Search

EP-3586324-B1 - METHODS AND SYSTEMS FOR FIRE DETECTION

EP3586324B1EP 3586324 B1EP3586324 B1EP 3586324B1EP-3586324-B1

Inventors

  • ZHENG, JIA
  • TIAN, Jianguo
  • PAN, Huadong

Dates

Publication Date
20260513
Application Date
20170527

Claims (13)

  1. A method for fire detection, comprising: initializing a fire detection; acquiring data related to a monitored area, wherein the data comprises image data related to the monitored area; determining a time at which the image data is captured being a daytime or a nighttime based on grey values of the captured image data, the time being a daytime in response to determining that a percentage of blocks with an average gray value greater than a first threshold in a total blocks of the image data is not less than a second threshold, the time being a nighttime in response to determining that a percentage of blocks with an average gray value greater than the first threshold in the total blocks of the image data is less than the second threshold; determining a first mode comprising a first smoke detection to be executed in response to determining that the time at which the image data is captured being the daytime; performing the first smoke detection by: determining, based on the image data, a first background image, the first background image being updated at a first update rate; determining, based on the image data, a second background image, the second background image being updated at a second update rate, and the second update rate exceeding the first update rate; generating a difference image between the first background image and the second background image; and identifying a candidate smoke region from the difference image, wherein pixels exceeding a threshold are candidate smoke pixels in the candidate smoke region; determining whether there is a risk of fire by conducting a color analysis on the candidate smoke region, conducting the color analysis including comparing one or more color components of a pixel in the candidate smoke region to one or more thresholds to determine the risk of fire; in response to determining that there is no a risk of fire, initializing another fire detection; determining whether the second smoke detection needs to be executed by comparing a size of one or more motion regions with a threshold in response to determining that there is a risk of fire, wherein the motion region is a region in which pixels change in a time period and the second smoke detection is conducted based on at least one of a smoke energy analysis or a smoke diffusion analysis, the smoke energy analysis including determining one or more parameters representative of energy for each of blocks in the candidate smoke region, and the smoke diffusion analysis being conducted based on a number of potential smoke blocks increasing, decreasing, or maintaining in a time period in the candidate smoke region; in response to determining that the second smoke detection does not need to be executed, configuring an image acquisition device and acquiring new image data related to the monitored area; in response to determining that the second smoke detection needs to be executed, performing the second smoke detection; determining a second mode comprising a first flame detection to be executed in response to determining that the time at which the image data is captured being the nighttime; performing the first flame detection; determining whether there is a risk of fire based on information related to the first flame detection; in response to determining that there is no a risk of fire, initializing another fire detection; in response to determining that there is a risk of fire, determining whether the second flame detection needs to be executed by determining whether a motion region percentage is less than a threshold; in response to determining that the motion region percentage is less than the threshold, acquiring an image with adjusting preset information of the image acquisition device; in response to determining that the motion region percentage is not less than the threshold, conducting the second flame detection; determining whether a fire has been detected based on the second smoke detection and the second flame detection; in response to determining that a fire has been detected, generating and/or outputting a notification; and in response to determining that a fire has not been detected, initializing another fire detection.
  2. The method of claim 1, wherein the identifying a candidate smoke region from the difference image comprises: determining whether one or more smoke pixels exist in the difference image by comparing the pixel value of each pixel of the difference image with a threshold; in response to determining that one or more smoke pixels exist in the difference image, generating one or more foreground images based on the difference image; and identifying the candidate smoke region based on the one or more foreground images.
  3. The method of claim 2, wherein the conducting the color analysis includes conducting the color analysis based on a YUV model.
  4. The method of any one of claims 1 to 3, further comprising: in response to determining that the second smoke detection needs to be executed, performing the second smoke detection by: dividing the candidate smoke region into the blocks; conducting at least one of the smoke energy analysis or the smoke diffusion analysis on the blocks; and determining a potential smoke region based on a result of the at least one of the smoke energy analysis or the smoke diffusion analysis.
  5. The method of claim 4, wherein the second smoke detection further comprises determining whether the potential smoke region is a smoke region by processing a portion of the image data that relates to the potential smoke region using a classifier.
  6. The method of claim 1, wherein the first flame detection comprises: generating a background image based on the image data; generating a highlight background region based on the background image; producing a foreground image based on the background image; and identifying a candidate flame region based on at least one of the highlight background region or the foreground image.
  7. The method of claim 6, wherein the second flame detection comprises: acquiring a highlight edge region related to the highlight background region; identifying a foreground accumulation image based on the candidate flame region; determining a flicker foreground image based on at least one of the highlight edge region or the foreground accumulation image; and processing image data related to the flicker foreground image using a classifier.
  8. The method of any one of claims 1-5, further comprising identifying a portion of the image data corresponding to the area for the fire detection by performing a skyline detection on the image data.
  9. A system for fire detection, comprising: an image acquisition module configured to acquire image data related to a monitored area; and an analysis module configured to initialize a fire detection; determine a time at which the image data is captured being a daytime or a nighttime based on grey values of the captured image data, the time being a daytime in response to determining that a percentage of blocks with an average gray value greater than a first threshold in a total blocks of the image data is not less than a second threshold, the time being a nighttime in response to determining that a percentage of blocks with an average gray value greater than the first threshold in the total blocks of the image data is less than the second threshold; and determine a first mode comprising a first smoke detection to be executed in response to determining that the time at which the image data is captured being the daytime, perform the first smoke detection by: determining, based on the image data, a first background image, the first background image being updated at a first update rate; determining, based on the image data, a second background image, the second background image being updated at a second update rate, and the second update rate exceeding the first update rate; generating a difference image between the first background image and the second background image; and identifying a candidate smoke region from the difference image, wherein pixels exceeding a threshold are candidate smoke pixels in the candidate smoke region; and determine whether there is a risk of fire by conducting a color analysis on the candidate smoke region, conducting the color analysis including comparing one or more color components of a pixel in the candidate smoke region to one or more thresholds to determine the risk of fire; in response to determining that there is no a risk of fire, initialize another fire detection; determine whether the second smoke detection needs to be executed by comparing a size of one or more motion regions with a threshold in response to determining that there is a risk of fire, wherein the motion region is a region in which pixels change in a time period and the second smoke detection is conducted based on at least one of a smoke energy analysis or a smoke diffusion analysis, the smoke energy analysis including determining one or more parameters re presentative of energy for each of blocks in the candidate smoke region, and the smoke diffusion analysis including determining a number of potential smoke blocks in the candidate smoke region; in response to determining that the second smoke detection does not need to be executed, configure an image acquisition device and acquire new image data related to the monitored area; in response to determining that the second smoke detection needs to be executed, perform the second smoke detection; determine a second mode comprising a first flame detection to be executed in response to determining that the time at which the image data is captured being the nighttime; perform the first flame detection; determine whether there is a risk of fire based on information related to the first flame detection; in response to determining that there is no a risk of fire, initialize another fire detection; in response to determining that there is a risk of fire, determine whether the second flame detection needs to be executed by determining whether a motion region percentage is less than a threshold; in response to determining that the motion region percentage is less than the threshold, acquire an image with adjusting preset information of the image acquisition device; in response to determining that the motion region percentage is not less than the threshold, conduct the second flame detection; determine whether a fire has been detected based on the second smoke detection and the second flame detection; in response to determining that a fire has been detected, generate and/or output a notification; and in response to determining that a fire has not been detected, initialize another fire detection.
  10. The system of claim 9, wherein the identifying a candidate smoke region from the difference image comprises: determining whether one or more smoke pixels exist in the difference image by comparing the pixel value of each pixel of the difference image with a threshold; in response to determining that one or more smoke pixels exist in the difference image, generating one or more foreground images based on the difference image; and identifying the candidate smoke region based on the one or more foreground images.
  11. The system of claim 10, wherein in response to determining that a second smoke detection needs to be executed, the analysis module is further configured to conduct the second smoke detection by: dividing the candidate smoke region into a plurality of blocks; conducting at least one of a smoke energy analysis or a smoke diffusion analysis on the plurality of blocks; and determining a potential smoke region based on at least one of the smoke energy analysis or the smoke diffusion analysis.
  12. The system of claim 9, wherein the analysis module further comprises a flame detection unit configured to conduct the first flame detection by: generating a background image based on the image data; generating a highlight background region based on the background image; producing a foreground image based on the background image; and identifying a candidate flame region based on at least one of the highlight background region or the foreground image.
  13. The system of claim 12, wherein the flame detection unit is further configured to conduct the second flame detection by: acquiring a highlight edge region related to the highlight background region; generating a foreground accumulation image based on the candidate flame region; determining a flicker foreground image based on at least one of the highlight edge region or the foreground accumulation image; and processing image data related to the flicker foreground image using a classifier.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present disclosure claims priority of Chinese Application No. CN 201710193196.4 filed on March 28, 2017. TECHNICAL FIELD The present disclosure generally relates to image processing, and more particularly, to fire detection using image processing techniques. BACKGROUND Fast and continuous establishment of industrial business and home buildings may have contributed to an increasing number of fire incidents. In addition, significant climate change may have caused increasingly destructive wildfires globally. Accordingly, it would be desirable to provide new mechanisms for fire detection. CN101587622B is directed to methods and devices for forest fire detection. CN101872526A is directed to methods for fire detection. TASDEMIR K ET AL: "Video based fire detection at night", SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, 2009. SIU 2009. IEEE 17TH, IIEEE, PISCATAWAY, NJ, USA, 9 April 2009 (2009-04-09), pages 720-723, XP031480637, ISBN:987-1-4244-4435-9 provides a method for video-based detection of fire at night (in the dark). SUMMARY The invention is set out in the appended set of claims. BRIEF DESCRIPTION OF THE DRAWINGS The present disclosure is further described in terms of exemplary embodiments. These exemplary embodiments are described in detail with reference to the drawings. These embodiments are non-limiting exemplary embodiments, in which like reference numerals represent similar structures throughout the several views of the drawings, and wherein: FIG. 1 is a generalized block diagram of an example of a system for fire detection in accordance with some embodiments of the disclosed subject matter;FIG. 2 is a block diagram illustrating an example of a fire detection system in accordance with some embodiments of the disclosed subject matter;FIG. 3 is a flowchart illustrating an example of a process for fire detection in accordance with some embodiments of the disclosed subject matter;FIG. 4 is a block diagram illustrating an example of a monitoring module in accordance with some embodiments of the disclosed subject matter;FIG. 5 is a block diagram illustrating an example of an analysis module in accordance with some embodiments of the disclosed subject matter;FIG. 6 is a flow diagram illustrating an example of a process for fire detection in accordance with some embodiments of the disclosed subject matter;FIG. 7A is a flow diagram illustrating an example of a process for first smoke detection in accordance with some embodiments of the disclosed subject matter;FIG. 7B is a flow diagram illustrating an example of a process for second smoke detection in accordance with some embodiments of the disclosed subject matter;FIG. 8A is a flow diagram illustrating an example of a process for first flame detection in accordance with some embodiments of the disclosed subject matter;FIG. 8B is a flow diagram illustrating an example of a process for second flame detection in accordance with some embodiments of the disclosed subject matter;FIG. 9 is a flow diagram illustrating an example of a process for smoke detection in accordance with some embodiments of the disclosed subject matter; andFIG. 10 is a flow diagram illustrating an example of a process for flame detection in accordance with some embodiments of the disclosed subject matter. DETAILED DESCRIPTION In the following detailed description, numerous specific details are set forth by way of example in order to provide a thorough understanding of the relevant disclosure. However, it should be apparent to those skilled in the art that the present disclosure may be practiced without such details. In other instances, well-known methods, procedures, systems, components, and/or circuitry have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present disclosure. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments shown, but to be accorded the widest scope consistent with the claims. It will be understood that the term "system," "module" and/or "unit" used herein are one method to distinguish different components, elements, parts, section or assembly of different level in ascending order. However, the terms may be displaced by another expression if they may achieve the same purpose. It will be understood that when a device, unit or module is referred to as being "on," "connected to," or "coupled to" another device, unit, or module, it may be directly on, connected or coupled to, or communicate with the other device, unit, or module, or an intervening device, unit, or module may be present, unless the context clearly indicates otherwise. As used herein, the term "and/or" includes any an