CN102915612B - Based on the video analytic system of video image analysis flame detecting device - Google Patents
Based on the video analytic system of video image analysis flame detecting device Download PDFInfo
- Publication number
- CN102915612B CN102915612B CN201210460262.7A CN201210460262A CN102915612B CN 102915612 B CN102915612 B CN 102915612B CN 201210460262 A CN201210460262 A CN 201210460262A CN 102915612 B CN102915612 B CN 102915612B
- Authority
- CN
- China
- Prior art keywords
- module
- video image
- video
- flame
- virtual camera
- 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.)
- Expired - Fee Related
Links
- 238000010191 image analysis Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000779 smoke Substances 0.000 description 4
- 230000002265 prevention Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Landscapes
- Fire-Detection Mechanisms (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
本发明公开了一种基于视频图像分析的火灾检测装置，包括用于采集视频图像的采集系统、视频图像分析系统、火灾告警系统，所述视频图像分析系统包括四个模块：视频图像预处理模块、移动目标识别模块、火焰像素识别模块、火灾判断模块，所述视频图像预处理模块，包括真实摄像头系统，包括真实摄像头、第一驱动程序模块和第一？DirectShow组件；虚拟摄像头系统，包括利用DSF构架模拟出的虚拟摄像头、第二驱动程序模块和第二DirectShow组件；视频处理模块，从第一DirectShow组件读取数据，对数据进行特效处理，传送给虚拟摄像头。本发明具有较高的火焰识别精确度，适应范围广的优点。<!--1-->
The invention discloses a fire detection device based on video image analysis, which includes a video image acquisition system, a video image analysis system, and a fire alarm system. The video image analysis system includes four modules: a video image preprocessing module , a moving target identification module, a flame pixel identification module, and a fire judgment module, the video image preprocessing module includes a real camera system, including a real camera, a first driver module and a first? DirectShow component; virtual camera system, including the virtual camera simulated by DSF framework, the second driver module and the second DirectShow component; the video processing module, which reads data from the first DirectShow component, performs special effect processing on the data, and transmits it to the virtual Camera. The invention has the advantages of high flame identification accuracy and wide application range. <!--1-->
Description
技术领域 technical field
本发明涉及一种基于视频图像分析火焰检测装置的视频分析系统，尤其是通过对实时采集的视频图像中像素颜色特征的分析，来进行火焰探测和告警，属于智能火灾监控的技术领域。 The invention relates to a video analysis system based on a video image analysis flame detection device, in particular to perform flame detection and alarm by analyzing pixel color features in a video image collected in real time, and belongs to the technical field of intelligent fire monitoring.
背景技术 Background technique
火灾监控和预警装置系统在许多领域，包括大型建筑物防火，森林防火，自然环境监测中，起着非常重要的作用。传统的火灾监测技术和装置包括粒子型烟雾传感器、红外线和激光技术等。粒子型烟雾传感器需要烟雾颗粒进入传感器才能引起报警，红外线和激光技术也需要烟雾遮挡才能引发报警，另外，对大型空间的建筑物和室外环境，需要布局大量的传感器设备才能达到较高的监控覆盖率和监测精度，造成成本上升。 Fire monitoring and early warning device systems play a very important role in many fields, including large building fire prevention, forest fire prevention, and natural environment monitoring. Traditional fire monitoring technologies and devices include particle-type smoke sensors, infrared and laser technologies, etc. Particle-type smoke sensors require smoke particles to enter the sensor to cause an alarm. Infrared and laser technology also require smoke occlusion to trigger an alarm. In addition, for large-scale buildings and outdoor environments, a large number of sensor devices need to be deployed to achieve high monitoring coverage. rate and monitoring accuracy, resulting in rising costs.
近年来随着视频监控系统和计算机视觉识别技术的发展和提高，基于视频图像分析的火灾检测系统正有取代传统装置的趋势，尤其在大型建筑物防火和室外环境监测中。在基于视频图像的火灾检测系统的现有技术中，许多方法被提出和采用。在这些方法中，基于视频图像分析的火焰探测方法分为两个主要模块：移动目标的识别和分割，火焰特征分析。经过移动目标的识别和分割处理的图像像素数据输入到火焰特征分析模块，通过对移动目标的颜色、形状和跳动形式等特征进行分析，以及和火焰特有的特征进行分析对比，来达到火焰识别和检测的目的。然而，在这些方法中，一些算法采用传统的颜色空间例如RGB和YUV进行火焰颜色特征识别，误判率较高；一些算法首先执行火焰特征分析，再进行移动目标识别，造成计算速度较慢，运行成本较高。而另外一些算法针对火焰形状等动态特征进行分析和检测，算法架构复杂且误判率较高。 In recent years, with the development and improvement of video surveillance systems and computer vision recognition technology, fire detection systems based on video image analysis are tending to replace traditional devices, especially in large-scale building fire prevention and outdoor environment monitoring. In the prior art of fire detection systems based on video images, many methods have been proposed and adopted. Among these methods, the flame detection method based on video image analysis is divided into two main modules: recognition and segmentation of moving targets, and flame feature analysis. The image pixel data processed by the identification and segmentation of the moving target is input to the flame feature analysis module. By analyzing the color, shape and jumping form of the moving target, and analyzing and comparing with the unique features of the flame, flame recognition and recognition are achieved. purpose of detection. However, in these methods, some algorithms use traditional color spaces such as RGB and YUV for flame color feature recognition, and the misjudgment rate is high; some algorithms first perform flame feature analysis, and then perform moving target recognition, resulting in slow calculation speed. Higher operating costs. While other algorithms analyze and detect dynamic features such as flame shape, the algorithm structure is complex and the misjudgment rate is high.
发明内容 Contents of the invention
本发明的目的是克服现有技术中存在的不足，提供一种基于视频图像分析火焰检测装置的视频分析系统，本装置是通过对实时采集的视频图像中像素颜色特征在另外一种颜色空间上的分析，来提高火灾检测和预警的精度，同时采用火焰检测和移动目标检测并行处理的方式，来提高火灾检测的处理速度。 The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a video analysis system based on video image analysis flame detection device. In order to improve the accuracy of fire detection and early warning, the parallel processing of flame detection and moving object detection is adopted to improve the processing speed of fire detection.
本发明提供的技术方案，基于视频图像分析火焰检测装置的视频分析系统，包括视频图像预处理模块，视频图像预处理模块，移动目标识别模块，火焰像素识别模块，和火灾判断模块；所述视频图像预处理模块，包括真实摄像头系统，包括真实摄像头、第一驱动程序模块和第一DirectShow组件；虚拟摄像头系统，包括利用DSF构架模拟出的虚拟摄像头、第二驱动程序模块和第二DirectShow组件；视频处理模块，从第一DirectShow组件读取数据，对数据进行特效处理，传送给虚拟摄像头。 The technical solution provided by the present invention is a video analysis system based on a video image analysis flame detection device, including a video image preprocessing module, a video image preprocessing module, a moving target identification module, a flame pixel identification module, and a fire judgment module; The image preprocessing module includes a real camera system, including a real camera, a first driver module and a first DirectShow component; a virtual camera system, including a simulated virtual camera using the DSF framework, a second driver module and a second DirectShow component; The video processing module reads data from the first DirectShow component, performs special effect processing on the data, and transmits the data to the virtual camera.
本发明的优点：采用将采集的视频图像从RGB颜色空间转换为CIExyY颜色空间，通过和标定的标准火焰颜色在CIExy色度图上的分布特征对比，来达到火焰像素的识别。CIExy是一种设备独立的线性颜色空间，在本质上更能精确地表述颜色特征。标准火焰颜色在CIExy色度图上有明显的分辨性和独特性。所以本发明有较高的火焰检测精确度。另外由于本发明采用火焰检测和移动目标检测并行处理的方式，火灾检测运行反应速度快，适应范围广。 The invention has the advantages of converting the collected video image from the RGB color space to the CIExyY color space, and by comparing with the distribution characteristics of the calibrated standard flame color on the CIExy chromaticity diagram, the recognition of flame pixels is achieved. CIExy is a device-independent linear color space that is inherently more accurate in expressing color characteristics. The standard flame color has obvious discrimination and uniqueness on the CIExy chromaticity diagram. Therefore, the present invention has higher flame detection accuracy. In addition, because the present invention adopts the mode of parallel processing of flame detection and moving target detection, the fire detection operation has fast response speed and wide application range.
附图说明 Description of drawings
图1为本发明结构示意图。 Fig. 1 is a schematic diagram of the structure of the present invention.
图2为本发明中视频图像预处理模块的结构示意图。 FIG. 2 is a schematic structural diagram of a video image preprocessing module in the present invention.
具体实施方式 Detailed ways
下面结合具体附图和实施对本发明作进一步说明。 The present invention will be further described below in conjunction with specific drawings and implementation.
如图1所示，本发明的系统装置示意图。本发明包括用于采集视频图像的采集系统301，视频图像分析系统302，火灾告警系统307，视频图像分析系统包括四个模块：视频图像预处理模块303，移动目标识别模块304，火焰像素识别模块305，和火灾判断模块306。 As shown in FIG. 1 , a schematic diagram of the system device of the present invention. The present invention includes a collection system 301 for collecting video images, a video image analysis system 302, and a fire alarm system 307. The video image analysis system includes four modules: a video image preprocessing module 303, a moving target recognition module 304, and a flame pixel recognition module 305, and a fire judgment module 306.
视频图像采集系统301可以是模拟式摄像机，也可以是IP摄像机，来保证能连续不断采集当前监控场景图像并输入到视频图像分析系统302。视频图像分析系统302位于计算机系统内，对采集的视频图像进行处理和分析，并作出是否有火灾发生的判断。首先，视频图像分系统302通过预处理模块303对图像图像颜色空间转换等预处理。视频图像预处理模块303，包括真实摄像头系统1，包括真实摄像头11、第一驱动程序模块12和第一DirectShow组件12；虚拟摄像头系统2，包括利用DSF构架模拟出的虚拟摄像头21、第二驱动程序模块22和第二DirectShow组件23；视频处理模块3，从第一DirectShow组件12读取数据，对数据进行特效处理，传送给虚拟摄像头21。经过颜色空间转换后的视频图像数据分别输入到两个并行处理模块：移动目标识别模块304和火焰像素识别模块305。这种并行处理不同于传统的串行处理，可大大加快火灾判断的处理和反应速度。移动目标识别模块304还包括一帧背景图像缓存器。火焰像素识别模块305还包括事先标定的标准火焰颜色数据图。火灾判断模块306接受移动目标识别模块304和火焰像素识别模块305的输出结果，来作出是否有火灾发生的判断，并将火灾预警信号输入到火灾预警系统307。火灾预警系统307为常规的火灾预警系统，火灾预警系统307的作用及结构为本技术领域人员所熟知，此处不再详述。 The video image acquisition system 301 can be an analog camera or an IP camera, so as to ensure that images of the current monitoring scene can be continuously collected and input to the video image analysis system 302 . The video image analysis system 302 is located in the computer system, processes and analyzes the collected video images, and makes a judgment on whether there is a fire. First, the video image subsystem 302 preprocesses the image, such as image color space conversion, through the preprocessing module 303 . Video image preprocessing module 303, comprises real camera system 1, comprises real camera 11, first driver module 12 and first DirectShow component 12; Virtual camera system 2, comprises the virtual camera 21 that utilizes DSF framework simulation, the second driver The program module 22 and the second DirectShow component 23 ; the video processing module 3 reads data from the first DirectShow component 12 , performs special effect processing on the data, and transmits it to the virtual camera 21 . The video image data after color space conversion are respectively input into two parallel processing modules: moving object recognition module 304 and flame pixel recognition module 305 . This kind of parallel processing is different from traditional serial processing, which can greatly speed up the processing and response speed of fire judgment. The moving object identification module 304 also includes a buffer for a frame of background image. The flame pixel identification module 305 also includes a pre-calibrated standard flame color data map. The fire judging module 306 accepts the output results of the moving object recognition module 304 and the flame pixel recognition module 305 to judge whether there is a fire, and inputs the fire warning signal to the fire warning system 307 . The fire early warning system 307 is a conventional fire early warning system. The function and structure of the fire early warning system 307 are well known to those skilled in the art, and will not be described in detail here.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210460262.7A CN102915612B (en) | 2012-11-15 | 2012-11-15 | Based on the video analytic system of video image analysis flame detecting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210460262.7A CN102915612B (en) | 2012-11-15 | 2012-11-15 | Based on the video analytic system of video image analysis flame detecting device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102915612A CN102915612A (en) | 2013-02-06 |
| CN102915612B true CN102915612B (en) | 2015-12-23 |
Family
ID=47613958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210460262.7A Expired - Fee Related CN102915612B (en) | 2012-11-15 | 2012-11-15 | Based on the video analytic system of video image analysis flame detecting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102915612B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101046908A (en) * | 2007-05-08 | 2007-10-03 | 中国科学院上海技术物理研究所 | Forest fire behavior dynamic monitoring alarm system based on infrared camera |
| CN101339602A (en) * | 2008-07-15 | 2009-01-07 | 中国科学技术大学 | A video fire smoke image recognition method based on optical flow method |
| CN101493980A (en) * | 2009-03-05 | 2009-07-29 | 中国科学技术大学 | Rapid video flame detection method based on multi-characteristic fusion |
| CN102208018A (en) * | 2011-06-01 | 2011-10-05 | 西安工程大学 | Method for recognizing fire disaster of power transmission line based on video variance analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0709329D0 (en) * | 2007-05-15 | 2007-06-20 | Ipsotek Ltd | Data processing apparatus |
-
2012
- 2012-11-15 CN CN201210460262.7A patent/CN102915612B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101046908A (en) * | 2007-05-08 | 2007-10-03 | 中国科学院上海技术物理研究所 | Forest fire behavior dynamic monitoring alarm system based on infrared camera |
| CN101339602A (en) * | 2008-07-15 | 2009-01-07 | 中国科学技术大学 | A video fire smoke image recognition method based on optical flow method |
| CN101493980A (en) * | 2009-03-05 | 2009-07-29 | 中国科学技术大学 | Rapid video flame detection method based on multi-characteristic fusion |
| CN102208018A (en) * | 2011-06-01 | 2011-10-05 | 西安工程大学 | Method for recognizing fire disaster of power transmission line based on video variance analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102915612A (en) | 2013-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108447219A (en) | System and method for detecting fire hazard based on video image | |
| JP4705090B2 (en) | Smoke sensing device and method | |
| binti Zaidi et al. | Fire recognition using RGB and YCbCr color space | |
| CN105575034B (en) | A kind of two waveband forest fire protection intelligent monitoring software image processing analysis method | |
| CN105574468B (en) | Video flame detection method, device and system | |
| CN111476964A (en) | Remote forest fire prevention monitoring system and method | |
| CN104504382B (en) | A kind of flame identification algorithm based on image processing techniques | |
| CN101715070B (en) | Method for automatically updating background in specifically monitored video | |
| CN106778488B (en) | Low illumination smoke video detection method based on image correlation | |
| CN103020588B (en) | Flame Detection Method Based on Video Image Analysis | |
| CN103150736A (en) | Camera motion detecting method based on video monitoring | |
| CN101315326B (en) | Smoke detection method and device | |
| CN117789105A (en) | Complex scene fire detection method based on multi-feature extraction | |
| CN101930540A (en) | Video-based multi-feature fusion flame detecting device and method | |
| CN103020587B (en) | Based on video image analysis flame regarding figure analysis method | |
| CN102999994A (en) | Flame detection device based on video image analysis | |
| CN105869184B (en) | Forest fires smog image detecting method based on path analysis | |
| CN108648406A (en) | A kind of indoor smog detection alarm system based on machine vision | |
| CN107748011A (en) | The test system and method for testing of medium-wave infrared detector image-forming time delay | |
| CN102915612B (en) | Based on the video analytic system of video image analysis flame detecting device | |
| CN108765833A (en) | Based on the incipient fire detection algorithm for improving mixed Gaussian and machine learning | |
| CN106898014A (en) | A kind of intrusion detection method based on depth camera | |
| CN107967448B (en) | Early fire smoke real-time detection method and system | |
| CN103106392B (en) | The video image analysis system of flame detecting device | |
| CN104933739B (en) | A kind of flame detecting method based on I1I2I3 color spaces |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151223 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |