CN112580396A - Forest fire recognition method - Google Patents
Forest fire recognition method Download PDFInfo
- Publication number
- CN112580396A CN112580396A CN201910931755.6A CN201910931755A CN112580396A CN 112580396 A CN112580396 A CN 112580396A CN 201910931755 A CN201910931755 A CN 201910931755A CN 112580396 A CN112580396 A CN 112580396A
- Authority
- CN
- China
- Prior art keywords
- image
- forest fire
- water mist
- recognition method
- steps
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Abstract
A forest fire recognition method relates to the technical field of image recognition, and aims to solve the problem that forest fires cannot be found timely in the prior art, and comprises the following steps: acquiring a video image in a monitoring area; step two: judging the type of the smoke image or the water mist image according to the image information, and then positioning the area where the tree is located in the image; step three: preprocessing the acquired image; step four: extracting the region of interest of the processed image; step five: obtaining cut image information from the smog or water mist image information in the training set according to the steps, and training by utilizing an SVM classifier; step six: and inputting the test set to obtain a recognition result. The invention can comprehensively monitor the forest fire-prevention area, discover the fire condition in the monitoring area in time and give an alarm in time.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a forest fire recognition method.
Background
Forest fire refers to the action of forest fire which loses artificial control, freely spreads and expands in forest lands and brings certain harm and loss to forests, forest ecosystems and human beings. Forest fires are natural disasters which are strong in burst, large in destructiveness and difficult to dispose and rescue.
The forest fire prevention work is an important component of the Chinese disaster prevention and reduction work, is important content of the construction of the national public emergency system, is an important guarantee of social stability and the people's living and entertainment industry, is an important guarantee for accelerating the development of the forest industry and strengthening the basis and the premise of the ecological construction, and relates to forest resources and ecological safety, and the life and property safety of people, while the timely discovery of forest fires can greatly reduce the property loss and can quickly control the fire behavior.
Disclosure of Invention
The purpose of the invention is: aiming at the problem that the forest fire cannot be found in time in the prior art, the forest fire identification method is provided.
The technical scheme adopted by the invention to solve the technical problems is as follows: a forest fire recognition method comprises the following steps:
the method comprises the following steps: acquiring a video image in a monitoring area;
step two: judging the type of the smoke image or the water mist image according to the image information, and then positioning the area where the tree is located in the image;
step three: preprocessing the acquired image;
step four: extracting the region of interest of the processed image;
step five: obtaining cut image information from the smog or water mist image information in the training set according to the steps, and training by utilizing an SVM classifier;
step six: and inputting the test set to obtain a recognition result.
Further, the detailed steps of the second step are as follows:
step two, firstly: obtaining an image containing smoke or water mist;
step two: carrying out gray level processing on the smoke image or the water mist image;
step two and step three: and judging the type of the image according to whether continuous ripples exist in the image, labeling the image, and taking the image as a training set, wherein the classification result is smoke or water mist.
Further, the detailed steps of the fourth step are as follows:
step four, firstly: multiplying and averaging values in the x direction and the y direction by using a Sobel edge enhancement method, and then carrying out binarization processing;
step four and step two: numbering the profile;
step four and step three: and carrying out linear approximation value taking on the coordinate values of the phase points by a least square method according to the serial number of the profile.
Further, the images in the training set and the test set are in an RGB format.
Further, the preprocessing in the third step comprises: filtering, binarization and morphological processing.
Further, the acquisition of the video image is completed through a monitoring camera installed in the monitored area.
The invention has the beneficial effects that: the invention can comprehensively monitor the forest fire prevention area, timely discover the fire condition in the monitoring area and timely give an alarm, can discover the abnormal state at the first time and send an alarm, reduces the workload of monitoring personnel, improves the working efficiency by more than one time, and realizes the effective monitoring of the hidden danger of forest fire within 24 hours.
Detailed Description
The first embodiment is as follows: the forest fire recognition method in the embodiment comprises the following steps:
the method comprises the following steps: acquiring a video image in a monitoring area;
step two: judging the type of the smoke image or the water mist image according to the image information, and then positioning the area where the tree is located in the image;
step three: preprocessing the acquired image;
step four: extracting the region of interest of the processed image;
step five: obtaining cut image information from the smog or water mist image information in the training set according to the steps, and training by utilizing an SVM classifier;
step six: and inputting the test set to obtain a recognition result.
The second embodiment is as follows: this embodiment mode is further described with reference to the first embodiment mode, and the difference between this embodiment mode and the first embodiment mode is that the detailed steps of the second step mode are:
step two, firstly: obtaining an image containing smoke or water mist;
step two: carrying out gray level processing on the smoke image or the water mist image;
step two and step three: and judging the type of the image according to whether continuous ripples exist in the image, labeling the image, and taking the image as a training set, wherein the classification result is smoke or water mist.
In the embodiment, when mist is judged to be smoke or water mist, whether continuous ripples exist in a finally obtained image is judged, if the continuous ripples exist, the image is the smoke, and if the continuous ripples do not exist, the image is the water mist.
In the specific implementation of the invention, when the smoke is judged, the alarm processing is carried out, and if the smoke is water mist, the alarm processing is not carried out.
The third concrete implementation mode: this embodiment mode is further described with reference to the first embodiment mode, and the difference between this embodiment mode and the first embodiment mode is that the detailed step of the fourth step is:
step four, firstly: multiplying and averaging values in the x direction and the y direction by using a Sobel edge enhancement method, and then carrying out binarization processing;
step four and step two: numbering the profile;
step four and step three: and carrying out linear approximation value taking on the coordinate values of the phase points by a least square method according to the serial number of the profile.
In the embodiment, a line appears in the image after the image is processed, one end of the line is a fire point, and the smoke image is formed around the fire point.
The fourth concrete implementation mode: the present embodiment is further described with respect to the first embodiment, and the difference between the present embodiment and the first embodiment is that the training set and the test set all use RGB formats.
The fifth concrete implementation mode: the present embodiment is further described with reference to the first embodiment, and the difference between the present embodiment and the first embodiment is that the pretreatment in the third step includes: filtering, binarization and morphological processing.
The sixth specific implementation mode: the present embodiment is described in further detail with reference to the first embodiment, and the difference between the present embodiment and the first embodiment is that the video image is acquired by a monitoring camera installed in a monitored area.
It should be noted that the detailed description is only for explaining and explaining the technical solution of the present invention, and the scope of protection of the claims is not limited thereby. It is intended that all such modifications and variations be included within the scope of the invention as defined in the following claims and the description.
Claims (6)
1. A forest fire recognition method is characterized by comprising the following steps:
the method comprises the following steps: acquiring a video image in a monitoring area;
step two: judging the type of the smoke image or the water mist image according to the image information, and then positioning the area where the tree is located in the image;
step three: preprocessing the acquired image;
step four: extracting the region of interest of the processed image;
step five: obtaining cut image information from the smog or water mist image information in the training set according to the steps, and training by utilizing an SVM classifier;
step six: and inputting the test set to obtain a recognition result.
2. A forest fire recognition method as claimed in claim 1, wherein: the detailed steps of the second step are as follows:
step two, firstly: obtaining an image containing smoke or water mist;
step two: carrying out gray level processing on the smoke image or the water mist image;
step two and step three: and judging the type of the image according to whether continuous ripples exist in the image, labeling the image, and taking the image as a training set, wherein the classification result is smoke or water mist.
3. A forest fire recognition method as claimed in claim 1, wherein: the detailed steps of the fourth step are as follows:
step four, firstly: multiplying and averaging values in the x direction and the y direction by using a Sobel edge enhancement method, and then carrying out binarization processing;
step four and step two: numbering the profile;
step four and step three: and carrying out linear approximation value taking on the coordinate values of the phase points by a least square method according to the serial number of the profile.
4. A forest fire recognition method as claimed in claim 1, wherein: the images in the training set and the test set are in an RGB format.
5. A forest fire recognition method as claimed in claim 1, characterized in that the preprocessing in step three comprises: filtering, binarization and morphological processing.
6. A forest fire recognition method as claimed in claim 1, wherein: and the acquisition of the video image is completed through a monitoring camera arranged in a monitored area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910931755.6A CN112580396A (en) | 2019-09-29 | 2019-09-29 | Forest fire recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910931755.6A CN112580396A (en) | 2019-09-29 | 2019-09-29 | Forest fire recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112580396A true CN112580396A (en) | 2021-03-30 |
Family
ID=75110926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910931755.6A Pending CN112580396A (en) | 2019-09-29 | 2019-09-29 | Forest fire recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112580396A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114863350A (en) * | 2022-07-06 | 2022-08-05 | 江苏开放大学（江苏城市职业学院） | Forest monitoring method and system based on image recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030215141A1 (en) * | 2002-05-20 | 2003-11-20 | Zakrzewski Radoslaw Romuald | Video detection/verification system |
| CN101326053A (en) * | 2005-12-05 | 2008-12-17 | 3M创新有限公司 | Hyperabsorptive nanoparticle compositions |
| CN103456122A (en) * | 2013-08-26 | 2013-12-18 | 中国科学技术大学 | Forest fire smoke recognizing method and device |
| CN105426868A (en) * | 2015-12-10 | 2016-03-23 | 山东大学 | Lane detection method based on adaptive region of interest |
| CN105844295A (en) * | 2016-03-21 | 2016-08-10 | 北京航空航天大学 | Video smog fine classification method based on color model and motion characteristics |
| CN108470349A (en) * | 2018-03-29 | 2018-08-31 | 汕头大学 | A kind of milli machine part dimension measurement screening technique under movement background |
| CN110135374A (en) * | 2019-05-21 | 2019-08-16 | 吉林大学 | It is identified using image block characteristics and returns the fire hazard smoke detecting method classified |
-
2019
- 2019-09-29 CN CN201910931755.6A patent/CN112580396A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030215141A1 (en) * | 2002-05-20 | 2003-11-20 | Zakrzewski Radoslaw Romuald | Video detection/verification system |
| CN101326053A (en) * | 2005-12-05 | 2008-12-17 | 3M创新有限公司 | Hyperabsorptive nanoparticle compositions |
| CN103456122A (en) * | 2013-08-26 | 2013-12-18 | 中国科学技术大学 | Forest fire smoke recognizing method and device |
| CN105426868A (en) * | 2015-12-10 | 2016-03-23 | 山东大学 | Lane detection method based on adaptive region of interest |
| CN105844295A (en) * | 2016-03-21 | 2016-08-10 | 北京航空航天大学 | Video smog fine classification method based on color model and motion characteristics |
| CN108470349A (en) * | 2018-03-29 | 2018-08-31 | 汕头大学 | A kind of milli machine part dimension measurement screening technique under movement background |
| CN110135374A (en) * | 2019-05-21 | 2019-08-16 | 吉林大学 | It is identified using image block characteristics and returns the fire hazard smoke detecting method classified |
Non-Patent Citations (2)
| Title |
|---|
| VLADIMIR SEDLÁK .ETC: "A real-time method for smoke detection in monitored forest areas", 《2017 INTERNATIONAL CONFERENCE ON APPLIED ELECTRONICS (AE)》 * |
| 陈无畏等: "一种基于边缘点投影的车道线快速识别算法", 《汽车工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114863350A (en) * | 2022-07-06 | 2022-08-05 | 江苏开放大学（江苏城市职业学院） | Forest monitoring method and system based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040669A (en) | Intelligent substation video fence method and system | |
| CN113344326A (en) | System and method for identifying dynamic hidden danger and evaluating risk of multi-information fusion special operation site | |
| CN202771441U (en) | Face recognition monitoring system | |
| CN109544838B (en) | Artificial intelligence cognitive recognition system for special area | |
| CN113297926B (en) | Behavior detection and recognition method and system | |
| CN111540173B (en) | Drowning alarm system and method based on intelligent picture recognition | |
| Yang et al. | Early detection of forest fire based on unmaned aerial vehicle platform | |
| CN109460744A (en) | A kind of video monitoring system based on deep learning | |
| CN112580396A (en) | Forest fire recognition method | |
| CN112818953A (en) | Mask wearing state identification method, device, equipment and readable storage medium | |
| CN110956652A (en) | Early warning method for transformer substation personnel crossing line | |
| CN103077612A (en) | System and method for detecting road occupation of automotive vehicle on fire-fighting access | |
| CN115100813A (en) | Intelligent community system based on digital twins | |
| CN110930632A (en) | Early warning system based on artificial intelligence | |
| CN114092875A (en) | Operation site safety supervision method and device based on machine learning | |
| CN110751125A (en) | Wearing detection method and device | |
| CN111582183A (en) | Mask identification method and system in public place | |
| CN116311729A (en) | AI-based power grid infrastructure site safety management system | |
| CN100483471C (en) | Signalling system with imaging sensor | |
| CN105338315A (en) | Intelligent mobile terminal-based warehouse anti-theft video monitoring system | |
| Bayoumi et al. | A real-time fire detection and notification system based on computer vision | |
| CN110895686A (en) | On-duty identification method for special person of fire-fighting person | |
| CN112800896A (en) | Security emergency measure self-response method and system based on knowledge graph | |
| CN113705357A (en) | Method, system, device and storage medium for identifying electric vehicle based on camera | |
| CN112584095A (en) | Intelligent pole tower external damage prevention monitoring method based on 3D convolution technology |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210330 |