CN112115875A - Forest fire smoke root detection method based on dynamic and static combination area stacking strategy - Google Patents

Forest fire smoke root detection method based on dynamic and static combination area stacking strategy Download PDF

Info

Publication number
CN112115875A
CN112115875A CN202010994762.3A CN202010994762A CN112115875A CN 112115875 A CN112115875 A CN 112115875A CN 202010994762 A CN202010994762 A CN 202010994762A CN 112115875 A CN112115875 A CN 112115875A
Authority
CN
China
Prior art keywords
smoke
dynamic
frame
image
static
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.)
Granted
Application number
CN202010994762.3A
Other languages
Chinese (zh)
Other versions
CN112115875B (en
Inventor
程朋乐
娄黎明
郑鑫
秦政
闫磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Forestry University
Original Assignee
Beijing Forestry University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Forestry University filed Critical Beijing Forestry University
Priority to CN202010994762.3A priority Critical patent/CN112115875B/en
Publication of CN112115875A publication Critical patent/CN112115875A/en
Application granted granted Critical
Publication of CN112115875B publication Critical patent/CN112115875B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
    • Y02A40/28—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture specially adapted for farming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a forest fire smoke root node detection method based on a dynamic and static combination area stacking strategy. The method comprises the steps of obtaining a rectangular frame capable of containing all smoke dynamic regions by performing condition superposition on extracted multi-frame smoke dynamic regions, then performing static feature extraction on an original input image in the rectangular frame to obtain smoke regions simultaneously meeting dynamic and static features, identifying non-rectangular frame regions as background regions, performing skeletonization on the smoke regions to obtain bone endpoints and obtaining smoke root nodes with higher confidence by a subsequent multi-frame discrete confidence strategy, solving the problems that continuous and complete smoke regions cannot be obtained only by a single-frame dynamic extraction method and complete and continuous connected regions cannot be obtained, and also improving the problem that a static feature extraction method is difficult to remove background interferents.

Description

Forest fire smoke root detection method based on dynamic and static combination area stacking strategy
Technical Field
The invention belongs to the field of forest fire prevention and video target detection, and particularly relates to a video-based smoke source root node detection method.
Background
Due to the particularity of the forest, once a forest fire is caused, the forest fire is easy to rapidly spread under the promotion of wind power, the area of the forest is large, the fire cannot be found in time when the fire occurs, the fire often spreads a quite wide distance when the fire is found, the suppression of the forest fire is also quite difficult at the moment, the forest fire often causes huge resource damage, and therefore the early identification of the forest fire is very important. The smoke is an obvious characteristic of forest fire in the early stage, the smoke is often in an irregular shape which drifts upwards, the smoke is thinner and harder to detect the smoke in the early stage of the forest fire, but the source position of the early smoke is often determined and is unchanged in a short time, and based on the principle, the determination of the position of the smoke source through the distribution form of the smoke becomes one of important breakthrough openings.
The patent application number is 201910490504.9, and the invention is a Chinese patent named as a smoke root node detection method under a remote complex environment based on MSER. The method comprises the steps of extracting a candidate region of a long-distance smoke scene by adopting an MSER algorithm, eliminating possible interference items in an image by adopting an angular point extraction algorithm and a convex hull detection algorithm, extracting smoke root node candidate points from the candidate region by adopting a skeleton extraction algorithm, and finally extracting smoke root nodes by adopting interframe information of continuous frames. The core idea of the MSER algorithm is to extract MSER candidate regions based on the characteristic that gray values of gray images tend to be stable in a certain range. The smoke diffuses under a dynamic condition, only the gray value of the central part of the smoke tends to be stable, the gray value of the edge of the smoke frequently changes, so that the MSER algorithm cannot completely extract the smoke contour, a part of the smoke region and a large number of background interferents are contained in the feature region extracted by the MSER, not all the interferent contours can be extracted by the corner points, the finally obtained feature region has more errors and interferences, and the result directly causes that the correct smoke region cannot be extracted, so that the position of a smoke root node cannot be determined.
The patent application number is 201711440134, and the invention discloses a Chinese patent of a forest fire smoke video target detection method based on characteristic roots and hydrodynamics. The method extracts continuous frame images in the video for dynamic extraction, skeletonizes a connected region in the dynamic region through a morphological algorithm, extracts suspicious smoke root characteristic candidate points in continuous frame skeleton end points, and puts the suspicious smoke root characteristic candidate points into a two-dimensional smoke engine to judge whether the suspicious smoke root is a real smoke root or not. According to the method, only the difference image is obtained through an interframe difference method, the complete smoke region cannot be accurately obtained, and finally obtained smoke root candidate points are greatly deviated from real smoke root nodes.
The patent application number is 201811318766, and the invention is a Chinese patent named as a smoke root node detection method based on a least square method. The method comprises the steps of carrying out statistical calculation on substitution points of the connected domains according to the distribution condition of the connected domains in continuous frame images to obtain dynamic regions continuously existing in the continuous images, obtaining intersection points of the dynamic regions continuously existing through a regression algorithm, obtaining a calculation result by adopting three continuous frame images, and determining the smoke source. In the smoke root candidate point extraction process, the connected domain of the smoke candidate area also needs to be calculated, a dynamic area extraction algorithm of an interframe difference method is adopted, complete smoke information cannot be accurately obtained only by dynamic extraction, and if the candidate area of the smoke cannot be successfully extracted, a collapse calculation cliff area cannot be divided by the collapse algorithm provided by the patent, so that detection failure is caused.
The patent application number is 201910613683.0, and the invention discloses a Chinese patent named as a self-adaptive smoke root node detection method under a large-scale space. The invention adopts an image fusion method based on Bayesian theory in the specification of 'step 401-step 411', and the method carries out probability statistics on images in a partition grid mode on the basis of 4 Vibe images and 3 MSER images. And after the fusion probability of each grid region is calculated, performing fusion calculation on the regions exceeding the threshold probability to obtain a fusion image. The application background of the algorithm is a smoke root detection algorithm, and the requirement on the continuity of continuous existence information between continuous frames is high. According to the calculation principle of the fusion algorithm, the algorithm can contain image information of 7 continuous frames at most, and each calculation needs to perform traversal statistics on all pixel points in a 10 × 10 grid area. This calculation process is not friendly to multi-frame images, and calculating the root node even for the minimum unit of consecutive frame images requires a great amount of calculation. And in order to guarantee the running speed of the algorithm, the number of the images containing the continuous frames is not allowed to be too large, and the method has great limitation.
Disclosure of Invention
The invention provides a forest fire smoke root node detection method based on a dynamic and static combination area stacking strategy, which can be used for positioning a smoke source root node by an original video frame image.
The method comprises the following basic steps:
firstly, preprocessing video information, extracting frame images by collecting continuous frame smoke images of a fixed camera, and obtaining single-channel gray image frames with specific sizes by a basic image processing method;
secondly, extracting a smoke dynamic region, namely performing dynamic region extraction on all the obtained single-channel gray frame images through a Vibe algorithm to obtain Vibe dynamic region images of all the frame images;
thirdly, carrying out corrosion operation on all the obtained video images, removing the influence of background interference noise and obtaining dynamic characteristic images of all frames;
fourthly, summing all dynamic characteristic image frames to obtain a characteristic image containing all dynamic characteristics at all moments, solving a rectangular frame capable of containing all characteristic pixel points of the characteristic image, extending the lower edge of the y direction downwards for 10 pixels according to the characteristics of smoke to better contain smoke root nodes, extracting static characteristics of the single-channel gray-scale image obtained in the first step according to the rectangular frame, and extracting a binaryzation area characteristic image of the smoke;
fifthly, performing closing operation on the obtained binarization smoke area characteristic image to obtain a connected domain;
sixthly, extracting bones from the connected domain to obtain a smoke bone image;
and seventhly, solving a skeleton endpoint of the skeleton image, and obtaining a high-confidence smoke root node by a multi-frame discrete confidence root node judgment method.
In the fourth step, a smoke feature rectangular frame is obtained through dynamic features, and a static and dynamic combined smoke feature extraction method for extracting static features of a smoke frame through the rectangular frame is specifically implemented as follows:
step 401, summing the operation of all the vibe dynamic feature images with (1,1) corrosion kernels and background noise interference removed, wherein the operation formula is as follows:
Figure BDA0002692158650000041
where M (x, y) is the pixel value of the template image at (x, y), Pi(x, y) is the pixel value of the motion characteristic image of the ith frame, which is located in (x, y);
step 402, respectively calculating the maximum x value x of the pixel with the pixel value of 255 for the obtained template image with all dynamic characteristic pixelsmaxMinimum x value xminMaximum y value ymaxAnd minimum y value yminAccording to the characteristics of the smoke, a minimum rectangular frame is used for framing all smoke dynamic characteristic pixel point sets, and the coordinates of four end points of the rectangular frame are respectively as follows:
(xmin,ymin),(xmax,ymin),(xmin,ymax+10),(xmax,ymax+10) (2)
step 403, performing static feature extraction on the single-channel gray frame obtained in the first step, where F (x, y) is to obtain a static feature image and the extraction strategy is as follows:
Figure BDA0002692158650000042
f (x, y) is the pixel value of the single-channel gray image at the (x, y) position, and the static feature extraction method comprises the following steps:
Figure BDA0002692158650000043
Figure BDA0002692158650000044
(x, y) belonging to a rectangular frame area (5)
At step 404, static feature images of all input frames are obtained.
The beneficial effects of the method are as follows: the method comprises the steps of obtaining a rectangular frame capable of containing all smoke dynamic regions by performing condition superposition on extracted multi-frame smoke dynamic regions, then performing static feature extraction on an original input image in the rectangular frame to obtain smoke regions simultaneously meeting dynamic and static features, identifying non-rectangular frame regions as background regions, performing skeletonization on the smoke regions to obtain bone endpoints and obtaining smoke root nodes with higher confidence by a subsequent multi-frame discrete confidence strategy, solving the problems that continuous and complete smoke regions cannot be obtained only by a single-frame dynamic extraction method and complete and continuous connected regions cannot be obtained, and also improving the problem that a static feature extraction method is difficult to remove background interferents. The complete connected domain plays a crucial role in obtaining the smoke root candidate points subsequently, the addition of calculated amount due to the incompleteness of smoke information and the interferent information is avoided, and the calculation efficiency and the accuracy of calculation results are greatly improved.
Drawings
FIG. 1 is a flow chart of the calculation process of the present invention.
Detailed Description
The foregoing and other features of the invention will become apparent from the following specification taken in conjunction with the accompanying drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the embodiments in which the principles of the invention may be employed, it being understood that the invention is not limited to the embodiments described, but, on the contrary, is intended to cover all modifications, variations, and equivalents falling within the scope of the appended claims.
Step 101, preprocessing video information, extracting frame images by collecting continuous frame smoke images of a fixed camera, performing single-channel graying processing on the frame images, and cutting the frame images into 480 × 320 pixels to obtain single-channel grayscale images;
step 201, reading each frame in a single-channel gray scale image format, and performing dynamic region extraction through a Vibe algorithm to obtain a Vibe dynamic region image of each frame image.
And 301, performing corrosion operation on all the obtained video images, removing background interference noise influence, and obtaining dynamic characteristic images of all frames.
Step 401, summing the operation of all the vibe dynamic feature images with (1,1) corrosion kernels and background noise interference removed, wherein the operation formula is as follows:
Figure BDA0002692158650000061
where M (x, y) is the pixel value of the template image at (x, y), Pi(x, y) is the pixel value of the motion characteristic image of the ith frame, which is located in (x, y);
step 402, respectively calculating the maximum x value x of the pixel with the pixel value of 255 for the obtained template image with all dynamic characteristic pixelsmaxMinimum x value xminMaximum y value ymaxAnd minimum y value yminAccording to the characteristics of the smoke, a minimum rectangular frame is used for framing all smoke dynamic characteristic pixel point sets, and the coordinates of four end points of the rectangular frame are respectively as follows:
(xmin,ymin),(xmax,ymin),(xmin,ymax+10),(xmax,ymax+10) (2)
step 403, performing static feature extraction on the single-channel gray frame obtained in the first step, where F (x, y) is to obtain a static feature image and the extraction strategy is as follows:
Figure BDA0002692158650000062
f (x, y) is the pixel value of the single-channel gray image at the (x, y) position, and the static feature extraction method comprises the following steps:
Figure BDA0002692158650000063
Figure BDA0002692158650000064
(x, y) belonging to a rectangular frame area (5)
And step 404, obtaining the binarization smog area characteristic image of all input frames.
Step 501, performing closing operation on the obtained binarization smoke region characteristic image to obtain a connected domain;
step 601, extracting bones of each frame of connected domain image to obtain a bone image of each frame of image, wherein in the calculation process of the bone image, the extraction conditions are as follows:
Figure BDA0002692158650000065
wherein P is1Is the central pixel value, Pi2,3, 9 is P1Critical domain pixel value, B, centered clockwise from pixel 12 dot(Pi)Is represented by a pixel PiCentered, the sum of the neighboring pixels is between 2 x 255 and 6 x 255, a(Pi)Is represented by a pixel PiBy taking the pixel as the center, the adjacent two pixels have the times of 0 to 255 change in the clockwise direction in 8 pixels in the adjacent domain.
Step 701, obtaining a skeleton endpoint from the skeleton image, and obtaining a smoke root node with high confidence by a multi-frame discrete confidence root node judgment method.

Claims (2)

1. A forest fire smoke root detection method based on a dynamic and static combination area stacking strategy is characterized by comprising the following steps:
firstly, preprocessing video information, extracting frame images by collecting continuous frame smoke images of a fixed camera, and obtaining single-channel gray image frames with specific sizes by a basic image processing method;
secondly, extracting a smoke dynamic region, namely performing dynamic region extraction on all the obtained single-channel gray frame images through a Vibe algorithm to obtain Vibe dynamic region images of all the frame images;
thirdly, carrying out corrosion operation on all the obtained video images, removing the influence of background interference noise and obtaining dynamic characteristic images of all frames;
fourthly, summing all dynamic characteristic image frames to obtain a characteristic image containing all dynamic characteristics at all moments, solving a rectangular frame capable of containing all characteristic pixel points of the characteristic image, extending the lower edge of the y direction downwards for 10 pixels according to the characteristics of smoke to better contain smoke root nodes, extracting static characteristics of the single-channel gray-scale image obtained in the first step according to the rectangular frame, and extracting a binaryzation area characteristic image of the smoke;
fifthly, performing closing operation on the obtained binarization smoke area characteristic image to obtain a connected domain;
sixthly, extracting bones from the connected domain to obtain a smoke bone image;
and seventhly, solving a skeleton endpoint of the skeleton image, and obtaining a high-confidence smoke root node by a multi-frame discrete confidence root node judgment method.
2. The forest fire smoke root detection method based on the dynamic and static combination region stacking strategy according to claim 1, wherein the dynamic and static combination smoke feature extraction method for obtaining the smoke feature rectangular frame through the dynamic features and extracting the static features of the smoke frame through the rectangular frame in the fourth step is specifically implemented by the following steps:
step 401, summing the operation of all the vibe dynamic feature images with (1,1) corrosion kernels and background noise interference removed, wherein the operation formula is as follows:
Figure FDA0002692158640000021
where M (x, y) is the pixel value of the template image at (x, y), Pi(x, y) is the pixel value of the motion characteristic image of the ith frame, which is located in (x, y);
step 402, respectively calculating the maximum x value x of the pixel with the pixel value of 255 for the obtained template image with all dynamic characteristic pixelsmaxMinimum x value xminMaximum y value ymaxAnd minimum y value yminAccording to the characteristics of the smoke, a minimum rectangular frame is used for framing all smoke dynamic characteristic pixel point sets, and the coordinates of four end points of the rectangular frame are respectively as follows:
(xmin,ymin),(xmax,ymin),(xmin,ymax+10),(xmax,ymax+10) (2)
step 403, performing static feature extraction on the single-channel gray frame obtained in the first step, where F (x, y) is to obtain a static feature image and the extraction strategy is as follows:
Figure FDA0002692158640000022
f (x, y) is the pixel value of the single-channel gray image at the (x, y) position, and the static feature extraction method comprises the following steps:
Figure FDA0002692158640000023
Figure FDA0002692158640000024
and step 404, obtaining the binarization smog area characteristic image of all input frames.
CN202010994762.3A 2020-09-21 2020-09-21 Forest fire smoke root detection method based on dynamic and static combined region lamination strategy Active CN112115875B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010994762.3A CN112115875B (en) 2020-09-21 2020-09-21 Forest fire smoke root detection method based on dynamic and static combined region lamination strategy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010994762.3A CN112115875B (en) 2020-09-21 2020-09-21 Forest fire smoke root detection method based on dynamic and static combined region lamination strategy

Publications (2)

Publication Number Publication Date
CN112115875A true CN112115875A (en) 2020-12-22
CN112115875B CN112115875B (en) 2024-05-24

Family

ID=73800882

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010994762.3A Active CN112115875B (en) 2020-09-21 2020-09-21 Forest fire smoke root detection method based on dynamic and static combined region lamination strategy

Country Status (1)

Country Link
CN (1) CN112115875B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113780195A (en) * 2021-09-15 2021-12-10 北京林业大学 Forest fire smoke root node detection method based on block extraction
CN114119754A (en) * 2021-12-08 2022-03-01 北京林业大学 Pixel-level fire smoke root node detection method based on connected particles
CN116416200A (en) * 2022-01-12 2023-07-11 中国消防救援学院 Forest fire smoke detection method based on region matching

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130091138A (en) * 2012-02-07 2013-08-16 홍익대학교 산학협력단 System and method for detecting smoke using surveillance camera
CN106650600A (en) * 2016-10-17 2017-05-10 东南大学 Forest smoke and fire detection method based on video image analysis
CN108009529A (en) * 2017-12-27 2018-05-08 北京林业大学 A kind of feature based root and hydromechanical forest fire cigarette video object detection method
US20180260963A1 (en) * 2015-11-20 2018-09-13 Fujitsu Limited Apparatus, method and image processing device for smoke detection in image
CN110309808A (en) * 2019-07-09 2019-10-08 北京林业大学 A kind of adaptive smog root node detection method under a wide range of scale space
CN110852174A (en) * 2019-10-16 2020-02-28 天津大学 Early smoke detection method based on video monitoring

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130091138A (en) * 2012-02-07 2013-08-16 홍익대학교 산학협력단 System and method for detecting smoke using surveillance camera
US20180260963A1 (en) * 2015-11-20 2018-09-13 Fujitsu Limited Apparatus, method and image processing device for smoke detection in image
CN106650600A (en) * 2016-10-17 2017-05-10 东南大学 Forest smoke and fire detection method based on video image analysis
CN108009529A (en) * 2017-12-27 2018-05-08 北京林业大学 A kind of feature based root and hydromechanical forest fire cigarette video object detection method
CN110309808A (en) * 2019-07-09 2019-10-08 北京林业大学 A kind of adaptive smog root node detection method under a wide range of scale space
CN110852174A (en) * 2019-10-16 2020-02-28 天津大学 Early smoke detection method based on video monitoring

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
郑鑫;高宇;陈锋;程朋乐;: "基于高斯混合模型林火"烟雾根"的识别", 林业和草原机械, no. 01, 29 February 2020 (2020-02-29) *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113780195A (en) * 2021-09-15 2021-12-10 北京林业大学 Forest fire smoke root node detection method based on block extraction
CN114119754A (en) * 2021-12-08 2022-03-01 北京林业大学 Pixel-level fire smoke root node detection method based on connected particles
CN114119754B (en) * 2021-12-08 2024-04-05 北京林业大学 Pixel-level fire smoke root node detection method based on connected particles
CN116416200A (en) * 2022-01-12 2023-07-11 中国消防救援学院 Forest fire smoke detection method based on region matching
CN116416200B (en) * 2022-01-12 2023-10-27 中国消防救援学院 Forest fire smoke detection method based on region matching

Also Published As

Publication number Publication date
CN112115875B (en) 2024-05-24

Similar Documents

Publication Publication Date Title
CN112115875A (en) Forest fire smoke root detection method based on dynamic and static combination area stacking strategy
CN109389121B (en) Nameplate identification method and system based on deep learning
CN111967394B (en) Forest fire smoke root node detection method based on dynamic and static grid fusion strategy
CN108121991B (en) Deep learning ship target detection method based on edge candidate region extraction
CN110766008A (en) Text detection method facing any direction and shape
CN112115878B (en) Forest fire smoke root node detection method based on smoke area density
CN109410512B (en) Smoke root node detection method based on least square method
CN111680690A (en) Character recognition method and device
CN109886978A (en) A kind of end-to-end warning information recognition methods based on deep learning
CN111914818B (en) Method for detecting forest fire smoke root nodes based on multi-frame discrete confidence
CN115294149A (en) Astronomical image background extraction method and system
CN113657264A (en) Forest fire smoke root node detection method based on fusion of dark channel and KNN algorithm
CN110889374A (en) Seal image processing method and device, computer and storage medium
CN117475353A (en) Video-based abnormal smoke identification method and system
CN111179289B (en) Image segmentation method suitable for webpage length graph and width graph
Zhu Moving Objects Detection and Segmentation Based on Background Subtraction and Image Over-Segmentation.
CN115187744A (en) Cabinet identification method based on laser point cloud
CN116416200B (en) Forest fire smoke detection method based on region matching
CN113284135B (en) SAR ship detection method based on global and local context information
Shuaishuai et al. Research on License Plate Recognition Algorithm Based on OpenCV
Tai et al. Braille document parameters estimation for optical character recognition
CN114612892B (en) PCB component surface 3D character segmentation method
CN116994261B (en) Intelligent recognition system for big data accurate teaching intelligent question card image
CN113838065B (en) Automatic cloud removing method based on image markers
Zhu Background subtraction and color clustering based moving objects detection

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant