技术领域technical field
本发明涉及电力工程技术领域，具体涉及一种集烟雾和红外识别联动的输电线路山火监测方法。The invention relates to the technical field of electric power engineering, in particular to a monitoring method for mountain fires on power transmission lines that integrates smoke and infrared identification.
背景技术Background technique
输电线路山火的发生主要是由于线路下方及保护区内存在的可燃物(包括：树木、茅草、构筑物、易燃易爆物品等)发生火灾，对线路造成损坏或故障。主要形式有山火、房屋起火、堆积物(煤炭、木材、塑料等)起火等。由于火灾发生后控制不良极易蔓延，易引发线路跳闸，短时间难以恢复线路正常运行。目前的输电线路山火监测方法主要借鉴于红外监测技术，如开发了基于地面红外监测、机载红外林火监测和微波辐射监测装置，在大面积森林山火监测方面得到了一定的推广。但在输电线路山火监测中，单纯通过红外监测易受太阳光束等高温因素干扰，且容易出现因火焰被遮挡而无法识别山火的情形。而基于烟雾的视频监控对于及早地发现火灾具有重要意义，但单纯基于烟雾的山火识别因受大气云雾干扰，误报率较高。The occurrence of mountain fires on transmission lines is mainly due to the fires of combustible materials (including: trees, thatch, structures, flammable and explosive materials, etc.) under the lines and in the protection areas, which cause damage or failure to the lines. The main forms are mountain fires, house fires, accumulations (coal, wood, plastic, etc.) fires, etc. After the fire occurs, the poor control is easy to spread, and it is easy to cause the line to trip, and it is difficult to restore the normal operation of the line in a short time. The current mountain fire monitoring methods on transmission lines are mainly based on infrared monitoring technology, such as the development of ground-based infrared monitoring, airborne infrared forest fire monitoring and microwave radiation monitoring devices, which have been promoted to a certain extent in the monitoring of large-scale forest fires. However, in the monitoring of mountain fires on power transmission lines, infrared monitoring alone is susceptible to interference from high temperature factors such as solar beams, and it is easy to fail to identify mountain fires because the flames are blocked. Smoke-based video surveillance is of great significance for early detection of fires, but the recognition of wildfires based solely on smoke has a high false alarm rate due to the interference of atmospheric clouds.
发明内容Contents of the invention
本发明要解决的技术问题是克服现有技术存在的不足，提供一种能缩短山火火情发现时间、提高山火监测准确性的集烟雾和红外识别联动的输电线路山火监测方法。The technical problem to be solved by the present invention is to overcome the deficiencies in the prior art and provide a transmission line mountain fire monitoring method that can shorten the time for mountain fire detection and improve the accuracy of mountain fire monitoring, which integrates smoke and infrared identification linkage.
为解决上述技术问题，本发明采用以下技术方案：In order to solve the problems of the technologies described above, the present invention adopts the following technical solutions:
一种集烟雾和红外识别联动的输电线路山火监测方法，包括以下步骤：A transmission line mountain fire monitoring method integrating smoke and infrared identification, comprising the following steps:
(S1)实时采集待监测区域的视频图像，并依据当前采集时间是白天还是晚上选择下一步骤，若当前采集时间是白天进入步骤(S2)，若当前采集时间是晚上则进入步骤(S3)；(S1) Collect video images of the area to be monitored in real time, and select the next step according to whether the current collection time is daytime or night, if the current collection time is daytime, enter step (S2), if the current collection time is night, then enter step (S3) ;
(S2)根据对待监测区域连续采集的2～3帧视频图像，采用高斯混合模型对所述视频图像进行建模获得背景模型，并利用采集的视频图像对背景模型进行更新，然后采用背景模型对后续视频图像进行前景检测，获得白天山火预检测结果；若白天山火预检测结果为疑似火情，进入步骤(S4)，若白天山火预检测结果为非疑似火情，则返回步骤(S1)；(S2) According to 2 to 3 frames of video images continuously collected in the area to be monitored, the Gaussian mixture model is used to model the video images to obtain a background model, and the collected video images are used to update the background model, and then the background model is used to Subsequent video images carry out foreground detection to obtain the pre-detection result of daytime mountain fire; if the pre-detection result of daytime mountain fire is suspected fire, enter step (S4); if the result of daytime mountain fire pre-detection is non-suspected fire, then return to step ( S1);
(S3)根据对待监测区域连续采集的2～3帧视频图像，采用阈值分割法对视频图像进行分割获得晚上山火预检测结果；若晚上山火预检测结果为疑似火情，进入步骤(S4)，若晚上山火预检测结果为非疑似火情，则返回步骤(S1)；(S3) According to the 2 to 3 frames of video images continuously collected in the area to be monitored, the threshold segmentation method is used to segment the video images to obtain the pre-detection result of the mountain fire at night; if the pre-detection result of the mountain fire at night is a suspected fire, enter the step (S4 ), if the wildfire pre-detection result at night is a non-suspected fire situation, then return to step (S1);
(S4)采集待监测区域的红外图像，针对每帧红外图像进行山火阈值识别，获得待监测区域的红外火情判别结果，当红外火情判别结果为火情时，控制摄像机瞄准火情区域并不断地收集现场山火图像；(S4) Collect the infrared images of the area to be monitored, identify the fire threshold for each frame of infrared image, obtain the infrared fire discrimination result of the area to be monitored, and when the infrared fire discrimination result is fire, control the camera to aim at the fire area And continue to collect on-site wildfire images;
(S5)采用图像连通区域标记算法对步骤(S2)的白天山火预检测结果或步骤(S3)的晚上山火预检测结果进行区域标记，获得烟火区的准确位置。(S5) Using the image connected area labeling algorithm to perform area marking on the daytime mountain fire pre-detection result of step (S2) or the evening mountain fire pre-detection result of step (S3), to obtain the exact location of the pyrotechnic area.
上述的输电线路山火监测方法，优选的，所述步骤(S2)中，采用背景模型对后续视频图像进行前景检测是：高斯混合模型使用3个高斯模型来表征视频图像中各个像素点的特征，在新一帧视频图像获得后更新高斯混合模型，用当前视频图像中的每个像素点与更新后的高斯混合模型匹配，如果成功则判定该像素点为背景点，否则判定为前景点。The above-mentioned transmission line mountain fire monitoring method, preferably, in the step (S2), using the background model to perform foreground detection on the subsequent video image is: the Gaussian mixture model uses 3 Gaussian models to characterize the characteristics of each pixel in the video image , update the Gaussian mixture model after a new frame of video image is obtained, and match each pixel in the current video image with the updated Gaussian mixture model. If successful, the pixel is determined as a background point, otherwise it is determined as a foreground point.
上述的输电线路山火监测方法，优选的，所述步骤(S3)中，采用阈值分割法对视频图像进行分割获得晚上山火预检测结果具体是：在采集到的视频图像中，首先选取一帧静止视频图像作为背景帧图像，然后将当前帧视频图像的像素减去之前所选的背景帧图像的像素，当相减后的某一像素的差值大于第一设定阈值T时，则判定该像素为山火预检测像素。Preferably, in the above-mentioned transmission line mountain fire monitoring method, in the step (S3), the threshold segmentation method is used to segment the video image to obtain the evening mountain fire pre-detection result. Specifically: in the collected video images, first select a Frame still video image as the background frame image, then subtract the pixel of the previously selected background frame image from the pixel of the current frame video image, when the difference of a certain pixel after the subtraction is greater than the first set threshold T, then It is determined that the pixel is a mountain fire pre-detection pixel.
上述的输电线路山火监测方法，优选的，所述第一设定阈值T为0.15。In the aforementioned method for monitoring mountain fires on transmission lines, preferably, the first set threshold T is 0.15.
上述的输电线路山火监测方法，优选的，所述步骤(S4)中，针对每帧红外图像进行山火阈值识别，获得待监测区域的红外火情判别结果具体是：当红外图像中灰度值大于第二设定阈值Y时，像素值被置为255；当阈值Y大于像素的灰度值时，像素值被置为0。Preferably, in the above-mentioned transmission line mountain fire monitoring method, in the step (S4), the mountain fire threshold recognition is carried out for each frame of infrared image, and the infrared fire discrimination result of the area to be monitored is specifically: when the grayscale in the infrared image When the value is greater than the second set threshold Y, the pixel value is set to 255; when the threshold Y is greater than the gray value of the pixel, the pixel value is set to 0.
上述的输电线路山火监测方法，优选的，所述第二设定阈值Y为185。In the above method for monitoring mountain fires on transmission lines, preferably, the second set threshold Y is 185.
上述的输电线路山火监测方法，优选的，所述步骤(S1)中，当前采集时间处于白天还是晚上是通过对视频图像亮度进行随机固定点数采样求平均值来确定。In the above method for monitoring mountain fires on power transmission lines, preferably, in the step (S1), whether the current acquisition time is daytime or night is determined by performing random fixed-point sampling and averaging of video image brightness.
上述的输电线路山火监测方法，优选的，所述步骤(S1)中的视频图像和步骤(S4)中的红外图像采用可见光-红外一体式摄像机采集。In the above method for monitoring mountain fires on power transmission lines, preferably, the video images in the step (S1) and the infrared images in the step (S4) are collected by a visible light-infrared integrated camera.
与现有技术相比，本发明的优点在于：Compared with the prior art, the present invention has the advantages of:
本发明集烟雾和红外识别联动的输电线路山火监测方法，耦合了输电线路山火火焰与烟雾的光谱特征和图像特征，将可见光和热红外两种图像的林火识别算法进行有机合成，形成一种耦合烟雾和火焰多特征识别的输电线路山火监测方法。通过利用红外监测消除可见光监测中林区烟雾干扰，同时利用可见光监测消除白天太阳光束干扰，可在山火初发期间快速获取现场山火信息。该方法能缩短山火火情发现时间，提高山火监测准确性，减少线路跳闸事故。The present invention integrates smoke and infrared identification linkage transmission line mountain fire monitoring method, couples the spectral characteristics and image characteristics of transmission line mountain fire flames and smoke, organically synthesizes forest fire identification algorithms of two images of visible light and thermal infrared images, and forms A transmission line mountain fire monitoring method coupled with smoke and flame multi-feature recognition. By using infrared monitoring to eliminate smoke interference in forest areas in visible light monitoring, and using visible light monitoring to eliminate daytime sun beam interference, it is possible to quickly obtain on-site mountain fire information during the initial outbreak of wildfires. The method can shorten the detection time of wildfires, improve the accuracy of wildfire monitoring, and reduce line tripping accidents.
具体实施方式Detailed ways
以下结合具体实施例对本发明作进一步详细说明。The present invention will be described in further detail below in conjunction with specific examples.
本实施例的集烟雾和红外识别联动的输电线路山火监测方法，包括以下步骤：The method for monitoring mountain fires on transmission lines that integrates smoke and infrared identification in this embodiment includes the following steps:
(S1)实时采集待监测区域的视频图像，并依据当前采集时间是白天还是晚上选择下一步骤，若当前采集时间是白天进入步骤(S2)，若当前采集时间是晚上则进入步骤(S3)；(S1) Collect video images of the area to be monitored in real time, and select the next step according to whether the current collection time is daytime or night, if the current collection time is daytime, enter step (S2), if the current collection time is night, then enter step (S3) ;
(S2)根据对待监测区域连续采集的2～3帧视频图像，采用高斯混合模型对所述视频图像进行建模获得背景模型，并利用采集的视频图像对背景模型进行更新，然后采用背景模型对后续视频图像进行前景检测，获得白天山火预检测结果；若白天山火预检测结果为疑似火情，进入步骤(S4)，若白天山火预检测结果为非疑似火情，则返回步骤(S1)；(S2) According to 2 to 3 frames of video images continuously collected in the area to be monitored, the Gaussian mixture model is used to model the video images to obtain a background model, and the collected video images are used to update the background model, and then the background model is used to Subsequent video images carry out foreground detection to obtain the pre-detection result of daytime mountain fire; if the pre-detection result of daytime mountain fire is suspected fire, enter step (S4); if the result of daytime mountain fire pre-detection is non-suspected fire, then return to step ( S1);
(S3)根据对待监测区域连续采集的2～3帧视频图像，采用阈值分割法对视频图像进行分割获得晚上山火预检测结果；若晚上山火预检测结果为疑似火情，进入步骤(S4)，若晚上山火预检测结果为非疑似火情，则返回步骤(S1)；(S3) According to the 2 to 3 frames of video images continuously collected in the area to be monitored, the threshold segmentation method is used to segment the video images to obtain the pre-detection result of the mountain fire at night; if the pre-detection result of the mountain fire at night is a suspected fire, enter the step (S4 ), if the wildfire pre-detection result at night is a non-suspected fire situation, then return to step (S1);
(S4)采集待监测区域的红外图像，针对每帧红外图像进行山火阈值识别，获得待监测区域的红外火情判别结果，当红外火情判别结果为火情时，控制摄像机瞄准火情区域并不断地收集现场山火图像；(S4) Collect the infrared images of the area to be monitored, identify the fire threshold for each frame of infrared image, obtain the infrared fire discrimination result of the area to be monitored, and when the infrared fire discrimination result is fire, control the camera to aim at the fire area And continue to collect on-site wildfire images;
(S5)采用图像连通区域标记算法对步骤(S2)的白天山火预检测结果或步骤(S3)的晚上山火预检测结果进行区域标记，获得烟火区的准确位置。(S5) Using the image connected area labeling algorithm to perform area marking on the daytime mountain fire pre-detection result of step (S2) or the evening mountain fire pre-detection result of step (S3), to obtain the exact location of the pyrotechnic area.
本实施例中，在上述步骤(S1)中，当前采集时间处于白天还是晚上是通过对视频图像亮度进行随机固定点数采样求平均值来确定。In this embodiment, in the above step (S1), whether the current collection time is daytime or night is determined by performing random fixed-point sampling and averaging on the brightness of the video image.
本实施例中，在上述步骤(S2)中，采用背景模型对后续视频图像进行前景检测是：高斯混合模型使用3个高斯模型来表征视频图像中各个像素点的特征，在新一帧视频图像获得后更新高斯混合模型，用当前视频图像中的每个像素点与更新后的高斯混合模型匹配，如果成功则判定该像素点为背景点，否则判定为前景点。In this embodiment, in the above step (S2), the use of the background model to perform foreground detection on subsequent video images is: the Gaussian mixture model uses 3 Gaussian models to characterize the characteristics of each pixel in the video image, and in a new frame of video image The Gaussian mixture model is updated after the acquisition, and each pixel in the current video image is matched with the updated Gaussian mixture model. If successful, the pixel is determined as a background point, otherwise it is determined as a foreground point.
本实施例中，在上述步骤(S3)中，采用阈值分割法对视频图像进行分割获得晚上山火预检测结果具体是：在采集到的视频图像中，首先选取一帧静止视频图像作为背景帧图像，然后将当前帧视频图像的像素减去之前所选的背景帧图像的像素，当相减后的某一像素的差值大于第一设定阈值T时，则判定该像素为山火预检测像素。优选的，第一设定阈值T为0.15，经试验验证，第一设定阈值T取为该值能够充分检测火点。In this embodiment, in the above step (S3), the threshold segmentation method is used to segment the video image to obtain the pre-detection result of the evening mountain fire. Specifically: in the collected video image, first select a frame of still video image as the background frame image, and then subtract the pixel of the previously selected background frame image from the pixel of the current frame video image, and when the difference of a certain pixel after the subtraction is greater than the first set threshold T, it is determined that the pixel is a forest fire prediction Detect pixels. Preferably, the first set threshold T is 0.15, and it has been verified by experiments that taking this value as the first set threshold T can fully detect the fire point.
本实施例中，在上述步骤(S4)中，针对每帧红外图像进行山火阈值识别，获得待监测区域的红外火情判别结果具体是：当红外图像中灰度值大于第二设定阈值Y时，像素值被置为255；当阈值Y大于像素的灰度值时，像素值被置为0。优选的，第二设定阈值Y为185，经试验验证，第二设定阈值Y取为该值能够充分检测火点。In this embodiment, in the above step (S4), the mountain fire threshold is identified for each frame of infrared image, and the infrared fire discrimination result of the area to be monitored is obtained. Specifically: when the gray value in the infrared image is greater than the second set threshold When Y, the pixel value is set to 255; when the threshold Y is greater than the gray value of the pixel, the pixel value is set to 0. Preferably, the second set threshold Y is 185. It has been verified by experiments that the second set threshold Y is set to this value, which can fully detect the fire point.
本实施例中，步骤(S1)中的视频图像和步骤(S4)中的红外图像采用可见光-红外一体式摄像机采集。In this embodiment, the video image in step (S1) and the infrared image in step (S4) are collected by a visible light-infrared integrated camera.
以上所述仅是本发明的优选实施方式，本发明的保护范围并不仅局限于上述实施例。对于本技术领域的技术人员来说，在不脱离本发明技术构思前提下所得到的改进和变换也应视为本发明的保护范围。The above descriptions are only preferred implementations of the present invention, and the scope of protection of the present invention is not limited to the above examples. For those skilled in the art, improvements and transformations obtained without departing from the technical concept of the present invention should also be regarded as the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910610248.2ACN110310448A (en) | 2019-07-08 | 2019-07-08 | A transmission line mountain fire monitoring method integrating smoke and infrared identification linkage |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910610248.2ACN110310448A (en) | 2019-07-08 | 2019-07-08 | A transmission line mountain fire monitoring method integrating smoke and infrared identification linkage |
| Publication Number | Publication Date |
|---|---|
| CN110310448Atrue CN110310448A (en) | 2019-10-08 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910610248.2APendingCN110310448A (en) | 2019-07-08 | 2019-07-08 | A transmission line mountain fire monitoring method integrating smoke and infrared identification linkage |
| Country | Link |
|---|---|
| CN (1) | CN110310448A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027520A (en)* | 2019-12-27 | 2020-04-17 | 广东电网有限责任公司电力科学研究院 | Method, device and equipment for judging and identifying mountain fire points |
| CN113259625A (en)* | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring system and method thereof |
| CN114973584A (en)* | 2022-05-10 | 2022-08-30 | 云南电网有限责任公司电力科学研究院 | Mountain fire warning method and device, computer equipment and storage medium |
| CN116091959A (en)* | 2022-11-21 | 2023-05-09 | 武汉坤达安信息安全技术有限公司 | Double-light linkage identification method and device based on all-weather smoke and fire |
| CN116824166A (en)* | 2023-08-29 | 2023-09-29 | 南方电网数字电网研究院有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
| CN117934457A (en)* | 2024-03-20 | 2024-04-26 | 国网江苏省电力有限公司 | Mountain fire detection method and system for power transmission line |
| CN119107758A (en)* | 2024-09-09 | 2024-12-10 | 武汉钢铁有限公司 | Fire monitoring method and related equipment for power overhead line corridor |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04324595A (en)* | 1991-04-11 | 1992-11-13 | Pittway Corp | Light-sensitive type smoke detector |
| CN101587622A (en)* | 2009-06-18 | 2009-11-25 | 任芳 | Forest rocket detection and recognition methods and equipment based on video image intelligent analysis |
| CN101872526A (en)* | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
| CN106997461A (en)* | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN108537202A (en)* | 2018-04-19 | 2018-09-14 | 广州林邦信息科技有限公司 | Forest fire identification device and system |
| CN108629940A (en)* | 2018-05-02 | 2018-10-09 | 北京准视科技有限公司 | A kind of image-type fire detection alarm system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04324595A (en)* | 1991-04-11 | 1992-11-13 | Pittway Corp | Light-sensitive type smoke detector |
| CN101587622A (en)* | 2009-06-18 | 2009-11-25 | 任芳 | Forest rocket detection and recognition methods and equipment based on video image intelligent analysis |
| CN101872526A (en)* | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
| CN106997461A (en)* | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN108537202A (en)* | 2018-04-19 | 2018-09-14 | 广州林邦信息科技有限公司 | Forest fire identification device and system |
| CN108629940A (en)* | 2018-05-02 | 2018-10-09 | 北京准视科技有限公司 | A kind of image-type fire detection alarm system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027520A (en)* | 2019-12-27 | 2020-04-17 | 广东电网有限责任公司电力科学研究院 | Method, device and equipment for judging and identifying mountain fire points |
| CN113259625A (en)* | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring system and method thereof |
| CN114973584A (en)* | 2022-05-10 | 2022-08-30 | 云南电网有限责任公司电力科学研究院 | Mountain fire warning method and device, computer equipment and storage medium |
| CN116091959A (en)* | 2022-11-21 | 2023-05-09 | 武汉坤达安信息安全技术有限公司 | Double-light linkage identification method and device based on all-weather smoke and fire |
| CN116091959B (en)* | 2022-11-21 | 2024-03-22 | 武汉坤达安信息安全技术有限公司 | Double-light linkage identification method and device based on all-weather smoke and fire |
| CN116824166A (en)* | 2023-08-29 | 2023-09-29 | 南方电网数字电网研究院有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
| CN116824166B (en)* | 2023-08-29 | 2024-03-08 | 南方电网数字电网研究院股份有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
| CN117934457A (en)* | 2024-03-20 | 2024-04-26 | 国网江苏省电力有限公司 | Mountain fire detection method and system for power transmission line |
| CN117934457B (en)* | 2024-03-20 | 2024-05-31 | 国网江苏省电力有限公司 | Transmission line wildfire detection method and system |
| CN119107758A (en)* | 2024-09-09 | 2024-12-10 | 武汉钢铁有限公司 | Fire monitoring method and related equipment for power overhead line corridor |
| Publication | Publication Date | Title |
|---|---|---|
| CN110310448A (en) | A transmission line mountain fire monitoring method integrating smoke and infrared identification linkage | |
| CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
| CN104269012B (en) | Method for monitoring mountain fire nearby electric transmission line based on MODIS data | |
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| CN112102578B (en) | Forest fire monitoring and early warning system, method, storage medium and computer equipment | |
| CN102708647A (en) | Image and multi-band infrared-ultraviolet compound fire disaster detection system and method | |
| CN107025753B (en) | Wide area fire alarm device based on multispectral image analysis | |
| CN105574468B (en) | Video flame detection method, device and system | |
| CN108648400A (en) | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning | |
| CN112785809B (en) | Fire re-ignition prediction method and system based on AI image recognition | |
| CN105976365A (en) | Nocturnal fire disaster video detection method | |
| CN101814133A (en) | Intelligent flame detector based on computer vision monitoring technology | |
| CN105575034A (en) | Image processing and analysis method of double-waveband forest fireproof intelligent monitoring software | |
| CN113221057B (en) | Straw burning fire point monitoring method based on multi-temporal satellite images | |
| CN110766685A (en) | A transmission line mountain fire monitoring method and system based on remote sensing data cloud detection | |
| KR20240028290A (en) | Device and method for detecting wildfire | |
| CN104537792A (en) | Transmission line wildfire satellite monitoring method based on background information | |
| CN116612597A (en) | Forest fire monitoring and early warning system based on data analysis | |
| CN108682105A (en) | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning | |
| Zhang et al. | 10-minute forest early wildfire detection: Fusing multi-type and multi-source information via recursive transformer | |
| CN102609685A (en) | Shadowing judging method of image type fire detector | |
| CN111476971A (en) | Transmission line closely mountain fire monitoring devices | |
| CN103446698A (en) | Method for automatically sequencing fire sources | |
| CN118918675A (en) | Multi-sensor information fusion mountain fire monitoring system, method and equipment | |
| CN117475378A (en) | Mountain fire spread prediction method and device, equipment and storage medium |
| 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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20191008 | |
| RJ01 | Rejection of invention patent application after publication |