CN111047818A - Forest fire early warning system based on video image - Google Patents
Forest fire early warning system based on video image Download PDFInfo
- Publication number
- CN111047818A CN111047818A CN201911060009.0A CN201911060009A CN111047818A CN 111047818 A CN111047818 A CN 111047818A CN 201911060009 A CN201911060009 A CN 201911060009A CN 111047818 A CN111047818 A CN 111047818A
- Authority
- CN
- China
- Prior art keywords
- fire
- early warning
- forest
- video
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 claims abstract description 95
- 238000001514 detection method Methods 0.000 claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 238000011161 development Methods 0.000 claims abstract description 23
- 238000012800 visualization Methods 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 239000000779 smoke Substances 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 2
- 230000007797 corrosion Effects 0.000 claims description 2
- 230000000877 morphologic effect Effects 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims 1
- 238000013527 convolutional neural network Methods 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Abstract
A forest fire early warning system based on video images comprises a video acquisition module, an edge calculation module, a cloud server, an early warning module and a communication module; the video acquisition module is directly connected with the edge calculation module, and the analysis result of the edge calculation module is sent to the early warning module and the cloud server. The video acquisition module is used for acquiring a monitoring video image of a forest area; the edge calculation module is used for storing and analyzing video images, and an edge computer of the forest monitoring station executes a fire detection algorithm; the cloud server is used for inquiring the monitoring video, storing the fire video image, configuring a fire detection algorithm for an edge computer of the forest monitoring station, and providing a fire detection algorithm development platform and fire map visualization; the early warning module is used for carrying out real-time early warning on the fire, and comprises three levels of forest area early warning, forest monitoring station early warning and cloud server early warning. The invention improves the real-time performance of algorithm detection and utilizes idle computer resources of the forest monitoring station.
Description
Technical Field
The invention relates to a forest fire early warning system based on video images, and belongs to the field of forest fire prevention.
Background
Forest fires destroy a great amount of forest resources every year, which not only causes great economic loss, but also seriously threatens the life safety of surrounding residents. The detection and early warning of forest fires are beneficial to reducing the loss of forest resources, personnel and property caused by the fires. The fire detection technology based on the video image has the characteristics of large monitoring range, easiness in deployment, high instantaneity and low false alarm rate, and is widely applied to forest fire early warning systems. The existing forest fire early warning system based on video images has the following defects: 1. the video image needs to be transmitted to a cloud server for algorithm analysis, and the real-time performance is insufficient; 2. the method comprises the following steps that computing resources of an edge computer of a forest monitoring station are idle, and computing resources of a cloud server are excessively used; 3. forest fire detection algorithms used by the system are difficult to optimize or update. These disadvantages make the forest fire early warning system based on video images insufficient in practicability.
Disclosure of Invention
The invention aims to overcome the defects of the existing system, and provides a forest fire early warning system based on a video image, which can improve the real-time performance of algorithm detection, utilize idle computer resources of a forest monitoring station, save cloud server computing resources and facilitate the optimization and the update of a forest fire detection algorithm.
In order to achieve the purpose, the invention adopts the technical scheme that:
the forest fire early warning system based on the video images comprises a video acquisition module, an edge calculation module, a cloud server, an early warning module and a communication module; the video acquisition module is directly connected with the edge calculation module, and an analysis result of the edge calculation module is sent to the early warning module and the cloud server;
the video acquisition module is used for acquiring monitoring video images of the forest area and sending the acquired video images to the edge calculation module for storage and analysis through the communication module;
the edge calculation module is used for storing and analyzing video images; the system comprises a forest monitoring station, a communication module, a cloud server and an early warning module, wherein an edge computer of the forest monitoring station analyzes acquired monitoring video images in time by using a fire detection algorithm provided by the cloud server, performs real-time early warning through the early warning module, and sends a fire detection result and fire situation video images to the cloud server through the communication module for storage and processing;
the cloud server is used for inquiring the monitoring video, storing the fire video image, configuring a fire detection algorithm for an edge computer of the forest monitoring station, and providing a fire detection algorithm development platform and fire map visualization.
The early warning module is used for carrying out real-time early warning on the fire, and comprises three levels of forest area early warning, forest monitoring station early warning and cloud server early warning.
Furthermore, the video acquisition module is a monitoring network formed by a certain number of network cameras. The network camera is used for collecting RGB monitoring video images near the deployment point and sending the RGB monitoring video images to an edge computer of the forest monitoring station. The network camera can be set with periodical automatic lens rotation and manual lens focusing, and can monitor a forest area with a large area.
Further, the edge calculation module comprises an edge computer of the forest monitoring station, gateway equipment and a local video storage hard disk. The edge computer of the forest monitoring station has the functions of displaying monitoring video images, setting the lens rotation period and the lens focal length of the network camera and analyzing the video images. The video image analysis function analyzes the video image acquired by the network camera by using a fire detection algorithm provided by the cloud server; if the fire is detected, early warning is triggered in time to inform monitoring station staff to verify, report and take emergency measures. The gateway equipment is used for receiving the video images of the connected network cameras and sending data such as fire detection results, fire video images and network camera geographic coordinates to the cloud server. The local video storage hard disk is used for storing monitoring video images collected by the network camera.
Further, the cloud server comprises a video query unit, a fire video storage unit, a fire detection algorithm configuration unit, a fire detection algorithm development unit and a fire map visualization unit. The video query unit is used for querying and downloading the monitoring video images stored in the forest monitoring station. The fire video storage unit is used for storing fire video images sent by the forest monitoring station and providing a data set for algorithm development. The fire detection algorithm configuration unit is used for configuring the developed fire detection algorithms including a flame recognition algorithm and a smoke recognition algorithm to an edge computer of a forest monitoring station. The fire detection algorithm development unit provides a development platform of related algorithms for researchers, and the development platform comprises a fire video data set using interface, an algorithm verification interface, a traditional image algorithm access interface, a machine learning algorithm access interface and an algorithm deployment interface. The fire detection algorithm development unit provides a development platform of related algorithms for researchers, and the development platform comprises a fire video data set using interface, an algorithm verification interface, a traditional image algorithm access interface, a machine learning algorithm access interface and an algorithm deployment interface. The current version of the detection algorithm uses a combination of visual and motion features. In terms of visual features, the identification of flame is realized by setting RGB color threshold and HIS color threshold, and the identification of smoke is realized by training and generating a Convolutional Neural Network (CNN) model by using smoke data set; in terms of motion characteristics, a background subtraction method and a moving image accumulation method are used to extract a motion region in a video. Research personnel can optimize the existing algorithm and develop a new algorithm by utilizing the stored fire video data set on the basis of the current version algorithm, and update the algorithm to the system by using the corresponding access interface. The fire map visualization module is used for providing a visualization function of forest fire monitoring conditions on a map, and can realize visualization of fire distribution on a geographic information system according to fire statistical data reported by a forest monitoring station.
Further, the early warning module comprises a forest monitoring station early warning unit, a forest area early warning unit and a cloud server early warning unit. And the early warning unit of the forest monitoring station timely informs workers to verify, report and take emergency measures through voice according to the fire detection result of the edge computer. The forest region early warning unit consists of a certain number of voice rods deployed in a forest region. When the forest monitoring station detects the fire, the voice rod in the corresponding area is triggered to play fire emergency voice, and nearby personnel are notified to avoid danger in time. The cloud server early warning unit is used for counting fire data reported by each forest monitoring station, judging whether a large-area fire occurs or not by combining the fire video images, and informing workers to take large-scale emergency measures in time.
Further, the communication module includes a section for: the video acquisition module and the edge calculation module are communicated through a wired network or a 4G network, the edge calculation module and the cloud server are communicated through the wired network or WIFI, and the forest area early warning units in the edge calculation module and the early warning module are communicated through the wired network or the 4G network.
The invention has the following advantages:
1. according to the invention, an edge calculation mode is adopted, and the fire detection is calculated and analyzed on an edge computer of the forest monitoring station, so that the real-time performance of the forest fire early warning system is improved;
2. according to the invention, idle computer resources of the forest monitoring station are effectively utilized, and the calculation load of the cloud server is reduced;
3. the invention provides a development platform of a forest fire detection algorithm, which facilitates the optimization and the update of the algorithm.
Drawings
FIG. 1 is a schematic diagram of the system architecture of the present invention.
Fig. 2 is a schematic diagram of the early warning process of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
As shown in fig. 1, the forest fire early warning system based on video images of the present invention includes a video acquisition module, an edge calculation module, a cloud server, an early warning module, and a communication module; the video acquisition module is directly connected with the edge calculation module, and an analysis result of the edge calculation module is sent to the early warning module and the cloud server;
the video acquisition module is used for acquiring monitoring video images of the forest area and sending the acquired video images to the edge calculation module for storage and analysis through the communication module;
the edge calculation module is used for storing and analyzing video images; the system comprises a forest monitoring station, a communication module, a cloud server and an early warning module, wherein an edge computer of the forest monitoring station analyzes acquired monitoring video images in time by using a fire detection algorithm provided by the cloud server, performs real-time early warning through the early warning module, and sends a fire detection result and fire situation video images to the cloud server through the communication module for storage and processing;
the cloud server is used for inquiring the monitoring video, storing the fire video image, configuring a fire detection algorithm for an edge computer of the forest monitoring station, and providing a fire detection algorithm development platform and fire map visualization.
The early warning module is used for carrying out real-time early warning on the fire, and comprises three levels of forest area early warning, forest monitoring station early warning and cloud server early warning.
Specifically, the video acquisition module is a monitoring network composed of a certain number of network cameras. The network camera is deployed at a designated position of a forest area and used for collecting RGB monitoring video images near a deployment point and sending the collected monitoring video images to an edge computer of a forest monitoring station through gateway equipment and a wired or 4G network. The network camera can be provided with a periodic automatic lens to rotate, 360-degree omnibearing monitoring is realized, lens focusing can be manually carried out, the monitoring area range is controlled, and the forest area with a large area is monitored.
Specifically, the edge calculation module comprises an edge computer of the forest monitoring station, gateway equipment and a local video storage hard disk. The edge computer of the forest monitoring station has the functions of displaying monitoring video images, setting lens parameters of the network camera and analyzing the video images. The display of the monitoring video image is realized by connecting an electronic display screen with an edge computer. The setting function of the lens parameters of the network camera, including the automatic rotation period and the focal length of the lens, is realized by installing a client application program of a monitoring station on an edge computer. The video image analysis function analyzes the video image acquired by the network camera by using a fire detection algorithm provided by the cloud server; if the fire is detected, early warning is triggered in time to inform monitoring station staff to verify, report and take emergency measures. The gateway equipment is used for receiving the video images of the connected network cameras and sending data such as fire detection results, fire video images and network camera geographic coordinates to the cloud server through a wired network or WIFI. The local video storage hard disk is used for storing monitoring video images acquired by the network camera and is usually a large-capacity mechanical hard disk.
Specifically, the cloud server comprises a video query unit, a fire video storage unit, a fire detection algorithm configuration unit, a fire detection algorithm development unit and a fire map visualization unit. The functions of each unit are integrated in a server-side application program. The video query unit is used for querying and downloading the monitoring video images stored in the forest monitoring station. The fire video storage unit is used for storing fire video images sent by the forest monitoring station and providing a data set for algorithm development. The fire detection algorithm configuration unit is used for configuring the developed fire detection algorithms including a flame recognition algorithm and a smoke recognition algorithm to an edge computer of a forest monitoring station through a wired network or WIFI. The fire detection algorithm development unit provides a development platform of related algorithms for researchers, and the development platform comprises a fire video data set using interface, an algorithm verification interface, a traditional image algorithm access interface, a machine learning algorithm access interface and an algorithm deployment interface. The current version of the detection algorithm uses a combination of visual and motion features. In terms of visual features, the identification of flames is realized by setting RGB color threshold values and HSI color threshold values, and the identification of smoke is realized by training and generating a Convolutional Neural Network (CNN) model by using smoke data sets; in terms of motion characteristics, a frame difference method and a moving image accumulation method are used to extract a motion region in a video. Research personnel can optimize the existing algorithm and develop a new algorithm by utilizing the stored fire video data set on the basis of the current version algorithm, wherein the algorithm comprises threshold parameter adjustment, deep learning network structure optimization, algorithm logic, realization adjustment and the like, and finally, the algorithm is updated to the system by using a corresponding access interface. The fire map visualization module is used for providing a visualization function of forest fire monitoring conditions on a map, and can realize visualization of fire distribution on a geographic information system according to fire statistical data reported by a forest monitoring station.
Specifically, the fire detection algorithm of the current version of the system is realized by performing computer processing on video image information of each frame, identifying flame and smoke regions by using an RGB and HSI color threshold method, a CNN model and a motion model, and according to the following steps:
step 1: the video image of each frame is converted into RGB and HSI color models.
Step 2: in the image color model extracted in the step 1, marking pixel points meeting the following conditions as flame pixels:
(1)R>RT;(2)R>G>B;(3)S>(255-R)*ST/RT;
wherein R isTIs the threshold value of the R color component in the RGB model, and the value of the current algorithm is 180; s is the saturation component in the HSI model, STThe current algorithm takes the value of 65 for the saturation threshold.
And step 3: and (3) carrying out smoke recognition on the RGB image color model extracted in the step (1) by using the trained CNN model, and extracting a smoke region in the image. Wherein, the CNN model comprises: an image block input layer, the size of the image block being 240 × 240; two-dimensional convolutional layers, the size and number of filters are 5 and 20, respectively; a linear rectification unit layer; a maximum pooling layer with a pooling parameter of 2; the output class parameters of the full connection layer are consistent with the sample class parameters; and finally, a Softmax function layer and a classification output layer. And marking the image blocks identified as smoke pixel blocks according to the output result of the CNN model.
And 4, step 4: the method comprises the following steps of establishing a motion model for an input video image sequence, and extracting a continuously moving video image area by using a frame difference method and a motion accumulation method, wherein the method comprises the following steps:
(1) for a video image cur of a current frame, extracting two previous frame video images pre1 and pre2, respectively converting the two previous frame video images into gray maps, calculating diff 1-pre 1-pre2 and diff 2-cur-pre 1, setting a difference threshold T1, and thresholding diff1 and diff2 into binary gray maps;
(2) logically anding diff1 and diff 2: form-diff 1& diff 2; performing morphological operation of corrosion before expansion on form to obtain a foreground image;
(3) setting a video image sequence window, wherein the window size s is set to be 200; the window stores the processed continuous binary image sequence img of the links (1) and (2)1,img2,……,imgs(ii) a Calculating a motion image A, the value of each pixel of A being equal to img1,img2,……,imgsThe sum of the corresponding pixel point values;
(4) if the pixel point value of A is larger than the threshold value T2, marking the pixel point as a continuous motion area; t2 is set to 100.
And 5: and finally determining the fire occurrence and fire area according to the flame pixel area obtained in the step 2, the smoke pixel area obtained in the step 3 and the continuous motion area obtained in the step 4.
Specifically, the early warning module comprises a forest monitoring station early warning unit, a forest area early warning unit and a cloud server early warning unit. And the early warning unit of the forest monitoring station timely informs workers to verify, report and take emergency measures through voice according to the fire detection result of the edge computer. The forest region early warning unit consists of a certain number of voice rods deployed in a forest region. When the forest monitoring station detects the fire, the voice rod in the corresponding area is triggered to play fire emergency voice, and nearby personnel are notified to avoid danger in time. The forest monitoring station is communicated with the forest area early warning unit through a wired network or a 4G network. The cloud server early warning unit is used for counting fire data reported by each forest monitoring station, judging whether a large-area fire occurs or not by combining the fire video images, and informing workers to take large-scale emergency measures in time.
Specifically, the communication module includes a section: the video acquisition module and the edge calculation module are communicated through a wired network or a 4G network, the edge calculation module and the cloud server are communicated through the wired network or WIFI, and the forest area early warning units in the edge calculation module and the early warning module are communicated through the wired network or the 4G network.
Specifically, the fire early warning process of the system is shown in fig. 2, and comprises the steps of monitoring video image acquisition and analysis, multi-level early warning after a fire occurs, large-scale fire analysis and fire map visualization.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments described herein but rather by equivalents thereof as may occur to those skilled in the art upon consideration of the present disclosure.
Claims (7)
1. The utility model provides a forest fire early warning system based on video image which characterized in that: the system comprises a video acquisition module, an edge calculation module, a cloud server, an early warning module and a communication module; the video acquisition module is directly connected with the edge calculation module, and an analysis result of the edge calculation module is sent to the early warning module and the cloud server;
the video acquisition module is used for acquiring monitoring video images of the forest area and sending the acquired video images to the edge calculation module for storage and analysis through the communication module;
the edge calculation module is used for storing and analyzing video images; the system comprises a forest monitoring station, a communication module, a cloud server and an early warning module, wherein an edge computer of the forest monitoring station analyzes acquired monitoring video images in time by using a fire detection algorithm provided by the cloud server, performs real-time early warning through the early warning module, and sends a fire detection result and fire situation video images to the cloud server through the communication module for storage and processing;
the cloud server is used for inquiring the monitoring video, storing the fire video image, configuring a fire detection algorithm for an edge computer of the forest monitoring station, and providing a fire detection algorithm development platform and fire map visualization;
the early warning module is used for carrying out real-time early warning on the fire, and comprises three levels of forest area early warning, forest monitoring station early warning and cloud server early warning.
2. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the video acquisition module is a monitoring network consisting of a certain number of network cameras; the network camera is used for collecting RGB monitoring video images near the deployment point and sending the RGB monitoring video images to an edge computer of a forest monitoring station; the network camera can be set with periodical automatic lens rotation and manual lens focusing, and can monitor a forest area with a large area.
3. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the edge computing module comprises an edge computer of the forest monitoring station, gateway equipment and a local video storage hard disk; the edge computer of the forest monitoring station has the functions of displaying monitoring video images, setting the lens rotation period and the lens focal length of the network camera and analyzing the video images; the video image analysis function analyzes the video image acquired by the network camera by using a fire detection algorithm provided by the cloud server; if the fire is detected, early warning is triggered in time to inform monitoring station workers to verify, report and take emergency measures; the gateway equipment is used for receiving video images acquired by the connected network cameras and sending data such as fire detection results, fire videos and network camera geographic coordinates to the cloud server; the local video storage hard disk is used for storing monitoring video images collected by the network camera.
4. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the cloud server comprises a video query unit, a fire video storage unit, a fire detection algorithm configuration unit, a fire detection algorithm development unit and a fire map visualization unit; the video query unit is used for querying and downloading monitoring video images stored in the forest monitoring station; the fire video storage unit is used for storing fire video images sent by the forest monitoring station and providing a data set for algorithm development; the fire detection algorithm configuration unit is used for configuring the developed fire detection algorithms including a flame recognition algorithm and a smoke recognition algorithm to an edge computer of a forest monitoring station; the fire detection algorithm development unit provides a development platform of related algorithms for researchers, and the development platform comprises a fire video data set using interface, an algorithm verification interface, a traditional image algorithm access interface, a machine learning algorithm access interface and an algorithm deployment interface; the fire map visualization module is used for providing a visualization function of forest fire monitoring conditions on a map, and can realize visualization of fire distribution on a geographic information system according to fire statistical data reported by a forest monitoring station.
5. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the fire detection algorithm is realized by carrying out computer processing on video image information of each frame and identifying flame and smoke regions by utilizing an RGB and HSI color threshold method, a CNN model and a motion model according to the following steps:
step 1: converting the video image of each frame into RGB and HSI color models;
step 2: in the image color model extracted in the step 1, marking pixel points meeting the following conditions as flame pixels:
(1)R>RT;(2)R>G>B;(3)S>(255-R)*ST/RT;
wherein R isTIs the threshold value of the R color component in the RGB model, and the value of the current algorithm is180 of the total weight of the composition; s is the saturation component in the HSI model, STThe value of the current algorithm is 65 for the saturation threshold;
and step 3: and (3) carrying out smoke recognition on the RGB image color model extracted in the step (1) by using the trained CNN model, and extracting a smoke region in the image. Wherein, the CNN model comprises: an image block input layer, the size of the image block being 240 × 240; two-dimensional convolutional layers, the size and number of filters are 5 and 20, respectively; a linear rectification unit layer; a maximum pooling layer with a pooling parameter of 2; the output class parameters of the full connection layer are consistent with the sample class parameters; finally, a Softmax function layer and a classification output layer are arranged; according to the output result of the CNN model, marking the image blocks identified as smoke pixel blocks;
and 4, step 4: the method comprises the following steps of establishing a motion model for an input video image sequence, and extracting a continuously moving video image area by using a frame difference method and a motion accumulation method, wherein the method comprises the following steps:
(1) for a video image cur of a current frame, extracting two previous frame video images pre1 and pre2, respectively converting the two previous frame video images into gray maps, calculating diff 1-pre 1-pre2 and diff 2-cur-pre 1, setting a difference threshold T1, and thresholding diff1 and diff2 into binary gray maps;
(2) logically anding diff1 and diff 2: form-diff 1& diff 2; performing morphological operation of corrosion before expansion on form to obtain a foreground image;
(3) setting a video image sequence window, wherein the window size s is set to be 200; the window stores the processed continuous binary image sequence img of the links (1) and (2)1,img2,……,imgs(ii) a Calculating a motion image A, the value of each pixel of A being equal to img1,img2,……,imgsThe sum of the corresponding pixel point values;
(4) if the pixel point value of A is larger than the threshold value T2, marking the pixel point as a continuous motion area; t2 is set to 100;
and 5: and finally determining the fire occurrence and fire area according to the flame pixel area obtained in the step 2, the smoke pixel area obtained in the step 3 and the continuous motion area obtained in the step 4.
6. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the early warning module comprises a forest monitoring station early warning unit, a forest area early warning unit and a cloud server early warning unit; the early warning unit of the forest monitoring station notifies workers to verify, report and take emergency measures in time through voice according to the fire detection result of the edge computer; the forest area early warning unit consists of a certain number of voice rods deployed in a forest area; when the forest monitoring station detects a fire, the voice rod in the corresponding area is triggered to play fire emergency voice, and nearby personnel are notified to avoid danger in time; the cloud server early warning unit is used for counting fire data reported by each forest monitoring station, judging whether a large-area fire occurs or not by combining the fire video images, and informing workers to take large-scale emergency measures in time.
7. The forest fire early warning system based on the video image as claimed in claim 1, wherein: the communication module comprises the following parts: the video acquisition module and the edge calculation module are communicated through a wired network or a 4G network, the edge calculation module and the cloud server are communicated through the wired network or WIFI, and the forest area early warning units in the edge calculation module and the early warning module are communicated through the wired network or the 4G network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911060009.0A CN111047818A (en) | 2019-11-01 | 2019-11-01 | Forest fire early warning system based on video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911060009.0A CN111047818A (en) | 2019-11-01 | 2019-11-01 | Forest fire early warning system based on video image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111047818A true CN111047818A (en) | 2020-04-21 |
Family
ID=70232840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911060009.0A Pending CN111047818A (en) | 2019-11-01 | 2019-11-01 | Forest fire early warning system based on video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111047818A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899457A (en) * | 2020-07-10 | 2020-11-06 | 河海大学 | Museum fire alarm monitoring system based on edge calculation |
CN111901573A (en) * | 2020-08-17 | 2020-11-06 | 泽达易盛(天津)科技股份有限公司 | Fine granularity real-time supervision system based on edge calculation |
CN111899452A (en) * | 2020-08-04 | 2020-11-06 | 成都云图睿视科技有限公司 | Forest fire prevention early warning system based on edge calculation |
CN112150750A (en) * | 2020-08-25 | 2020-12-29 | 航天信德智图(北京)科技有限公司 | Forest fire alarm monitoring system based on edge calculation |
CN112261353A (en) * | 2020-09-01 | 2021-01-22 | 浙江大华技术股份有限公司 | Video monitoring and shunting method, system and computer readable storage medium |
CN112309068A (en) * | 2020-10-29 | 2021-02-02 | 电子科技大学中山学院 | Forest fire early warning method based on deep learning |
CN112580481A (en) * | 2020-12-14 | 2021-03-30 | 康佳集团股份有限公司 | Edge node and cloud cooperative video processing method, device and server |
CN112862150A (en) * | 2020-12-30 | 2021-05-28 | 广州智能科技发展有限公司 | Forest fire early warning method based on image and video multi-model |
CN113298048A (en) * | 2021-07-08 | 2021-08-24 | 环球数科集团有限公司 | Forest fire detection and early warning system based on computer vision |
CN113593170A (en) * | 2021-08-11 | 2021-11-02 | 张佳 | Intelligent early warning system based on remote smoke detection |
CN113689650A (en) * | 2021-09-07 | 2021-11-23 | 广州邦讯信息系统有限公司 | Forest fire prevention smoke detection method and system based on monitoring camera |
CN113808361A (en) * | 2021-09-13 | 2021-12-17 | 深圳市长江鑫电气有限公司 | Fire protection device capable of early warning high temperature and early warning system thereof |
CN114221939A (en) * | 2021-11-08 | 2022-03-22 | 中通服和信科技有限公司 | Internet of things video streaming media edge computing gateway |
CN114558267A (en) * | 2022-03-03 | 2022-05-31 | 上海应用技术大学 | Industrial scene fire prevention and control system |
CN114666355A (en) * | 2022-04-27 | 2022-06-24 | 深圳市千乘机器人有限公司 | Video analysis method based on mobile robot |
CN115062706A (en) * | 2022-06-17 | 2022-09-16 | 中国电信股份有限公司 | Forest fire monitoring method and device, storage medium and electronic equipment |
CN115512528A (en) * | 2022-08-16 | 2022-12-23 | 金茂云科技服务(北京)有限公司 | Fire monitoring system and method and computer equipment |
CN115938065A (en) * | 2022-09-21 | 2023-04-07 | 慧之安信息技术股份有限公司 | Fire engine intelligent recognition system based on edge calculation |
CN116630843A (en) * | 2023-04-13 | 2023-08-22 | 安徽中科数智信息科技有限公司 | Fire prevention supervision and management method and system for fire rescue |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060115154A1 (en) * | 2004-11-16 | 2006-06-01 | Chao-Ho Chen | Fire detection and smoke detection method and system based on image processing |
CN105741480A (en) * | 2016-03-17 | 2016-07-06 | 福州大学 | Fire and smoke detection method based on image identification |
CN109377703A (en) * | 2018-12-06 | 2019-02-22 | 河池学院 | A kind of forest fireproofing early warning system and its method based on machine vision |
CN109961042A (en) * | 2019-03-22 | 2019-07-02 | 中国人民解放军国防科技大学 | Smoke detection method combining deep convolutional neural network and visual change diagram |
-
2019
- 2019-11-01 CN CN201911060009.0A patent/CN111047818A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060115154A1 (en) * | 2004-11-16 | 2006-06-01 | Chao-Ho Chen | Fire detection and smoke detection method and system based on image processing |
CN105741480A (en) * | 2016-03-17 | 2016-07-06 | 福州大学 | Fire and smoke detection method based on image identification |
CN109377703A (en) * | 2018-12-06 | 2019-02-22 | 河池学院 | A kind of forest fireproofing early warning system and its method based on machine vision |
CN109961042A (en) * | 2019-03-22 | 2019-07-02 | 中国人民解放军国防科技大学 | Smoke detection method combining deep convolutional neural network and visual change diagram |
Non-Patent Citations (1)
Title |
---|
张科等: "基于边缘计算的森林火警监测系统", 《大数据》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899457A (en) * | 2020-07-10 | 2020-11-06 | 河海大学 | Museum fire alarm monitoring system based on edge calculation |
CN111899452A (en) * | 2020-08-04 | 2020-11-06 | 成都云图睿视科技有限公司 | Forest fire prevention early warning system based on edge calculation |
CN111901573A (en) * | 2020-08-17 | 2020-11-06 | 泽达易盛(天津)科技股份有限公司 | Fine granularity real-time supervision system based on edge calculation |
CN112150750A (en) * | 2020-08-25 | 2020-12-29 | 航天信德智图(北京)科技有限公司 | Forest fire alarm monitoring system based on edge calculation |
CN112261353A (en) * | 2020-09-01 | 2021-01-22 | 浙江大华技术股份有限公司 | Video monitoring and shunting method, system and computer readable storage medium |
CN112261353B (en) * | 2020-09-01 | 2022-10-28 | 浙江大华技术股份有限公司 | Video monitoring and shunting method, system and computer readable storage medium |
CN112309068A (en) * | 2020-10-29 | 2021-02-02 | 电子科技大学中山学院 | Forest fire early warning method based on deep learning |
CN112580481A (en) * | 2020-12-14 | 2021-03-30 | 康佳集团股份有限公司 | Edge node and cloud cooperative video processing method, device and server |
CN112862150A (en) * | 2020-12-30 | 2021-05-28 | 广州智能科技发展有限公司 | Forest fire early warning method based on image and video multi-model |
CN113298048A (en) * | 2021-07-08 | 2021-08-24 | 环球数科集团有限公司 | Forest fire detection and early warning system based on computer vision |
CN113593170B (en) * | 2021-08-11 | 2022-08-30 | 张佳 | Intelligent early warning system based on remote smoke detection |
CN113593170A (en) * | 2021-08-11 | 2021-11-02 | 张佳 | Intelligent early warning system based on remote smoke detection |
CN113689650A (en) * | 2021-09-07 | 2021-11-23 | 广州邦讯信息系统有限公司 | Forest fire prevention smoke detection method and system based on monitoring camera |
CN113808361A (en) * | 2021-09-13 | 2021-12-17 | 深圳市长江鑫电气有限公司 | Fire protection device capable of early warning high temperature and early warning system thereof |
CN114221939A (en) * | 2021-11-08 | 2022-03-22 | 中通服和信科技有限公司 | Internet of things video streaming media edge computing gateway |
CN114558267A (en) * | 2022-03-03 | 2022-05-31 | 上海应用技术大学 | Industrial scene fire prevention and control system |
CN114666355A (en) * | 2022-04-27 | 2022-06-24 | 深圳市千乘机器人有限公司 | Video analysis method based on mobile robot |
CN114666355B (en) * | 2022-04-27 | 2023-12-15 | 深圳市千乘机器人有限公司 | Video analysis method based on mobile robot |
CN115062706A (en) * | 2022-06-17 | 2022-09-16 | 中国电信股份有限公司 | Forest fire monitoring method and device, storage medium and electronic equipment |
CN115512528A (en) * | 2022-08-16 | 2022-12-23 | 金茂云科技服务(北京)有限公司 | Fire monitoring system and method and computer equipment |
CN115938065A (en) * | 2022-09-21 | 2023-04-07 | 慧之安信息技术股份有限公司 | Fire engine intelligent recognition system based on edge calculation |
CN115938065B (en) * | 2022-09-21 | 2023-09-15 | 慧之安信息技术股份有限公司 | Fire engine intelligent identification system based on edge calculation |
CN116630843A (en) * | 2023-04-13 | 2023-08-22 | 安徽中科数智信息科技有限公司 | Fire prevention supervision and management method and system for fire rescue |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111047818A (en) | Forest fire early warning system based on video image | |
CN110738127A (en) | Helmet identification method based on unsupervised deep learning neural network algorithm | |
CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
CN110516529A (en) | It is a kind of that detection method and system are fed based on deep learning image procossing | |
CN105791774A (en) | Surveillance video transmission method based on video content analysis | |
CN109377713B (en) | Fire early warning method and system | |
CN102201146A (en) | Active infrared video based fire smoke detection method in zero-illumination environment | |
CN111222478A (en) | Construction site safety protection detection method and system | |
CN112149522A (en) | Intelligent visual external-damage-prevention monitoring system and method for cable channel | |
CN104820995A (en) | Large public place-oriented people stream density monitoring and early warning method | |
CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
CN112309068B (en) | Forest fire early warning method based on deep learning | |
CN111401310B (en) | Kitchen sanitation safety supervision and management method based on artificial intelligence | |
CN110659546A (en) | Illegal booth detection method and device | |
CN103888731A (en) | Structured description device and system for mixed video monitoring by means of gun-type camera and dome camera | |
CN113642403A (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
CN116846059A (en) | Edge detection system for power grid inspection and monitoring | |
CN115035088A (en) | Helmet wearing detection method based on yolov5 and posture estimation | |
Hermina et al. | A Novel Approach to Detect Social Distancing Among People in College Campus | |
CN112883755A (en) | Smoking and calling detection method based on deep learning and behavior prior | |
CN105095891A (en) | Human face capturing method, device and system | |
CN113095160B (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
CN112532927A (en) | Intelligent safety management and control system for construction site | |
CN115829324A (en) | Personnel safety risk silent monitoring method | |
CN109190555B (en) | Intelligent shop patrol system based on picture comparison |
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 |
Application publication date: 20200421 |
|
WD01 | Invention patent application deemed withdrawn after publication |