Flame detection method and device combined with polariscope, equipment and medium

By using a composite polarizer in the flame detection system to automatically adjust the polarizer state and perform geometric calculations, the misjudgment problem of flame detection in the light environment is solved, and higher detection accuracy and reliability are achieved.

CN120388325AActive Publication Date: 2025-07-29GUANGDONG ZHISHI CLOUD CONTROL TECHNOLOGY CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202510276658.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-10
Publication Date
2025-07-29
Estimated Expiration
2045-03-10

AI Technical Summary

Technical Problem

Existing flame detection technology is prone to misjudgment in strong or low-light environments, resulting in a decrease in detection accuracy.

Method used

A composite polarizer is used to automatically adjust the polarizer state under different light intensities, and combine geometric calculations to determine the angle between the light source line segment and the reference line to conduct secondary confirmation of flame events.

Benefits of technology

It effectively reduces the false alarm of flame events caused by light environment interference and improves the accuracy and reliability of flame detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120388325A_ABST
    Figure CN120388325A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of flame detection, in particular to a flame detection method, device and equipment combined with a polariscope and a medium, and the method comprises the following steps: when a composite polariscope is in a polaroid-free state, controlling a camera device to carry out image acquisition on a detection area; if the flame target is detected in the first image acquired by the camera device, setting the composite polariscope to be in a polaroid state of a level corresponding to the environment illumination intensity; light source targets are detected in a second image collected by the camera device, and if it is determined that the light source targets corresponding to the flame target exist in the second image and the number of the light source targets is multiple, multiple light source line segments are formed based on the multiple light source targets, determining whether a flame event exists or not based on the included angle between the light source line segment and the two reference lines with the shortest distance; the flame detection accuracy can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of flame detection, and particularly to a flame detection method, device, equipment and medium combined with a polarizer. Background Art

[0002] In public places, important facilities and large-scale events, cameras are usually used for real-time monitoring, and a flame detection system is used to timely identify potential fire risks.

[0003] The detection method in the related art realizes flame detection through video 2D pictures and is relatively sensitive to light conditions. The change of light in the video picture may affect the recognition of flame characteristics, thereby affecting the detection accuracy. For example, in strong light or weak light environments, the characteristics such as the color and brightness of the flame may change, resulting in the camera may misjudge other bright light sources (such as car lights, reflective objects, etc.) as flames, causing unnecessary alarms. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present invention is to provide a flame detection method, device, equipment and medium combined with a polarizer to improve the accuracy of flame detection.

[0005] On the one hand, the embodiments of the present invention provide a flame detection method combined with a polarizer, and the method includes the following steps: When the composite polarizer is in a non-polarizing film state, control the imaging device to collect images of the detection area; wherein, the composite polarizer is arranged in the collection direction of the imaging device, and the composite polarizer includes a non-polarizing film state and multiple levels of polarizing film states; If a flame target is detected in the first image collected by the imaging device, set the composite polarizer to the polarizing film state corresponding to the environmental light intensity level; Detect a light source target in the second image collected by the imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, then form multiple light source line segments based on the multiple light source targets, and determine whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance; wherein, the reference line is a line segment perpendicular to the driving lane and parallel to the road surface in the detection area.

[0006] Optionally, the setting the composite polarizer to the polarizing film state corresponding to the environmental light intensity level includes: Obtain a correspondence table between the average light intensity and the polarizing film state. The correspondence table includes multiple continuous light intensity intervals, each light intensity interval corresponds to a polarizing film state, and the level of the polarizing film state increases as the light intensity interval decreases; Determine the light intensity range in the corresponding relationship table where the ambient light intensity is located, and set the polarizing lens to the polarizing film state corresponding to this light intensity range.

[0007] Optionally, the determining whether there is a light source target corresponding to the flame target in the second image includes: If a flame target is detected in the first image collected by the imaging device, obtain the initial position and moving speed of the flame target in the detection area; Determine the time difference between collecting the second image and the first image, and determine the predicted position of the flame target based on the time difference, the initial position of the flame target in the detection area, and the moving speed; Based on whether the position of the light source target in the detection area is within the predicted position of the flame target, if so, determine that there is a light source target corresponding to the flame target in the second image.

[0008] Optionally, the method further includes: If it is determined that there is a light source target corresponding to the flame target in the second image and the number of the light source targets is one, determine that the flame target is a flame and there is a flame event.

[0009] Optionally, the forming multiple light source line segments based on the multiple light source targets includes: Obtain the position of each light source target in the detection area, determine the center point of each light source target, and connect the center points of each light source target in pairs to form multiple light source line segments.

[0010] Optionally, the determining whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance includes: If it is determined that both angles are greater than the angle threshold, determine that the flame target is a flame and determine that there is a flame event.

[0011] Optionally, the method further includes: After determining whether the flame target is a flame, set the compound polarizing lens to the non-polarizing film state.

[0012] On the other hand, an embodiment of the present invention provides a flame detection device combined with a polarizing lens, characterized in that the device includes: A first module, configured to control the imaging device to collect images of the detection area when the compound polarizing lens is in the non-polarizing film state; wherein, the compound polarizing lens is arranged in the collection direction of the imaging device, and the compound polarizing lens includes a non-polarizing film state and multiple levels of polarizing film states; A second module, configured to set the compound polarizing lens to the polarizing film state corresponding to the ambient light intensity if a flame target is detected in the first image collected by the imaging device; A third module is configured to detect a light source target in a second image collected by an imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, multiple light source line segments are formed based on the multiple light source targets, and whether a flame event exists is determined based on the included angle between the light source line segments and the two reference lines with the shortest distance; wherein, the reference lines are line segments perpendicular to the driving lane and parallel to the road surface within the detection area.

[0013] On the other hand, an embodiment of the present invention provides an electronic device, which includes: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0014] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used to execute the above method when executed by the processor.

[0015] The embodiments of the present invention have the following beneficial effects: In this embodiment, when a flame target is detected in the state without a polarizer, it is preliminarily determined that a flame event may occur; then, according to the ambient light intensity, the corresponding level of polarizer state is determined, and the polarizing lens in front of the camera is set to this polarizer state, and then image acquisition is continued; the secondary confirmation of the flame event is realized, and by using geometric calculation to judge the relationship between the light source line segment and the known reference line, and calculating the included angle to distinguish the nature of the light source. The present invention effectively reduces the false alarm of the flame event caused by the interference of the illumination environment in the detected video image by adding a polarizing lens to filter the light of the video picture, and improves the accuracy of the flame event detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0017] Figure 1 It is a schematic flowchart of the steps of a flame detection method combining a polarizing lens provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the detection area in an embodiment of the present invention; Figure 3 It is a front view of a composite polarizing lens in an embodiment of the present invention; Figure 4It is a design schematic diagram of the composite polarizer in the embodiment of the present invention; Figure 5 It is a schematic diagram of the state without a polarizer in the embodiment of the present invention; Figure 6 It is a schematic diagram of the state of the first-level polarizer in the embodiment of the present invention; Figure 7 It is a schematic diagram of the state of the second-level polarizer in the embodiment of the present invention; Figure 8 It is a structural block diagram of a flame detection device combined with a polarizer provided by the embodiment of the present invention; Figure 9 It is a structural block diagram of an electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0018] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the embodiments of the present invention. They are only examples of devices and methods consistent with some aspects of the embodiments of the present invention described in detail in the appended claims.

[0019] It can be understood that the terms "first", "second", etc. used in the present invention can be used in this document to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present invention, the first information can also be called the second information, and similarly, the second information can also be called the first information. Depending on the context, the words "if", "when" as used herein can be interpreted as "when...", "when...", or "in response to determining".

[0020] The terms "at least one", "a plurality", "each", "any one", etc. used in the present invention, at least one includes one, two or more, a plurality includes two or more, each refers to each of the corresponding plurality, and any one refers to any one of the plurality.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0022] Such as Figure 1 And Figure 2As shown in the figure, an embodiment of the present invention provides a flame detection method combined with a polarizer. The method includes the following steps: S100, when the composite polarizer is in a state without a polarizing film, control the imaging device to collect images of the detection area; wherein, the composite polarizer is arranged in the collection direction of the imaging device, and the composite polarizer includes a state without a polarizing film and multiple levels of polarizing film states; S200, if a flame target is detected in the first image collected by the imaging device, set the composite polarizer to the polarizing film state corresponding to the ambient light intensity level; By adjusting the brightness and contrast, filter the background noise and highlight the light source to be detected. By timely adjusting the polarizer, respond to the light source change in real time and reduce the probability of misjudgment.

[0023] S300, detect the light source target in the second image collected by the imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, form multiple light source line segments based on the multiple light source targets, and determine whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance; wherein, the reference line is a line segment perpendicular to the driving lane and parallel to the road surface in the detection area.

[0024] In the embodiment of the present invention, through image preprocessing and feature extraction of the monitoring video, an image recognition algorithm is used to detect the flame target. If a flame target is detected, it is initially judged that a flame event may occur; then, according to the ambient light intensity, the corresponding level of polarizing film state is determined, and the polarizer at the front end of the camera is set to this polarizing film state, and then image collection is continued; to achieve secondary confirmation of the flame event, by using geometric calculation to judge the relationship between the light source and the known reference line and calculating the angle to distinguish the nature of the light source.

[0025] Compared with the traditional flame detection method based on computer vision and deep learning, the originally obtained video image is greatly affected by light interference. By adding a polarizer to filter the light of the video image, the false alarm of the flame event caused by the interference of the light environment of the detected video image is effectively reduced, and the accuracy of the flame event detection is improved.

[0026] In the related art, after a flame event is detected, simply through video detection, due to the lighting effect of vehicle lights, large spots will be formed under the effect of the camera at night, which is very similar to the appearance of a flame and is prone to false alarm events. To reduce the influence of the spots, a polarizer is added in front of the camera. The polarizer reduces the spot brightness and restores the light source, and the flame event is confirmed by detecting the light source.

[0027] However, adding a polarizer will cause the following problems in the video image: ① Light loss: The anti-glare treatment may reduce the light passing through the polarizer, which may cause the image or visual effect to become darker in some cases; ② Color cast: Different types of anti-glare polarizers may introduce a certain degree of color cast, affecting color accuracy; ③ Possible blurriness: In some cases, low-quality polarizers may cause the image to be blurred, affecting clarity.

[0028] To reduce the impact of the polarizer on the video picture effect, the present invention introduces an automatic control technology for the polarizer. When a normal camera detects a flame event, the polarizing film in the polarizer is automatically added in front of the camera. The light source intensity is reduced through the polarizer, and after a second confirmation, the polarizer automatically returns to its original position after the event is confirmed. The present invention can achieve a second confirmation of the flame event by automatically adjusting the state of the polarizing film without affecting the video picture.

[0029] Polarizers are usually divided into two levels, specifically as follows: Level 1 polarizer: The polarization direction of this polarizer is parallel to the filter used. It can effectively reduce reflections and is relatively inexpensive. Level 1 polarizers are widely used in basic daily life.

[0030] Level 2 polarizer: The polarization direction of this polarizer is perpendicular to that of the Level 1 polarizer. Compared with the Level 1 polarizer, the Level 2 polarizer can better eliminate reflections and provide better clarity and contrast. Level 2 polarizers are mainly used in outdoor sports, driving, wilderness exploration and other scenarios.

[0031] Design of the rotation principle of the polarizer: To meet the requirements of different ambient brightness in actual scenarios, the polarizer is designed as a composite polarizer with multiple states. The composite polarizer can be transformed into 3 states, namely no polarizing film, Level 1 polarizing film and Level 2 polarizing film; and the polarizer rotates according to the ambient brightness to achieve the effect of light filtering. The overall design is as shown in Figure 3 and Figure 4 shown.

[0032] Normally, the polarizer is in the polarizer box. When a flame event is detected, during the frame-by-frame processing stage, a loop body is entered to continuously read each frame in the video. For each frame, first the frame is converted into a grayscale image, which can simplify the subsequent brightness calculation. Then, the program calculates the brightness index of the current frame, that is, the average illumination intensity. Finally, the rotation state of the polarizer is set according to the average illumination intensity. Each time the control period of the polarizer is 1S, and after 1S, the state of the polarizing film is restored to light = 0.

[0033] When the state of the polarizing film Light = 0, no polarizing film is in front of the camera, maintaining the initial state. The state of no polarizing film is as shown inFigure 5 as shown

[0034] When the polarizer state Light = 1, the stepper motor rotates clockwise by 120°, and a first-level polarizer is in front of the camera directly. When reset, the stepper motor rotates counterclockwise by 120°. The state of the first-level polarizer is as Figure 6 shown

[0035] When the polarizer state Light = 2, the stepper motor rotates counterclockwise by 120°, and a second-level polarizer is in front of the camera directly. When reset, the stepper motor rotates clockwise by 120°. The state of the second-level polarizer is as Figure 7 shown

[0036] In some embodiments, setting the composite polarizing mirror to the polarizer state corresponding to the ambient light intensity includes: S210, obtaining a correspondence table between the average light intensity and the polarizer state, the correspondence table including a plurality of consecutive light intensity intervals, each light intensity interval corresponding to a polarizer state, and the level of the polarizer state increasing as the light intensity interval decreases; S220, determining the light intensity interval in the correspondence table where the ambient light intensity is located, and setting the polarizing mirror to the polarizer state corresponding to the light intensity interval.

[0037] In this embodiment, the polarizer state of the polarizing mirror is controlled by brightness calculation, avoiding light loss caused by excessive filtering and affecting the detection effect.

[0038] Specifically, the correspondence between the polarizer state and the light intensity is as follows: In an actual scenario, the camera image can be divided into four situations: daytime, evening and sunrise, night with lighting, and night without lighting according to the ambient brightness.

[0039] Without adding a polarizing mirror, video images of four scenarios, namely daytime, evening / sunrise, night with lighting, and night without lighting, are obtained from the camera, the ambient brightness of the video images is detected, and the average light intensity of the four scenarios is calculated.

[0040] Table 1: Average light intensity of four scenarios without adding a polarizing mirror (unit: lux)

[0041] According to the above actually measured data, the correspondence between the light intensity and the polarizer state is set as follows: When the average light intensity > 100, the polarizer state light = 0; indicating that there is no polarizer in front of the camera directly; When 80 < average light intensity < 100, the polarizer state light = 1; indicating that a first-level polarizer is in front of the camera directly.

[0042] When the average light intensity < 80, the polarizer state light = 2. It means that the front of the camera is a secondary polarizer.

[0043] In some embodiments, determining whether there is a light source target corresponding to the flame target in the second image includes: S310, if a flame target is detected in the first image collected by the imaging device, obtain the initial position and moving speed of the flame target in the detection area; S320, determine the time difference between collecting the second image and the first image, and determine the predicted position of the flame target based on the time difference, the initial position of the flame target in the detection area, and the moving speed; S330, based on whether the position of the light source target in the detection area is within the predicted position of the flame target, if so, determine that there is a light source target corresponding to the flame target in the second image.

[0044] In this embodiment, by predicting the position of the flame target and comparing the light source position, the possibility that the light source target is a flame is identified, so as to achieve more accurate fire detection and early warning.

[0045] In some embodiments, the method further includes: If it is determined that there is a light source target corresponding to the flame target in the second image and the number of the light source targets is one, determine that the flame target is a flame and there is a flame event.

[0046] In this embodiment, after combining the filter lens, the light interference is excluded. If the detected light source target is single and there is a light source target corresponding to the flame target, it means that the light source target is the flame target, and it is confirmed that there is an actual flame event.

[0047] In some embodiments, forming multiple light source line segments based on the multiple light source targets includes: Obtain the position of each light source target in the detection area, determine the center point of each light source target, and connect the center points of each light source target in pairs to form multiple light source line segments.

[0048] In this embodiment, the light source targets are simplified in the form of center points, and the center points of each light source target are connected in pairs to form multiple light source line segments, which improves the efficiency of generating light source line segments, facilitates analyzing and identifying the emission direction of the light source, and ensures the accuracy and real-time performance of fire detection.

[0049] In some embodiments, determining whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance includes: If it is determined that both included angles are greater than the included angle threshold, it is determined that the flame target is a flame, and a flame event exists.

[0050] In this embodiment, the included angle calculation method ensures that even in a complex background, the flame event can be accurately determined. By comparing the included angles between the light source line segment and the two reference lines, false alarms can be effectively excluded, and the accuracy and reliability of the fire detection system can be improved.

[0051] In some embodiments, the method further includes: After determining whether the flame target is a flame, the compound polarizing lens is set to the non-polarizing filter state; In this embodiment, after the determination of the flame target is completed, it is readjusted to the non-polarizing filter state to ensure that subsequent image acquisition is not affected by polarization, so as to provide the best image quality for the detection of other potential fire sources.

[0052] The overall process of the embodiment of the present invention is as follows: Detect the flame target in the non-polarizing filter state; Condition 1: In the non-polarizing filter state, no flame target is detected: If no flame target is detected in the video frame, the polarizing lens remains in its original state, i.e., light = 0.

[0053] Condition 2: In the non-polarizing filter state, a flame target is detected; after setting the polarizing filter state of the polarizing lens, a light source target is obtained; Record the flame coordinates; If a flame event is detected in the video frame, record the initial position of the flame event. The coordinate format of the initial position is fire_1steven = [x1, y1, w1, h1], where (x1, y1) is the coordinate of the flame center point, and w1 and h1 are the width and height respectively.

[0054] Calculate the moving speed and direction of the flame to estimate its predicted position at the prediction time. The coordinate calculation formula for the predicted position is: Fire_newlocal = fire_1steven + speed × time; where speed represents the moving speed of the flame (the moving speed is a vector including direction), time represents the set prediction time, and Fire_newlocal represents the coordinate of the predicted position; The motion model is implemented using a Kalman filter to improve the prediction accuracy. The moving speed of the flame is obtained through the motion model. By using the Kalman filter in combination with the motion model (such as uniform linear motion) to predict the future position of the target, effective tracking can be ensured in a dynamic scene.

[0055] Control the polarizer; adjust the state of the polarizer according to the correspondence between the light intensity and the polarizer state. After adjusting the polarizer to the polarizer state corresponding to the light intensity, continue the detection.

[0056] Obtain the monitoring video, intercept the current frame image from the monitoring video, and detect the light source target in the current frame image; Traverse the light source targets detected in the current frame image, obtain the positions of the light source targets, and the coordinates of the positions are represented as fire_2ndeven = [x2, y2, w2, h2]; in the current frame image, judge whether the predicted position Fire_newlocal contains the coordinates of the position fire_2ndeven of the light source target.

[0057] If there is only one light source target obtained, and it is judged that the predicted position contains the position of the light source target, then judge that the light source target is a flame and determine that a flame event has occurred.

[0058] Condition three: Detect a flame target in the state without a polarizer; after setting the polarizer state of the polarizer, obtain multiple light source targets; Obtain the coordinates fire_2ndeven1, fire_2ndeven2,... of all light sources.

[0059] Connect the light source center points in pairs to form light source line segments fire_2nd_line1, fire_2nd_line2,...

[0060] Calculate the shortest distance; Calculate the shortest distance between each light source line segment fire_2nd_line1, fire_2nd_line2,... and the known reference lines x1, x2, x3,... respectively, and obtain the two reference lines with the shortest distance to the light source line segment. For example, the two reference lines with the shortest distance to fire_2nd_line1 are x1 and x2.

[0061] Angle calculation; Calculate the angle between each light source line segment and the reference line. For example: Calculate the angle angles1 between fire_2nd_line1 and the reference line x1.

[0062] Calculate the angle angles2 between fire_2nd_line1 and the reference line x2.

[0063] Judge the angle; If one of the angles is less than 5°, determine that the flame target is caused by a vehicle headlight. For example: When aangles1 < 5° or angles2 < 5°, judge it as a light source caused by a vehicle headlight and exclude the flame event.

[0064] If all included angles are greater than 5°, it is determined that the flame target is caused by a flame. For example: When angles1 > 5° and angles2 > 5°, it is determined that the flame target is a flame, and it is confirmed as a flame event.

[0065] After determining that a flame event has occurred, reset the polarizer state to the non-polarizer state.

[0066] According to motion prediction, determine whether multiple flame targets are the same event; according to motion prediction, if the positions of the flame targets coincide, they are defined as the same event and no repeated detection is performed.

[0067] In the embodiment of the present invention, considering that when the vehicle is driving, one or more light sources will appear on the detected video screen. After being filtered by the polarizing lens, the positions of the light sources are restored, and the central points of any two light sources are respectively connected in pairs to obtain the light source line segment fire_2nd_line; Considering situations such as the existence of road bends on the road surface, therefore, according to the road surface change, within the road surface detection area, take multiple reference lines X1, X2, X3,... that are perpendicular to the driving lane and parallel to the road surface; Considering the situation where the driving direction of the vehicle is straight and parallel to the road surface direction, the headlight line is relatively parallel to the road surface, and the headlight line is relatively parallel to the reference line. Therefore, the detected light source line segment is relatively parallel to the reference line; Considering situations such as the vehicle bouncing up and down, turning left and right, and the road surface turning during driving, that is, there is a deflection angle between the driving direction of the vehicle and the road surface direction, then there is also a deflection angle between the headlight line and the reference line. Therefore, set the threshold angle angles of the deflection angle, and the initial value of angles is 5°.

[0068] Refer to Figure 8 , the embodiment of the present invention provides a flame detection device combined with a polarizing lens, and the device includes: The first module is used to control the imaging device to collect images of the detection area when the composite polarizing lens is in the non-polarizer state; wherein, the composite polarizing lens is arranged in the collection direction of the imaging device, and the composite polarizing lens includes a non-polarizer state and multiple levels of polarizer states; The second module is used to set the composite polarizing lens to the polarizer state corresponding to the environmental light intensity if a flame target is detected in the first image collected by the imaging device; A third module is configured to detect a light source target in a second image collected by an imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, multiple light source line segments are formed based on the multiple light source targets, and whether a flame event exists is determined based on the included angles between the light source line segments and the two reference lines with the shortest distance; wherein, the reference lines are line segments perpendicular to the driving lane and parallel to the road surface within the detection area.

[0069] It can be understood that the content in the above method embodiments is applicable to this device embodiment. The functions specifically implemented by this device embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0070] Reference Figure 9 , an embodiment of the present invention further provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method in the above embodiment is implemented.

[0071] It can be understood that the content in the above method embodiments is applicable to this embodiment. The functions specifically implemented by this embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0072] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above method is implemented.

[0073] It can be understood that the content in the above method embodiments is applicable to this storage medium embodiment. The functions specifically implemented by this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0074] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0075] The embodiments described in the embodiments of the present invention are to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation to the technical solutions provided by the embodiments of the present invention. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0076] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation to the embodiments of the present invention, and may include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0079] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present invention and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0080] It should be understood that, in the present invention, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Here, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0081] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0082] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0084] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memory (ROM), random-access memory (RAM), magnetic disks, or optical discs.

[0085] The preferred embodiments of the embodiments of the present invention have been described above with reference to the accompanying drawings, and thus do not limit the scope of the rights of the embodiments of the present invention. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present invention shall be within the scope of the rights of the embodiments of the present invention.

Claims

1. A flame detection method combined with a polarizer, characterized in that, The method includes the following steps: When the compound polarizer is in the state of no polarizing film, control the imaging device to collect images of the detection area; wherein, the compound polarizer is arranged in the collection direction of the imaging device, and the compound polarizer includes the state of no polarizing film and multiple levels of polarizing film states; If a flame target is detected in the first image collected by the imaging device, set the compound polarizer to the polarizing film state corresponding to the environmental light intensity level; Detect a light source target in the second image collected by the imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, then form multiple light source line segments based on the multiple light source targets, and determine whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance; wherein, the reference line is a line segment perpendicular to the driving lane and parallel to the road surface in the detection area.

2. The method according to claim 1, wherein The setting the compound polarizer to the polarizing film state corresponding to the environmental light intensity level includes: Obtain a correspondence table between the average light intensity and the polarizing film state. The correspondence table includes multiple continuous light intensity intervals, each light intensity interval corresponds to a polarizing film state, and the level of the polarizing film state increases as the light intensity interval decreases; Determine the light intensity interval where the environmental light intensity is located in the correspondence table, and set the polarizer to the polarizing film state corresponding to the light intensity interval.

3. The method according to claim 2, wherein The determining whether there is a light source target corresponding to the flame target in the second image includes: If a flame target is detected in the first image collected by the imaging device, obtain the initial position and moving speed of the flame target in the detection area; Determine the time difference between the collection of the second image and the first image, and determine the predicted position of the flame target based on the time difference, the initial position and the moving speed of the flame target in the detection area; Based on whether the position of the light source target in the detection area is within the predicted position of the flame target, if so, determine that there is a light source target corresponding to the flame target in the second image.

4. The method according to claim 1, wherein The method further includes: If it is determined that there is a light source target corresponding to the flame target in the second image and the number of the light source targets is one, determine that the flame target is a flame and there is a flame event.

5. The method according to claim 1, wherein The forming multiple light source line segments based on the multiple light source targets includes: Obtain the position of each light source target in the detection area, determine the center point of each light source target, and connect the center points of each light source target in pairs to form multiple light source line segments.

6. The method according to claim 1, wherein The determining whether there is a flame event based on the angle between the light source line segment and the two reference lines with the shortest distance includes: If it is determined that both angles are greater than the angle threshold, determine that the flame target is a flame and determine that there is a flame event.

7. The method according to claim 1, wherein The method further includes: After determining whether the flame target is a flame, set the compound polarizer to the state of no polarizing film.

8. A flame detection device combined with a polarizer, characterized in that, The device includes: The first module is used to control the imaging device to collect images of the detection area when the composite polarizer is in the non-polarizing filter state; wherein, the composite polarizer is arranged in the acquisition direction of the imaging device, and the composite polarizer includes a non-polarizing filter state and multiple levels of polarizing filter states; The second module is used to set the composite polarizer to the polarizing filter state corresponding to the ambient light intensity level if a flame target is detected in the first image collected by the imaging device; The third module is used to detect a light source target in the second image collected by the imaging device. If it is determined that there is a light source target corresponding to the flame target in the second image and the number of light source targets is multiple, then multiple light source line segments are formed based on the multiple light source targets, and it is determined whether there is a flame event based on the angle between the light source line segments and the two reference lines with the shortest distance; wherein, the reference lines are line segments perpendicular to the driving lane and parallel to the road surface in the detection area.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that, The program executable by the processor is used to execute the method according to any one of claims 1 to 7 when executed by the processor.

Citation Information

Patent Citations

  • Method and device for reading identification mark on surface of wafer

    CN101334840A

  • Stereoscopic image display and method for producing the same

    CN101639617A

  • System used for conducting on-line monitoring for pushed slab kiln inner wall surface condition

    CN103090814A

  • Online real-time dynamic detection system for carbon content of converter steelmaking molten steel

    CN106153553A