CN103150549B - A kind of road tunnel fire detection method based on the early stage motion feature of smog - Google Patents
A kind of road tunnel fire detection method based on the early stage motion feature of smog Download PDFInfo
- Publication number
- CN103150549B CN103150549B CN201310044830.XA CN201310044830A CN103150549B CN 103150549 B CN103150549 B CN 103150549B CN 201310044830 A CN201310044830 A CN 201310044830A CN 103150549 B CN103150549 B CN 103150549B
- Authority
- CN
- China
- Prior art keywords
- block
- image
- area
- target
- background
- 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.)
- Active
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 239000000779 smoke Substances 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000005484 gravity Effects 0.000 claims description 4
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
本发明提供了一种基于烟雾早期运动特征的公路隧道火灾检测方法，通过获取背景图像，划分块，求取计算块和背景块的灰度差值的绝对值之和并赋值得到二值化图像，标定出检测区域，得到检测目标的连通域，重复上述过程，得到疑似烟雾区域，对该区域逆向进行跟踪匹配处理，最终确定该检测目标是否为烟雾，此处是否发生了火灾。本发明的火灾检测方法，与现有技术相比，可对视频监控范围内发生的火灾事件进行检测，不受环境限制，能够实时对视频进行检测，且检测时间短、易于实现、准确性较高，适合于实时检测公路隧道火灾事件，具有广阔的应用前景。
The invention provides a road tunnel fire detection method based on the early movement characteristics of the smoke, by obtaining the background image, dividing the blocks, calculating the sum of the absolute values of the gray difference between the calculation block and the background block, and assigning a value to obtain a binarized image , the detection area is calibrated, the connected domain of the detection target is obtained, the above process is repeated, and the suspected smoke area is obtained, and the reverse tracking and matching process is performed on the area to finally determine whether the detection target is smoke and whether a fire has occurred here. Compared with the prior art, the fire detection method of the present invention can detect fire events occurring within the scope of video surveillance, without being restricted by the environment, and can detect video in real time, and the detection time is short, easy to implement, and relatively accurate. High, suitable for real-time detection of road tunnel fire events, and has broad application prospects.
Description
技术领域technical field
本发明属于视频检测领域，具体涉及一种基于烟雾早期运动特征的公路隧道火灾检测方法。The invention belongs to the field of video detection, and in particular relates to a road tunnel fire detection method based on the early motion characteristics of smoke.
背景技术Background technique
近年来,公路隧道的安全问题日益为世人所关注，在公路隧道发生的安全事故中，火灾是危害最大的一类。但在这种大空间、大面积、环境比较恶劣的场所，传统的火灾探测器无法及时地进行火灾报警，而且也不能提供诸如着火的具体位置、规模、火焰的扩散程度等信息，给营救工作带来了诸多不便，导致了严重的经济损失和人员伤亡。误报警现象也时有发生。In recent years, the safety problems of road tunnels have been paid more and more attention to by the world. Among the safety accidents in road tunnels, fire is the most harmful type. However, in such places with large spaces, large areas, and relatively harsh environments, traditional fire detectors cannot provide fire alarms in a timely manner, and cannot provide information such as the specific location, scale, and spread of flames, etc., for rescue work. It has brought a lot of inconvenience and caused serious economic losses and casualties. False alarms also occur from time to time.
随着计算机技术和机器视觉技术的迅速发展，产生了一种全新的火灾探测器，即基于视频的火灾检测系统。目前，图像型火灾烟雾探测技术相对与传统的火灾探测技术仍然处于起步阶段。已有的技术为：通过烟雾纹理自相似性检测烟雾；结合隐马尔可夫模型对烟雾场景边缘信息变化进行建模，从而判断场景中是否有烟雾的存在；根据烟雾的光谱特征判断是否有烟雾的存在等。但是隧道环境比较复杂，色调比较灰暗，灯光的影响尤为显著，仅通过纹理来检测烟雾并不准确，边缘特征也不明显。With the rapid development of computer technology and machine vision technology, a brand-new fire detector has emerged, that is, a video-based fire detection system. At present, image-based fire smoke detection technology is still in its infancy compared with traditional fire detection technology. Existing technologies are: detecting smoke through the self-similarity of smoke texture; combining the hidden Markov model to model the edge information changes of the smoke scene, so as to judge whether there is smoke in the scene; judge whether there is smoke according to the spectral characteristics of smoke existence etc. However, the tunnel environment is relatively complex, the color tone is relatively dark, and the influence of light is particularly significant. It is not accurate to detect smoke only through texture, and the edge features are not obvious.
发明内容Contents of the invention
针对现有技术的不足和缺陷，本发明的目的在于，提供一种基于烟雾早起运动特征的公路隧道火灾检测方法，该方法可以对视频范围内发生的火灾事件进行实时、可靠的检测。Aiming at the deficiencies and defects of the prior art, the object of the present invention is to provide a fire detection method in road tunnels based on smoke early movement characteristics, which can detect fire events occurring within the video range in real time and reliably.
为了实现上述任务，本发明采用如下技术方案予以实现：In order to realize above-mentioned task, the present invention adopts following technical scheme to realize:
一种基于烟雾早期运动特征的公路隧道火灾检测方法，该方法按照以下步骤进行：A fire detection method for road tunnels based on the early movement characteristics of smoke, the method is carried out according to the following steps:
步骤一，通过摄像机采集实时图像，获取并更新该图像的背景，即背景图像；Step 1, collect a real-time image through the camera, acquire and update the background of the image, that is, the background image;
步骤二，将第一帧图像和第一帧图像的背景图像在相同的块坐标系下都划分成多个块；Step 2, dividing the first frame image and the background image of the first frame image into multiple blocks under the same block coordinate system;
步骤三，对第一帧图像中的每个块，在背景图像中找到与该块位置相同的背景块，并计算该块与其相应的背景块之间各相同像素位置处的灰度差值的绝对值之和；Step 3: For each block in the first frame image, find the background block in the background image with the same position as the block, and calculate the gray value difference between the block and the corresponding background block at the same pixel position sum of absolute values;
当所得的绝对值之和大于设定的阈值A，所述的阈值A的取值为（3/4）×块的面积×255，则该块为目标块，将该目标块内所有像素的灰度值赋值为255；When the sum of the obtained absolute values is greater than the set threshold A, the value of the threshold A is (3/4)×area of the block×255, then the block is the target block, and all pixels in the target block The gray value assignment is 255;
当所得的绝对值之和小于或等于设定的阈值A，则该块为背景块，将背景块内所有像素的灰度值赋值为0；When the sum of the obtained absolute values is less than or equal to the set threshold A, the block is a background block, and the gray value of all pixels in the background block is assigned a value of 0;
最后将第一帧图像中的背景与目标分离开，得到第一帧图像的二值化图像；Finally, the background in the first frame image is separated from the target to obtain the binarized image of the first frame image;
步骤四，对于第一帧图像的二值化图像，在图像的上半区域标定出检测区域，对检测区域内出现的目标块进行连通域标记，将相邻的目标块标记为同一目标，得到检测目标的连通域，并确定和记录边界；Step 4, for the binarized image of the first frame image, mark the detection area in the upper half of the image, mark the connected domains of the target blocks appearing in the detection area, and mark the adjacent target blocks as the same target, and obtain Detect connected domains of objects, and determine and record boundaries;
步骤五，重复步骤二、步骤三和步骤四的方法对从第二帧图像起的所有连续的图像进行处理；Step 5, repeat the method of step 2, step 3 and step 4 to process all continuous images from the second frame image;
步骤六，当连续n帧图像检测出来的某一连通域的上下边界与检测区域的上下边界重合，并且重心位置的偏移量小于一定距离L，则将该目标区域作为疑似烟雾区域，其中：Step 6, when the upper and lower boundaries of a connected domain detected by consecutive n frames of images coincide with the upper and lower boundaries of the detection area, and the offset of the center of gravity is less than a certain distance L, the target area is regarded as a suspected smoke area, where:
n∈[80,100]，n为正整数；n∈[80,100], n is a positive integer;
L的取值为步骤二中所划分的块的宽度的5倍；The value of L is 5 times the width of the block divided in step 2;
步骤七，当连续n帧图像中第i帧图像检测出疑似烟雾区域，逆向进行跟踪匹配处理，获取第i-j(i>j，i和j均为正整数)帧的灰度图像，将目标区域重新分成m’×n’的小块每一小块作为一个模板，认为小块内各个像素的运动保持一致，并以每个小块的中心为起始点在待搜索图像中划定搜索范围，遍历搜索区域中的位置，计算以各个位置为中心且大小同样为m’×n’的小块与模板的相似度，与模板最相似的小块即为匹配块，并记录模板运动的方向，同时将匹配块作为下一次匹配所需要的模板块，将j加2，即待搜索图像与作为模板块的图像相差能够辨别明显运动变化的2帧；Step 7: When a suspected smoke area is detected in the i-th frame image in the n consecutive frames of images, the tracking and matching process is reversed to obtain the grayscale image of the i-jth (i>j, i and j are both positive integers) frames, and the target area Re-divided into m'×n' small blocks, each small block is used as a template, and the motion of each pixel in the small block is considered to be consistent, and the center of each small block is used as the starting point to delineate the search range in the image to be searched, Traverse the positions in the search area, calculate the similarity between the small blocks with the same size of m'×n' centered on each position and the template, the small block most similar to the template is the matching block, and record the direction of the template movement, At the same time, the matching block is used as the template block required for the next match, and j is added by 2, that is, the difference between the image to be searched and the image as the template block can distinguish obvious motion changes by 2 frames;
步骤八，当i>j时，重复步骤七的过程进行处理，当i=j时，匹配结束，得到每一个匹配块的运动方向，选取频率最高的作为目标区域块的运动主方向，当有3/4的目标块的运动主方向处于45°角和135°角之间，即该检测目标为烟雾，此处发生火灾。Step 8, when i>j, repeat the process of step 7 for processing, when i=j, the matching ends, get the movement direction of each matching block, select the one with the highest frequency as the main direction of movement of the target area block, when there is The main direction of movement of 3/4 of the target blocks is between 45° and 135°, that is, the detection target is smoke, and a fire occurs here.
本发明的基于烟雾早期运动特征的公路隧道火灾检测方法，与现有技术相比，可对视频监控范围内发生的火灾事件进行检测，不受环境限制，能够实时对视频进行检测，且检测时间短、易于实现、准确性较高，适合于实时检测公路隧道火灾事件，具有广阔的应用前景。Compared with the prior art, the road tunnel fire detection method based on the early smoke movement characteristics of the present invention can detect fire events within the scope of video surveillance, and is not limited by the environment, and can detect video in real time, and the detection time It is short, easy to implement, and has high accuracy. It is suitable for real-time detection of road tunnel fire events and has broad application prospects.
附图说明Description of drawings
图1为第1帧图像。Figure 1 is the first frame image.
图2为标定了检测区域的图像。Figure 2 is an image with the detection area marked.
图3为烟雾第一次出现的第985帧图像。Figure 3 is the 985th frame image where the smoke first appeared.
图4（a）、图4（b）和图4（c）依次为第1110、1120和1130帧三幅图像的二值化标记图像，图中白色目标为当前帧的二值化标记目标，白色矩形框为连通域边界，大矩形框为烟雾目标，小矩形框为干扰目标。Figure 4(a), Figure 4(b) and Figure 4(c) are the binarized marked images of the three images in the 1110th, 1120th and 1130th frames in turn, and the white target in the figure is the binarized marked target of the current frame, The white rectangle is the boundary of the connected domain, the big rectangle is the smoke target, and the small rectangle is the interference target.
图5为标定了烟雾运动主方向的视频图像，黑线为方向指示，图中大部分目标块的运动主方向处于45°角和135°角之间。Figure 5 is a video image with the main direction of smoke movement marked, the black line is the direction indicator, and the main direction of movement of most of the target blocks in the figure is between 45° and 135°.
以下结合附图和实施例对本发明的内容作进一步详细说明。The content of the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.
具体实施方式detailed description
本实施例给出一种基于烟雾早期运动特征的公路隧道火灾检测方法，通过基于块的二值化分割、连通域标记和目标运动主方向来判别公路隧道是否发生火灾。需要说明的是，本发明的方法过程中所处理的图像是视频中的沿正时间序列的第一帧图像、第二帧图像、第三帧图像、…、第m(m为正整数)帧图像。This embodiment presents a road tunnel fire detection method based on the early motion characteristics of smoke, and judges whether there is a fire in the road tunnel through block-based binarization segmentation, connected domain marking, and the main direction of target motion. It should be noted that the images processed in the method of the present invention are the first frame image, the second frame image, the third frame image, ..., the mth (m is a positive integer) frame along the positive time sequence in the video image.
设每一帧视频图像的大小为W*H，每个块的面积大小为w*h，其中W为每一帧视频视频图像水平方向的像素，H为每一帧视频图像垂直方向的像素，w为每个块区域的宽度，h为每个块区域的高度。Suppose the size of each frame of video image is W*H, and the area size of each block is w*h, wherein W is the pixel in the horizontal direction of each frame of video image, and H is the pixel in the vertical direction of each frame of video image, w is the width of each block area, and h is the height of each block area.
本实施例的方法具体采用以下步骤实现：The method of this embodiment specifically adopts the following steps to realize:
步骤一，通过摄像机采集实时图像，获取并更新该图像的背景，即背景图像；Step 1, collect a real-time image through the camera, acquire and update the background of the image, that is, the background image;
步骤二，将第一帧图像和第一帧图像的背景图像在相同的块坐标系下都划分成多个块；Step 2, dividing the first frame image and the background image of the first frame image into multiple blocks under the same block coordinate system;
步骤三，对第一帧图像中的每个块，在背景图像中找到与该块位置相同的背景块，并计算该块与其相应的背景块之间各相同像素位置处的灰度差值的绝对值之和；Step 3: For each block in the first frame image, find the background block in the background image with the same position as the block, and calculate the gray value difference between the block and the corresponding background block at the same pixel position sum of absolute values;
当所得的绝对值之和大于设定的阈值A，所述的阈值A的取值为（3/4）×（w*h）×255，则该块为目标块，将该目标块内所有像素的灰度值赋值为255；When the sum of the obtained absolute values is greater than the set threshold A, and the value of the threshold A is (3/4)×(w*h)×255, then the block is the target block, and all The gray value of the pixel is assigned a value of 255;
当所得的绝对值之和小于或等于设定的阈值A，则该块为背景块，将背景块内所有像素的灰度值赋值为0；When the sum of the obtained absolute values is less than or equal to the set threshold A, the block is a background block, and the gray value of all pixels in the background block is assigned a value of 0;
最后将第一帧图像中的背景与目标分离开，得到第一帧图像的二值化图像；Finally, the background in the first frame image is separated from the target to obtain the binarized image of the first frame image;
步骤四，对于第一帧图像的二值化图像，在图像的上半区域标定出检测区域，对检测区域内出现的目标块进行连通域标记，将相邻的目标块标记为同一目标，得到检测目标的连通域，并确定和记录边界；Step 4, for the binarized image of the first frame image, mark the detection area in the upper half of the image, mark the connected domains of the target blocks appearing in the detection area, and mark the adjacent target blocks as the same target, and obtain Detect connected domains of objects, and determine and record boundaries;
步骤五，重复步骤二、步骤三和步骤四的方法对从第二帧图像起的所有连续的图像进行处理；Step 5, repeat the method of step 2, step 3 and step 4 to process all continuous images from the second frame image;
步骤六，当连续n帧图像检测出来的某一连通域的上下边界与检测区域的上下边界重合，并且重心位置的偏移量小于一定距离L，则将该目标区域作为疑似烟雾区域，其中：Step 6, when the upper and lower boundaries of a connected domain detected by consecutive n frames of images coincide with the upper and lower boundaries of the detection area, and the offset of the center of gravity is less than a certain distance L, the target area is regarded as a suspected smoke area, where:
n∈[80,100]，n为正整数；n∈[80,100], n is a positive integer;
L的取值为步骤二中所划分的块的宽度的5倍；The value of L is 5 times the width of the block divided in step 2;
步骤七，当连续n帧图像中第i帧图像检测出疑似烟雾区域，逆向进行跟踪匹配处理，获取第i-j(i>j，i和j均为正整数)帧的灰度图像，将目标区域重新分成m’×n’的小块每一小块作为一个模板，认为小块内各个像素的运动保持一致，并以每个小块的中心为起始点在待搜索图像中划定搜索范围，遍历搜索区域中的位置，计算以各个位置为中心且大小同样为m’×n’的小块与模板的相似度，与模板最相似的小块即为匹配块，并记录模板运动的方向，同时将匹配块作为下一次匹配所需要的模板块，将j加2，即待搜索图像与作为模板块的图像相差能够辨别明显运动变化的2帧；Step 7: When a suspected smoke area is detected in the i-th frame image in the n consecutive frames of images, the tracking and matching process is reversed to obtain the grayscale image of the i-jth (i>j, i and j are both positive integers) frames, and the target area Re-divided into m'×n' small blocks, each small block is used as a template, and the motion of each pixel in the small block is considered to be consistent, and the center of each small block is used as the starting point to delineate the search range in the image to be searched, Traverse the positions in the search area, calculate the similarity between the small blocks with the same size of m'×n' centered on each position and the template, the small block most similar to the template is the matching block, and record the direction of the template movement, At the same time, the matching block is used as the template block required for the next match, and j is added by 2, that is, the difference between the image to be searched and the image as the template block can distinguish obvious motion changes by 2 frames;
步骤八，当i>j时，重复步骤七的过程进行处理，当i=j时，匹配结束，得到每一个匹配块的运动方向，选取频率最高的作为目标区域块的运动主方向，当有3/4的目标块的运动主方向处于45°角和135°角之间，即该检测目标为烟雾，此处发生火灾。Step 8, when i>j, repeat the process of step 7 for processing, when i=j, the matching ends, get the movement direction of each matching block, select the one with the highest frequency as the main direction of movement of the target area block, when there is The main direction of movement of 3/4 of the target blocks is between 45° and 135°, that is, the detection target is smoke, and a fire occurs here.
以下给出本发明的具体实施例，需要说明的是本发明并不局限于以下具体实施例，凡在本申请技术方案基础上做的等同变换均落入本发明的保护范围。Specific embodiments of the present invention are provided below, and it should be noted that the present invention is not limited to the following specific embodiments, and all equivalent transformations done on the basis of the technical solutions of the present application all fall within the scope of protection of the present invention.
实施例：Example:
实施例中处理过程中视频的采样频率是25帧每秒，帧图像大小为720×288，每块区域的大小为4×3，将帧图像分成180×96个块区域，目标区域二值化分割阈值为2295，得到疑似目标区域后，将该区域重新分块，每块的大小为5×5，搜索区域为10×12，按照本发明的方法依次对第1帧至第1982帧图像进行处理。The sampling frequency of the video during the processing in the embodiment is 25 frames per second, the size of the frame image is 720×288, and the size of each block area is 4×3, the frame image is divided into 180×96 block areas, and the target area is binarized The segmentation threshold is 2295. After the suspected target area is obtained, the area is re-divided into blocks. The size of each block is 5×5, and the search area is 10×12. According to the method of the present invention, the images from the first frame to the 1982nd frame are sequentially deal with.
已知视频正播时，图1为该视频的第1帧图像；图2为标定了检测区域的图像；烟雾目标第一次出现在第985帧图像中，如图3所示；从图4中可以看出烟雾目标运动的形态特征，自上而下连续不间断的，并且重心偏移量较小，图4（a）、图4（b）和图4（c）依次为第1110、1120和1130帧三幅图像的二值化标记图像，图中白色目标为当前帧的二值化标记目标，白色矩形框为连通域边界，大矩形框为烟雾目标，小矩形框为干扰目标。图5为标定了烟雾运动主方向的视频图像，黑线为方向指示，图中大部分目标块的运动主方向处于45°角和135°角之间。When it is known that the video is being broadcast, Figure 1 is the first frame of the video; Figure 2 is the image with the detection area marked; the smoke target first appears in the 985th frame of the image, as shown in Figure 3; from Figure 4 It can be seen that the morphological characteristics of the smoke target movement are continuous and uninterrupted from top to bottom, and the offset of the center of gravity is small. Figure 4(a), Figure 4(b) and Figure 4(c) are the 1110th, The binarized marked images of the three images at 1120 and 1130 frames, the white target in the figure is the binarized marked target of the current frame, the white rectangular box is the boundary of the connected domain, the large rectangular box is the smoke target, and the small rectangular box is the interference target. Figure 5 is a video image with the main direction of smoke movement marked, the black line is the direction indicator, and the main direction of movement of most of the target blocks in the figure is between 45° and 135°.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310044830.XA CN103150549B (en) | 2013-02-05 | 2013-02-05 | A kind of road tunnel fire detection method based on the early stage motion feature of smog |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310044830.XA CN103150549B (en) | 2013-02-05 | 2013-02-05 | A kind of road tunnel fire detection method based on the early stage motion feature of smog |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103150549A CN103150549A (en) | 2013-06-12 |
| CN103150549B true CN103150549B (en) | 2015-12-02 |
Family
ID=48548612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310044830.XA Active CN103150549B (en) | 2013-02-05 | 2013-02-05 | A kind of road tunnel fire detection method based on the early stage motion feature of smog |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103150549B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400111B (en) * | 2013-07-10 | 2017-02-08 | 重庆大学 | Method for detecting fire accident on expressway or in tunnel based on video detection technology |
| CN103870818B (en) * | 2014-03-31 | 2017-02-15 | 中安消技术有限公司 | Smog detection method and device |
| CN105469069A (en) * | 2015-12-09 | 2016-04-06 | 上海工业自动化仪表研究院 | Safety helmet video detection method for production line data acquisition terminal |
| CN105628192A (en) * | 2015-12-22 | 2016-06-01 | 湖南联智桥隧技术有限公司 | Tunnel ambient exterior luminance detection system and detection method by using detection system |
| CN106228150B (en) * | 2016-08-05 | 2019-06-11 | 南京工程学院 | Video image-based smoke detection method |
| CN106448161A (en) * | 2016-09-30 | 2017-02-22 | 广东中星微电子有限公司 | Road monitoring method and road monitoring device |
| CN107085714B (en) * | 2017-05-09 | 2019-12-24 | 北京理工大学 | A Video-Based Forest Fire Detection Method |
| CN107945209B (en) * | 2017-11-29 | 2021-03-05 | 中国人民解放军火箭军工程大学 | Accurate automatic calibration method of sequence image target point based on reverse structure matching tracking |
| CN110501914B (en) * | 2018-05-18 | 2023-08-11 | 佛山市顺德区美的电热电器制造有限公司 | Security monitoring method, equipment and computer readable storage medium |
| CN108898782B (en) * | 2018-07-20 | 2020-12-11 | 湖北烽火平安智能消防科技有限公司 | Smoke detection method and system for infrared image temperature information identification for tunnel fire prevention |
| CN110749599A (en) * | 2019-09-29 | 2020-02-04 | 四川捷祥医疗器械有限公司 | Method and device for analyzing surgical smoke and storage medium |
| CN112036411B (en) * | 2020-08-26 | 2024-07-02 | 广东宝利建设有限公司 | Method for cyclic error correction of intelligent fire-fighting monitoring and early-warning system |
| CN112447020B (en) * | 2020-12-15 | 2022-08-23 | 杭州六纪科技有限公司 | Efficient real-time video smoke flame detection method |
| CN114648852B (en) * | 2022-05-24 | 2022-08-12 | 四川九通智路科技有限公司 | Tunnel fire monitoring method and system |
| CN116311000A (en) * | 2023-05-16 | 2023-06-23 | 合肥中科类脑智能技术有限公司 | Firework detection method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1349091A (en) * | 2000-10-16 | 2002-05-15 | 中国科学技术大学 | Relative smog density image detector and its detection method |
| CN101395643A (en) * | 2006-09-25 | 2009-03-25 | 西门子瑞士有限公司 | Detection of smoke with a video camera |
| CN101441771A (en) * | 2008-12-19 | 2009-05-27 | 中国科学技术大学 | Video fire hazard smoke detecting method based on color saturation degree and movement mode |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080137906A1 (en) * | 2006-12-12 | 2008-06-12 | Industrial Technology Research Institute | Smoke Detecting Method And Device |
| TWI385602B (en) * | 2008-10-17 | 2013-02-11 | Ind Tech Res Inst | Smoke detection method and system |
-
2013
- 2013-02-05 CN CN201310044830.XA patent/CN103150549B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1349091A (en) * | 2000-10-16 | 2002-05-15 | 中国科学技术大学 | Relative smog density image detector and its detection method |
| CN101395643A (en) * | 2006-09-25 | 2009-03-25 | 西门子瑞士有限公司 | Detection of smoke with a video camera |
| CN101441771A (en) * | 2008-12-19 | 2009-05-27 | 中国科学技术大学 | Video fire hazard smoke detecting method based on color saturation degree and movement mode |
Non-Patent Citations (2)
| Title |
|---|
| 基于运动累积和半透明的视频烟雾探测模型;袁非牛;《数据采集与处理》;20071231;第22卷(第4期);全文 * |
| 长大隧道内火灾烟雾运动和温度分布数值模拟;李婷婷等;《武汉理工大学学报》;20100630;第32卷(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103150549A (en) | 2013-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103150549B (en) | A kind of road tunnel fire detection method based on the early stage motion feature of smog | |
| CN104134222B (en) | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion | |
| CN107705288B (en) | Infrared video detection method of dangerous gas leakage under strong interference of false target movement | |
| CN103324913B (en) | A kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis | |
| CN110310255B (en) | Point switch notch detection method based on target detection and image processing | |
| CN100545867C (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN107025432B (en) | A kind of efficient lane detection tracking and system | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN103630496B (en) | Based on the traffic video visibility detecting method of road surface apparent brightness and least square method | |
| CN103268470B (en) | Object video real-time statistical method based on any scene | |
| CN103136514B (en) | A kind of parking event detecting method based on bi-directional tracking | |
| CN101770583B (en) | Template matching method based on global features of scene | |
| CN103150550B (en) | A kind of road pedestrian event detection method based on gripper path analysis | |
| CN109145708A (en) | A kind of people flow rate statistical method based on the fusion of RGB and D information | |
| CN104063882A (en) | Vehicle video speed measuring method based on binocular camera | |
| Liang et al. | Research on concrete cracks recognition based on dual convolutional neural network | |
| WO2014079058A1 (en) | Method and system for processing video image | |
| CN102663350A (en) | Road tunnel fire detection method based on video | |
| Ryu et al. | Feature-based pothole detection in two-dimensional images | |
| CN107507140B (en) | Method for suppressing vehicle shadow interference in open scene of highway based on feature fusion | |
| CN110516527B (en) | Visual SLAM loop detection improvement method based on instance segmentation | |
| CN111582270A (en) | Identification tracking method based on high-precision bridge region visual target feature points | |
| CN102622582B (en) | Road pedestrian event detection method based on video | |
| CN107169969A (en) | A kind of measurement of highway crag collapse deposit thing size and warning system based on FPGA | |
| Gao et al. | Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211228 Address after: 710000 room d4405, 4th floor, free trade bonded building, No. 1, free trade Avenue, airport new town, Xixian new area, Xi'an, Shaanxi a44 Patentee after: Xi'an Dewei Shitong Intelligent Transportation Co.,Ltd. Address before: 710064 middle section of south 2nd Ring Road, Xi'an, Shaanxi Patentee before: CHANG'AN University |
|
| TR01 | Transfer of patent right | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 710000 room d4405, 4th floor, free trade bonded building, No. 1, free trade Avenue, airport new town, Xixian new area, Xi'an, Shaanxi a44 Patentee after: Xi'an Dewei Shitong Intelligent Technology Co.,Ltd. Address before: 710000 room d4405, 4th floor, free trade bonded building, No. 1, free trade Avenue, airport new town, Xixian new area, Xi'an, Shaanxi a44 Patentee before: Xi'an Dewei Shitong Intelligent Transportation Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |