID=74605675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011377912.2A Active CN112396121B (en) | 2020-11-30 | 2020-11-30 | Smoke image classification method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396121B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
| CN104050478A (en) * | 2014-07-09 | 2014-09-17 | 湖南大学 | Smog detection method and system |
| CN105225235A (en) * | 2015-09-18 | 2016-01-06 | 北京航空航天大学 | A kind of video flame detecting method based on multispectral characteristic |
| CN105608443A (en) * | 2016-01-22 | 2016-05-25 | 合肥工业大学 | Multi-feature description and local decision weighting face identification method |
| JP2016110263A (en) * | 2014-12-03 | 2016-06-20 | 能美防災株式会社 | Smoke detection device and smoke detection method |
| CN106952438A (en) * | 2017-04-19 | 2017-07-14 | 天津安平易视智能影像科技有限公司 | A kind of fire alarm method based on video image |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN109165577A (en) * | 2018-08-07 | 2019-01-08 | 东北大学 | A kind of early stage forest fire detection method based on video image |
| CN109191495A (en) * | 2018-07-17 | 2019-01-11 | 东南大学 | Black smoke vehicle detection method based on self-organizing background subtraction model and multiple features fusion |
| CN109711345A (en) * | 2018-12-27 | 2019-05-03 | 南京林业大学 | A kind of flame image recognition methods, device and its storage medium |
| CN109886227A (en) * | 2019-02-27 | 2019-06-14 | 哈尔滨工业大学 | Inside fire video frequency identifying method based on multichannel convolutive neural network |
| CN110033040A (en) * | 2019-04-12 | 2019-07-19 | 华南师范大学 | A kind of flame identification method, system, medium and equipment |
-
2020
- 2020-11-30 CN CN202011377912.2A patent/CN112396121B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
| CN104050478A (en) * | 2014-07-09 | 2014-09-17 | 湖南大学 | Smog detection method and system |
| JP2016110263A (en) * | 2014-12-03 | 2016-06-20 | 能美防災株式会社 | Smoke detection device and smoke detection method |
| CN105225235A (en) * | 2015-09-18 | 2016-01-06 | 北京航空航天大学 | A kind of video flame detecting method based on multispectral characteristic |
| CN105608443A (en) * | 2016-01-22 | 2016-05-25 | 合肥工业大学 | Multi-feature description and local decision weighting face identification method |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN106952438A (en) * | 2017-04-19 | 2017-07-14 | 天津安平易视智能影像科技有限公司 | A kind of fire alarm method based on video image |
| CN109191495A (en) * | 2018-07-17 | 2019-01-11 | 东南大学 | Black smoke vehicle detection method based on self-organizing background subtraction model and multiple features fusion |
| CN109165577A (en) * | 2018-08-07 | 2019-01-08 | 东北大学 | A kind of early stage forest fire detection method based on video image |
| CN109711345A (en) * | 2018-12-27 | 2019-05-03 | 南京林业大学 | A kind of flame image recognition methods, device and its storage medium |
| CN109886227A (en) * | 2019-02-27 | 2019-06-14 | 哈尔滨工业大学 | Inside fire video frequency identifying method based on multichannel convolutive neural network |
| CN110033040A (en) * | 2019-04-12 | 2019-07-19 | 华南师范大学 | A kind of flame identification method, system, medium and equipment |
Non-Patent Citations (3)
| Title |
|---|
| Forest Fire Smoke Detection Using Back-Propagation Neural Network Based on MODIS Data;Xiaolian Li等;《remote sensing》;4473-4498 * |
| 基于曲波域烟雾特征提取方法研究;唐田田;《中国优秀硕士学位论文全文数据库 信息科技辑》(第02期);I138-1192 * |
| 基于视频的火灾烟雾检测;高云玲;《中国优秀硕士学位论文全文数据库 信息科技辑》(第04期);I138-847 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112396121A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826632B (en) | Image change detection method, device, equipment and computer readable storage medium | |
| CN108579094B (en) | User interface detection method, related device, system and storage medium | |
| CN108229232B (en) | Method and device for scanning two-dimensional codes in batch | |
| CN113269046B (en) | High-altitude falling object identification method and system | |
| CN110570442A (en) | Contour detection method under complex background, terminal device and storage medium | |
| CN111079730A (en) | Method for determining area of sample image in interface image and electronic equipment | |
| CN111523490A (en) | Mask wearing detection method, device, equipment and readable storage medium | |
| CN111784665A (en) | OCT image quality assessment method, system and device based on Fourier transform | |
| CN111553241A (en) | Method, device and equipment for rejecting mismatching points of palm print and storage medium | |
| CN112839047B (en) | Asset vulnerability scanning method, device, equipment and medium on cloud platform | |
| CN112396121B (en) | Smoke image classification method based on neural network | |
| CN110874732A (en) | Scanned payment method and device based on mobile payment equipment | |
| CN113269752A (en) | Image detection method, device terminal equipment and storage medium | |
| JP4967045B2 (en) | Background discriminating apparatus, method and program | |
| CN111639523A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| CN116246161A (en) | Method and device for identifying target fine type of remote sensing image under guidance of domain knowledge | |
| CN109670514B (en) | Method, device, equipment and storage medium for identifying pore and skeleton of digital core | |
| CN114266643A (en) | Enterprise mining method, device, equipment and storage medium based on fusion algorithm | |
| CN109543565B (en) | Quantity determination method and device | |
| JP2018005505A (en) | Image recognition parameter setting device, image recognition parameter setting method and image recognition parameter setting program | |
| CN114202665A (en) | Image similarity determining method and device, equipment and storage medium | |
| CN111563181A (en) | Digital image file query method and device and readable storage medium | |
| CN111353503B (en) | Method and device for identifying functional area in user interface image | |
| CN111144244B (en) | Furniture wood category identification method and device | |
| CN114463243A (en) | Image detection method, device, storage medium and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |