CN113869164A - Smoke detection method based on deep learning - Google Patents
Smoke detection method based on deep learning Download PDFInfo
- Publication number
- CN113869164A CN113869164A CN202111100923.0A CN202111100923A CN113869164A CN 113869164 A CN113869164 A CN 113869164A CN 202111100923 A CN202111100923 A CN 202111100923A CN 113869164 A CN113869164 A CN 113869164A
- Authority
- CN
- China
- Prior art keywords
- smoke
- image
- deep learning
- scene
- detection method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000779 smoke Substances 0.000 title claims abstract description 88
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000013135 deep learning Methods 0.000 title claims abstract description 19
- 238000002474 experimental method Methods 0.000 claims abstract description 11
- 230000004044 response Effects 0.000 claims abstract description 11
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 10
- 235000019504 cigarettes Nutrition 0.000 claims description 6
- 241000208125 Nicotiana Species 0.000 claims description 3
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Images
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention discloses a smoke detection method based on deep learning, which comprises the following steps: (1) collecting an original image dataset; (2) preprocessing the image; (3) inputting the image into a convolutional neural network model for training; (4) applying the model in an actual scene to detect smoke; (5) and outputting a detection result, and storing the detected smoke image. The invention can effectively identify different types of smoke generated in a large scene, reduce the false alarm rate caused by non-smoke objects in the scene, and effectively improve the smoke detection rate and the real-time response rate in the scene by combining the actual scene for experiment.
Description
Technical Field
The invention relates to smoke detection, in particular to a smoke detection method based on deep learning.
Background
Once a fire occurs, serious life and property losses are brought to the society. The smoke is used as the early-stage sign of the fire, and the smoke is timely, effectively and accurately detected, so that the important significance is achieved for fire prevention and disaster relief. At present, most of indoor and outdoor smoke particles are detected and early-warned by adopting a sensor, and due to the diffusibility of smoke, the smoke is diffused when the smoke is detected, so that the real-time detection and early warning cannot be carried out. The smoke detection is mainly completed by timely and accurately detecting smoke in the first time when the smoke is generated, positioning the smoke to the position, responding in time and sending out early warning, and avoiding the occurrence of fire and reducing loss. From the detection of smoke by a traditional sensor to the input based on images and videos, each frame of image is analyzed, and then the analysis of smoke characteristics is carried out on the images or videos by the existing deep learning-based method, so that the efficiency and the accuracy of smoke detection are improved step by step. However, in an outdoor scene, due to the limited shooting angle, the smoke detection still has false alarm omission and fails to detect and respond in time.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a smoke detection method based on deep learning, so that the smoke detection rate is improved, and the false alarm rate is reduced.
The technical scheme is as follows: the invention relates to a smoke detection method based on deep learning, which comprises the following steps:
(1) collecting an original image dataset;
(2) preprocessing the image;
(3) inputting the image into a convolutional neural network model for training;
(4) applying the model in an actual scene to detect smoke;
(5) and outputting a detection result, and storing the detected smoke image.
The step (1) is specifically as follows:
(1.1) carrying out a cigarette lighting experiment by using the tobacco flakes under a scene to be detected;
(1.2) acquiring a smoke image when smoke is generated in a scene and a non-smoke image in the scene;
(1.3) the smoke and non-smoke images are saved in bmp format.
The step (2) is specifically as follows:
(2.1) converting the image format from bmp to png;
and (2.2) classifying and preprocessing the image, and changing the size and the resolution of the image to be in accordance with the input requirements of the neural network model.
The step (3) is specifically as follows:
(3.1) constructing a convolutional neural network model;
(3.2) inputting the image into a convolutional neural network to train the model, adjusting the structure and parameters of the model, selecting a proper loss function to enable the model to identify various smoke features, identifying different types of smoke features under the condition of influence of various factors such as different weather and environments, distinguishing non-smoke objects in the background environment, and well distinguishing the smoke image from the non-smoke image.
The step (4) is specifically as follows:
(4.1) combining the trained model with real-time video monitoring to identify and detect smoke generated in a scene;
(4.2) carrying out a cigarette lighting experiment, and detecting whether a response is generated in real time when smoke is generated.
(4.3) after a response is generated, positioning the image to the position, storing the smoke and non-smoke images to a specified folder, and checking and maintaining the image regularly; if no response exists, the model is adjusted to continue the experiment.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a deep learning based smoke detection method as described above.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a deep learning based smoke detection method as described above when executing the computer program.
Has the advantages that: compared with the prior art, the invention has the following advantages: the method can effectively identify different types of smoke generated in a large scene, reduce the false alarm rate caused by non-smoke objects in the scene, and effectively improve the smoke detection rate and the real-time response rate in the scene by combining the actual scene for experiment.
Drawings
FIG. 1 is a flow chart of the steps of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
Example 1:
as shown in fig. 1, a smoke detection method based on deep learning includes the following steps:
(1) collecting an original image dataset;
(2) preprocessing the image;
(3) inputting the image into a convolutional neural network model for training;
(4) applying the model in an actual scene to detect smoke;
(5) and outputting a detection result, and storing the detected smoke image.
The step (1) is specifically as follows:
(1.1) carrying out a cigarette lighting experiment by using the tobacco flakes under a scene to be detected;
(1.2) acquiring a smoke image when smoke is generated in a scene and a non-smoke image in the scene;
(1.3) the smoke and non-smoke images are saved in bmp format.
The step (2) is specifically as follows:
(2.1) converting the image format from bmp to png;
and (2.2) classifying and preprocessing the image, and changing the size and the resolution of the image to be in accordance with the input requirements of the neural network model.
The step (3) is specifically as follows:
(3.1) constructing a convolutional neural network model;
(3.2) inputting the image into a convolutional neural network to train the model, adjusting the structure and parameters of the model, selecting a proper loss function to enable the model to identify various smoke features, identifying different types of smoke features under the condition of influence of various factors such as different weather and environments, distinguishing non-smoke objects in the background environment, and well distinguishing the smoke image from the non-smoke image.
The step (4) is specifically as follows:
(4.1) combining the trained model with real-time video monitoring to identify and detect smoke generated in a scene;
(4.2) carrying out a cigarette lighting experiment, and detecting whether a response is generated in real time when smoke is generated.
(4.3) after a response is generated, positioning the image to the position, storing the smoke and non-smoke images to a specified folder, and checking and maintaining the image regularly; if no response exists, the model is adjusted to continue the experiment.
Example 2:
a computer storage medium having stored thereon a computer program which, when executed by a processor, implements a deep learning based smoke detection method as described above.
Example 3:
a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a deep learning based smoke detection method as described above when executing the computer program.
Claims (7)
1. A smoke detection method based on deep learning is characterized by comprising the following steps:
(1) collecting an original image dataset;
(2) preprocessing the image;
(3) inputting the image into a convolutional neural network model for training;
(4) applying the model in an actual scene to detect smoke;
(5) and outputting a detection result, and storing the detected smoke image.
2. The deep learning-based smoke detection method according to claim 1, wherein the step (1) is specifically as follows:
(1.1) carrying out a cigarette lighting experiment by using the tobacco flakes under a scene to be detected;
(1.2) acquiring a smoke image when smoke is generated in a scene and a non-smoke image in the scene;
(1.3) the smoke and non-smoke images are saved in bmp format.
3. The deep learning based smoke detection method according to claim 1, wherein the step (2) is specifically as follows:
(2.1) converting the image format from bmp to png;
and (2.2) classifying and preprocessing the image, and changing the size and the resolution of the image to be in accordance with the input requirements of the neural network model.
4. The deep learning based smoke detection method according to claim 1, wherein the step (3) is specifically as follows:
(3.1) constructing a convolutional neural network model;
(3.2) inputting the image into a convolutional neural network for model training, adjusting the structure and parameters of the model, selecting a proper loss function to enable the model to identify various smoke characteristics, and well distinguishing the smoke image from the non-smoke image.
5. The deep learning based smoke detection method according to claim 1, wherein the step (4) is specifically as follows:
(4.1) combining the trained model with real-time video monitoring to identify and detect smoke generated in a scene;
(4.2) carrying out a cigarette lighting experiment, and detecting whether a real-time detection response exists or not when smoke is generated;
(4.3) after a response is generated, positioning the image to the position, storing the smoke and non-smoke images to a specified folder, and checking and maintaining the image regularly; if no response exists, the model is adjusted to continue the experiment.
6. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a deep learning based smoke detection method according to any of claims 1-5.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements a deep learning based smoke detection method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111100923.0A CN113869164A (en) | 2021-09-18 | 2021-09-18 | Smoke detection method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111100923.0A CN113869164A (en) | 2021-09-18 | 2021-09-18 | Smoke detection method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113869164A true CN113869164A (en) | 2021-12-31 |
Family
ID=78992886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111100923.0A Pending CN113869164A (en) | 2021-09-18 | 2021-09-18 | Smoke detection method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869164A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598891A (en) * | 2018-12-24 | 2019-04-09 | 中南民族大学 | A kind of method and system for realizing Smoke Detection using deep learning disaggregated model |
| CN110991242A (en) * | 2019-11-01 | 2020-04-10 | 武汉纺织大学 | Deep learning smoke identification method for negative sample excavation |
| CN112349057A (en) * | 2020-12-01 | 2021-02-09 | 北京交通大学 | Deep learning-based indoor smoke and fire detection method |
-
2021
- 2021-09-18 CN CN202111100923.0A patent/CN113869164A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598891A (en) * | 2018-12-24 | 2019-04-09 | 中南民族大学 | A kind of method and system for realizing Smoke Detection using deep learning disaggregated model |
| CN110991242A (en) * | 2019-11-01 | 2020-04-10 | 武汉纺织大学 | Deep learning smoke identification method for negative sample excavation |
| CN112349057A (en) * | 2020-12-01 | 2021-02-09 | 北京交通大学 | Deep learning-based indoor smoke and fire detection method |
Non-Patent Citations (1)
| Title |
|---|
| 袁梅等: "基于卷积神经网络的烟雾检测", 《重庆邮电大学学报( 自然科学版)》, vol. 32, no. 4, 15 August 2020 (2020-08-15), pages 1 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN112287816B (en) | Dangerous work area accident automatic detection and alarm method based on deep learning | |
| CN111091072A (en) | YOLOv 3-based flame and dense smoke detection method | |
| JP4705090B2 (en) | Smoke sensing device and method | |
| US8983180B2 (en) | Method of detecting smoke of forest fire using spatiotemporal BoF of smoke and random forest | |
| CN113283344B (en) | Mining conveyor belt deviation detection method based on semantic segmentation network | |
| CN109815904B (en) | Fire identification method based on convolutional neural network | |
| WO2022067668A1 (en) | Fire detection method and system based on video image target detection, and terminal and storage medium | |
| CN111738054B (en) | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN | |
| EP3877906A1 (en) | Systems and methods for evaluating perception system quality | |
| CN110458126B (en) | Pantograph state monitoring method and device | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN111047565A (en) | Method, storage medium and equipment for forest cloud image segmentation | |
| CN113192038B (en) | Method for recognizing and monitoring abnormal smoke and fire in existing flame environment based on deep learning | |
| CN116259002A (en) | Human body dangerous behavior analysis method based on video | |
| CN103391441A (en) | Surveillance video object deleting, tampering and detecting algorithm based on capacity variance | |
| CN117475353A (en) | Video-based abnormal smoke identification method and system | |
| CN116977909A (en) | Deep learning fire intensity recognition method and system based on multi-modal data | |
| CN115830516B (en) | Computer neural network image processing method for battery deflagration detection | |
| CN113869164A (en) | Smoke detection method based on deep learning | |
| CN116563762A (en) | Fire detection method, system, medium, equipment and terminal for oil and gas station | |
| CN110852174A (en) | Early smoke detection method based on video monitoring | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN115546682A (en) | Dynamic smoke detection method based on video | |
| CN112215122B (en) | Fire detection method, system, terminal and storage medium based on video image target detection |
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 |