CN106650594A - Video fire detection method, device and system - Google Patents

Abstract

The present invention provides a video fire detection method, a device and a system, and relates to the video fire detection-related technical field. In embodiments of the present invention, a video image is extracted out of a data source end, and then the video image is converted to an HSV image. According to a preset HSV threshold range, a mask of the HSV image is constructed and the mask is subjected to contour detection. When the contour of the mask is detected, it is determined that the fire occurs. Meanwhile, the video image is transmitted to a server and the server forwards the video image to a client. The client displays the video image. According to the technical scheme of the video fire detection method, the device and the system, the fire detection and the video monitoring are unified, so that the network construction is simplified. The cost is reduced and the space is saved.

Description

Video fire detection method, device and system

technical field

The present invention relates to the technical field related to video fire detection, in particular to a video fire detection method, device and system.

Background technique

Fire is a very destructive and frequent disaster, especially with the increasing use of fire and electricity in people's production and life, careless management of fire and electricity, or frequent occurrences due to equipment failure or even arson These reasons lead to fires, which pose a huge threat to human life and property. Therefore, discovering the fire in time and taking effective protective measures to minimize the harm caused by the fire and ensure the safety of people's lives and properties has always been a research topic for people.

The existing monitoring system only includes the video monitoring function, and the existing fire detection is based on collecting corresponding data from smoke sensors and temperature sensors as the basis for judging whether a fire has occurred. There are two smoke sensors and temperature sensors, so the cost is relatively high; therefore, in the existing technical solutions, in order to monitor the indoor or outdoor conditions in real time and effectively detect the occurrence of fire, it is necessary to build a complex video surveillance system in the same space. At the same time, it is necessary to build an independent fire detection system network, and the independent construction of video surveillance network and fire detection system network will not only occupy a lot of space, but also increase the cost.

Therefore, how to solve the problem of large space occupation and high cost in the video surveillance network and fire detection system network is a major issue currently facing.

Contents of the invention

In view of this, the purpose of the embodiments of the present invention is to provide a video fire detection method to solve the problems of large space occupation and high cost existing in the independent construction of the existing video surveillance network and fire detection system network.

In addition, the purpose of the embodiments of the present invention is to provide a video fire detection device.

In addition, the purpose of the embodiment of the present invention is to provide a video fire detection system.

In order to achieve the above object, the technical solution adopted in the embodiment of the present invention is as follows:

In the first aspect, an embodiment of the present invention provides a video fire detection system, the video fire detection system includes a data source, a server and a client, wherein the data source is used to extract video images, and the video The image is converted into an HSV image, the mask of the HSV image is constructed according to the preset HSV threshold range, the mask is opened and closed, the image noise is eliminated, and the noise-eliminated mask is contour detected. When it is detected that the mask has an outline, the area of the video image corresponding to the outline is identified, and the data source is also used to send the video image to the server; the server is used to send the video image to the server; The video image is forwarded to the client; the client is used to display the video image.

Further, the data source terminal is also used for sending out an alarm signal when it is detected that the mask has an outline.

In the second aspect, the embodiment of the present invention also provides a video fire detection method, the video fire detection method includes: extracting video images; converting the video images into HSV images; The mask of the HSV image; the mask is contour detected, and when the contour is detected, it is determined that a fire occurs; the video image is sent to the server so that the server forwards the video image to the client to The video image is displayed by the client.

Further, before the step of performing contour detection on the mask, there is also a step of: performing an opening operation and a closing operation on the mask to eliminate image noise.

Further, the video fire detection method further includes: sending an alarm signal when it is detected that the mask has an outline.

Further, the video fire detection method further includes: when it is detected that the mask has an outline, marking an area of the video image corresponding to the outline.

In the third aspect, the implementation of the present invention also provides a video fire detection device, which is applied to the data source, and the video fire detection device includes:

A video capture module, used to extract video images;

An image conversion module, for converting the video image into an HSV image;

A mask construction module, configured to construct a mask of the HSV image according to a preset HSV threshold range;

The contour detection module is used to detect the contour of the mask, and when the contour is detected, it is determined that a fire has occurred.

The sending module is used to send the video image to a server, so that the server forwards the video image to a client for displaying the video image through the client.

Further, the video fire detection device also includes:

The denoising module is used to perform opening and closing operations on the mask to eliminate image noise.

Further, the video fire detection device also includes:

The alarm module is used for sending out an alarm signal when it is detected that the mask has an outline.

Further, the video fire detection device also includes:

The identification module is configured to identify the area of the video image corresponding to the outline when it is detected that the mask has an outline.

Compared with the prior art, the video fire detection method, device and system provided by the present invention extract the video image through the data source, convert the video image into an HSV image, and construct the mask of the HSV image according to the preset HSV threshold range , carry out outline detection on the mask, when an outline is detected, it is determined that a fire has occurred, and the video image is sent to the server, the server forwards the video image to the client, and the client displays the video image. The video fire detection method, device and system of the present invention unifies fire detection and video surveillance, simplifies network construction, reduces costs, and saves space.

In order to make the above-mentioned objects, features and advantages of the present invention more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.

Fig. 1 is a schematic diagram of a video fire detection system provided by a preferred embodiment of the present invention.

Fig. 2 is a schematic block diagram of a data source end provided by a preferred embodiment of the present invention.

Fig. 3 is a schematic diagram of functional modules of a video fire detection device provided by a preferred embodiment of the present invention.

Fig. 4 is a schematic flowchart of a video fire detection method provided by a preferred embodiment of the present invention.

Icons: 10-video fire detection system; 100-data source; 200-server; 300-client; 400-network; 110-video fire detection device; 1101-video acquisition module; 1102-image conversion module; 1103-mask Model building module; 1104-denoising module; 1105-contour detection module; 1106-alarm module; 1107-identification module; 1108-sending module; 111-memory; 112-storage controller; interface; 115-audio unit.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

As shown in FIG. 1 , it is a schematic diagram of a video fire detection system 10 provided by a preferred embodiment of the present invention. The video fire detection system 10 includes a data source 100, a server 200, and a client 300. The server 200 can communicate with the data source 100 and the client 300 through a network 400 to realize the communication between the server 200 and the data source 100. data communication or interaction between the server 200 and the client 300. The data source 100 may be several cameras. In this embodiment, the data source 100 completes the construction of the development environment by transplanting the embedded Linux system and the Open Source Computer Vision Library (Open Source Computer Vision Library, OpenCV), and installing the camera driver. This is achieved through open source computer vision libraries. The server 200 can be a web server, a database server, a cloud server, etc., and its operating system can be a Linux system. The server 200 is used as a relay for receiving video images, and is used to forward the video images sent by the data source 100 to the client 300. . The client 300 can be a personal computer (personal computer, PC), tablet computer, etc., which is used for playing video and capturing images, and the operating system of the client 300 can be a Linux system, a Windows system, or the like.

In this embodiment, when the video fire detection system 10 is working, the data source 100 and the client 300 first bind the IP address and port of the server 200 to realize network connection, and establish a connection between the data source 100 and the client 300. communication. The data source 100 sends video images to the server 200 through the Python network interface, and the server 200 runs a network interface program written by Python under the Linux system. After monitoring the connection request of the network 400, the data source 100 is sent immediately. The video image is forwarded to the client 300, and the client 300 receives and displays the video image.

As shown in FIG. 2 , it is a schematic block diagram of the data source terminal 100 provided by the preferred embodiment of the present invention. The data source 100 includes a video fire detection device 110 , a memory 111 , a storage controller 112 , a processor 113 , a peripheral interface 114 , and an audio unit 115 .

The memory 111 , storage controller 112 , processor 113 , peripheral interface 114 , and audio unit 115 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The video fire detection device 110 includes at least one software function module that can be stored in the memory 111 in the form of software or firmware (firmware) or solidified in the operating system (operating system, OS) of the data source 100 . The processor 113 is configured to execute executable modules stored in the memory 111 , such as software function modules or computer programs included in the video fire detection device 110 .

Wherein, memory 111 can be, but not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable Read-only memory (Erasable Programmable Read-Only Memory, EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Wherein, the memory 111 is used to store a program, and the processor 113 executes the program after receiving an execution instruction.

The processor 113 may be an integrated circuit chip with signal processing capability. Above-mentioned processor 113 can be general-purpose processor, comprises central processing unit (Central Processing Unit, be called for short CPU), network processor (Network Processor, be called for short NP) etc.; Can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor, or the processor 113 may be any conventional processor or the like.

The peripheral interface 114 couples various input/output devices (such as an audio unit 115 ) to the processor 113 and the memory 111 . In some embodiments, peripherals interface 114, processor 113, and memory controller 112 may be implemented in a single chip. In some other examples, they can be implemented by independent chips respectively.

The audio unit 115 provides an audio interface to the user, which may include one or more microphones, one or more speakers, and audio circuits.

As shown in FIG. 3 , it is a schematic diagram of the functional modules of the video fire detection device 110 provided by the preferred embodiment of the present invention. The video fire detection device 110 is applied to the data source 100, and the video fire detection device 110 includes a video acquisition module 1101, an image conversion module 1102, a mask construction module 1103, a denoising module 1104, a contour detection module 1105, an alarm module 1106, An identification module 1107 and a sending module 1108 .

The video capture module 1101 is used to extract video images captured by the camera.

The image conversion module 1102 is used to convert the video image into an HSV (Hue, Saturation, Value) image. Generally, the image obtained from the video is an image in RGB format, and RGB image is not suitable for image segmentation and feature extraction. HSV is a color space created according to the intuitive characteristics of color, H means hue, S means saturation, V means color The brightness information of the RGB image is converted to the HSV image, which is beneficial to image segmentation and feature extraction.

The mask construction module 1103 is configured to construct a mask of the HSV image according to a preset HSV threshold range. In this embodiment, the HSV image is binarized so that the entire image has only two states of black and white, presenting an obvious black and white effect.

In a preferred embodiment of the present invention, presetting the HSV threshold range is exactly to set the range from the HSV threshold to the flame color, which includes the HSV threshold upper limit and the HSV threshold lower limit. In the present embodiment, the threshold range of HSV is passed through in OpenCV In the HSV color space, it is obtained through experiments. Through experimental testing, the HSV value of the flame when a fire occurs is [5,150,150]. Therefore, in this embodiment, the upper limit of the HSV threshold can be set to [130,255,255], and the lower limit of the HSV threshold is [120, 100, 100], it should be noted that the upper and lower limits of the HSV threshold range are set according to actual needs, for example, the upper limit of the HSV threshold can also be set to [125, 255, 255], and the lower limit is [110, 100, 100], which is not limited in this embodiment. When constructing the mask, if the HSV value is within the preset HSV threshold range, this part of the image is white; if the HSV value is greater than the preset HSV threshold upper limit or less than the preset HSV threshold lower limit, then this part Part of the image appears black.

The denoising module 1104 is used to perform opening and closing operations on the constructed mask to eliminate image noise. In this embodiment, since some random noises such as isolated points will appear when constructing the mask, which will affect the flame detection and cause errors, this embodiment can better eliminate these random noises through the denoising module 1104 Brings effects that improve the extraction effect of the flame area.

The contour detection module 1105 is configured to perform contour detection on the mask, and when the contour is detected, it is determined that a fire has occurred.

In a preferred embodiment of the present invention, if the denoised mask presents an obvious black and white effect, the contour detection module 1105 draws the outer contour of the white area, which is the flame area.

The alarm module 1106 is used for sending out an alarm signal when it is detected that the mask has an outline. In this embodiment, when an outline of the mask is detected, the alarm module 1106 invokes an alarm program to drive the audio unit 115, and the audio unit 115 sends out an alarm signal to remind the user of a fire. At the same time, when it is detected that the mask has an outline, the identification module 1107 identifies the area of the video image corresponding to the outline. In a preferred embodiment of the present invention, the area is identified by drawing a rectangular frame surrounding the outline, that is to say, the area surrounded by the rectangular frame is the flame area, and by marking the flame area, it is convenient for users to view flame zone.

The sending module 1108 is configured to send the video image to the server 200 so that the server 200 forwards the video image to the client 300 so that the client 300 can display the video image. When the outline detection module 1105 did not detect an outline, the video image sent by the sending module 1108 was the video image extracted by the video acquisition module 1101; when the outline detection module 1105 detected an outline, the sending module 1108 sent The video image of is the video image obtained after being processed by the identification module 1107 to identify the flame area.

As shown in FIG. 4 , it is a schematic flowchart of a video fire detection method provided by a preferred embodiment of the present invention. It should be noted that the video fire detection method described in the present invention is not limited to the specific order shown in FIG. 3 and described below. It should be understood that in other embodiments, the order of some steps in the video fire detection method of the present invention may be exchanged according to actual needs, or some steps may be omitted or deleted. The specific process shown in FIG. 3 will be described in detail below.

Step S101, extract video images. The video image is collected by a camera. Wherein, the step S101 can be realized by the video collection module 1101 .

Step S102, converting the video image into an HSV (Hue, Saturation, Value) image. Generally, the image obtained from the video is an image in RGB format, and RGB image is not suitable for image segmentation and feature extraction. HSV is a color space created according to the intuitive characteristics of color, H means hue, S means saturation, V means color The brightness information of the RGB image is converted to the HSV image, which is beneficial to image segmentation and feature extraction. Wherein, the step S102 can be implemented by the image conversion module 1102 .

Step S103, constructing a mask of the HSV image according to a preset HSV threshold range. In this embodiment, the HSV image is binarized so that the entire image has only two states of black and white, presenting an obvious black and white effect. Presetting the HSV threshold range is exactly to set the range from the HSV threshold to the flame color, which includes the upper limit of the HSV threshold and the lower limit of the HSV threshold. In the present embodiment, the threshold range of HSV is obtained through experiments in the HSV color space of OpenCV. According to the test, the HSV value of the flame when the fire broke out was [5, 150, 150], so in this embodiment, the upper limit of the HSV threshold can be set to [130, 255, 255], and the lower limit of the HSV threshold is [120, 100, 100]. It should be noted that the HSV The upper and lower limits of the threshold range are set according to actual needs. For example, the upper limit of the fire HSV threshold can be set to [125, 255, 255] and the lower limit to [110, 100, 100], which is not limited in this embodiment. When constructing the mask, if the HSV value is within the preset HSV threshold range, this part of the image is white; if the HSV value is greater than the preset HSV threshold upper limit or less than the preset HSV threshold lower limit, then this part Part of the image appears black. Wherein, the step S103 can be realized by the mask construction module 1103 .

Step S104, performing an opening operation and a closing operation on the constructed mask to eliminate image noise. In this embodiment, since some random noises such as isolated points will appear when constructing the mask, which will affect the flame detection and cause errors, this embodiment can better eliminate these random noises by opening and closing operations. The effect of noise improves the extraction effect of the flame area. Wherein, the step S104 can be implemented by the denoising module 1104 .

In step S105, contour detection is performed on the mask, and when the contour is detected, it is determined that a fire has occurred. In a preferred embodiment of the present invention, if the denoised mask shows an obvious black and white effect, the outline of the white area in the mask is drawn, and the white area is the flame area. Wherein, the step S105 can be realized by the contour detection module 1105 .

Step S106, when it is detected that the mask has an outline, an alarm signal is sent. In this embodiment, when an outline of the mask is detected, an alarm program is invoked to drive the audio unit 115, and the audio unit 115 sends out an alarm signal to remind the user of a fire. Wherein, the step S106 can be realized by the alarm module 1106 .

Step S107, when it is detected that the mask has an outline, mark the area of the video image corresponding to the outline. In a preferred embodiment of the present invention, the area is identified by drawing a rectangular frame surrounding the outline, that is to say, the area surrounded by the rectangular frame is the flame area, and by marking the flame area, it is convenient for users to view flame zone. Wherein, the step S107 can be realized by the identification module 1107 .

Step S108 , sending the video image to the server 200 so that the server 200 forwards the video image to the client 300 so that the client 300 can display the video image. When the step S105 does not detect the outline, the video image sent in the step S108 is the video image extracted in the step S101; when the step S105 detects the outline, the video image sent in the step S108 is The video image that identifies the flame area is obtained after the processing in step S107. Wherein, the step S108 can be implemented by the sending module 1108 .

In summary, the video fire detection method, device and system provided by the present invention extract the video image through the data source, convert the video image into an HSV image, and construct the mask of the HSV image according to the preset HSV threshold range. The mask performs contour detection, and when a contour is detected, it is determined that a fire has occurred, and the video image is sent to the server, and the server forwards the video image to the client, and the client displays the video image. In addition, when an outline is detected, an alarm signal will be sent to remind the user of a fire, and at the same time, a rectangular frame will be used to mark the flame area on the video image before sending it out; when no outline is detected, the data source will The collected video images are sent out.

In the embodiments provided in this application, it should be understood that the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions and possible implementations of devices, methods and computer program products according to multiple embodiments of the present invention. operate. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

In addition, each functional module in the embodiment of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. . It should be noted that, in this document, the terms "comprising", "comprising" or any other variation thereof are intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention. It should be noted that like numerals and letters denote similar items in the following figures, therefore, once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. a kind of video fire hazard detecting system, it is characterised in that the video fire hazard detecting system includes data source, server And client, wherein,

The data source is used to extract video image, the video image is converted into HSV images, according to set in advance HSV threshold ranges build the mask of the HSV images, and opening operation and closed operation are carried out to the mask, eliminate picture noise, right Eliminating the mask of noise carries out contour detecting, when detecting that the mask has profile, to the corresponding video image of the profile Region be identified, the data source is additionally operable to for the video image to be sent to the server；

The server is used to for the video image to be transmitted to the client；

The client is used to show the video image.

2. video fire hazard detecting system according to claim 1, it is characterised in that the data source is additionally operable to when detection When going out the mask and having profile, alarm signal is sent.

3. a kind of video fire hazard detection method, it is characterised in that the video fire hazard detection method includes：

Extract video image；

The video image is converted into HSV images；

The mask of the HSV images is built according to HSV threshold ranges set in advance；

Contour detecting is carried out to the mask, when profile is detected, then judges the condition of a fire；

Video image is sent to server, the video image is forwarded into client in order to the server, with by institute State client and show the video image.

4. video fire hazard detection method according to claim 3, it is characterised in that described that profile inspection is carried out to the mask Also include step before the step of survey：

Opening operation and closed operation are carried out to the mask, picture noise is eliminated.

5. video fire hazard detection method according to claim 3, it is characterised in that the video fire hazard detection method is also wrapped Include：

When detecting that the mask has profile, alarm signal is sent.

6. video fire hazard detection method according to claim 3, it is characterised in that the video fire hazard detection method is also wrapped Include：

When detecting that the mask has profile, the region of the corresponding video image of the profile is identified.

7. a kind of video fire hazard detection means, is applied to data source, it is characterised in that the video fire hazard detection means bag Include：

Video acquisition module, for extracting video image；

Image conversion module, for the video image to be converted into HSV images；

Mask builds module, for building the mask of the HSV images according to HSV threshold ranges set in advance；

Profile detection module, for carrying out contour detecting to the mask, when profile is detected, then judges the condition of a fire；

Sending module, for video image to be sent to server, visitor is forwarded in order to the server by the video image Family end, to show the video image by the client.

8. video fire hazard detection means according to claim 7, it is characterised in that the video fire hazard detection means is also wrapped Include：

Denoising module, for carrying out opening operation and closed operation to the mask, eliminates picture noise.

9. video fire hazard detection means according to claim 7, it is characterised in that the video fire hazard detection means is also wrapped Include：

Alarm module, for when detecting that the mask has profile, sending alarm signal.

10. video fire hazard detection means according to claim 7, it is characterised in that the video fire hazard detection means is also Including：

Mark module, for when detecting that the mask has profile, carrying out to the region of the corresponding video image of the profile Mark.