A remote security assessment method, device and system

Abstract

The present invention relates to the field of remote assessment technology, and in particular to a method, device and system for remote safety assessment. The present invention determines a warning for a heat source according to a heat source risk evaluation value, determines a preset height, determines whether to save the two adjacent frames of images as a group of image pairs according to the structural similarity between the two adjacent frames of images in a recorded video, determines a sampling method for sampling the image pairs according to a second relative difference between the structural similarity and a preset structural similarity, determines a warning for a thermal airflow and a correction to a second preset heat source risk evaluation value according to the thermal airflow evaluation value, and overcomes the problem in the prior art that the thermal airflow above the heat source cannot be directly detected by a sensor, and that there is a lack of an accurate evaluation method to remotely evaluate the thermal airflow conditions on a UAV flight path, resulting in a risk of crashing the UAV when passing through the thermal airflow.

Description

Technical Field

[0001] The present invention relates to the technical field of remote assessment, and in particular to a method, device and system for remote security assessment. Background Art

[0002] When conducting drone flight missions, the flight safety of the drone is an important consideration. Especially in industrial environments, drones may need to fly over heat sources, such as chimneys, smelting furnaces, or other equipment that generates heat. The thermal airflow above these heat sources can pose a serious threat to the stability and safety of the drone. Thermal airflow may cause the drone to experience unstable aerodynamic effects and may even cause the drone to crash. In order to ensure the safe flight of the drone, real-time monitoring and evaluation of the heat source and the thermal airflow above it are required. Traditional monitoring methods may not provide enough information to assess the risks of drones flying over heat sources. For example, sensors in existing technologies cannot accurately detect thermal airflow remotely for safety assessment, and provide early warnings to drones to avoid danger.

[0003] Chinese Patent Publication No.: CN105235907A discloses a power line inspection drone equipped with a heat source detector, including a remote-controlled drone and a rotatable camera provided on the bottom of the remote-controlled drone; also includes a circuit device provided inside the remote-controlled drone, the circuit device includes a main control device, a communication module for receiving flight command signals and transmitting monitoring signals, the communication module and the camera are respectively connected to the main control device by signal; also includes a power module provided in the remote-controlled drone for powering the circuit device; the communication module includes an antenna, the antenna is pivotally connected to the bottom of the remote-controlled drone; also includes a heat source detector for detecting heat sources, the heat source detector is provided at the bottom of the remote-controlled drone and is connected to the main control device by signal.

[0004] It can be seen that the existing technology has the following problems: since the thermal airflow above the heat source cannot be directly detected by sensors, and there is a lack of accurate evaluation methods to remotely evaluate the thermal airflow conditions on the flight path of the drone, there is a risk of crashing the drone when passing through the thermal airflow. Summary of the invention

[0005] To this end, the present invention provides a remote safety assessment method, device and system to overcome the problem that the prior art cannot directly detect the thermal airflow above the heat source through sensors, and lacks an accurate assessment method to remotely assess the thermal airflow conditions on the flight path of the UAV, resulting in the risk of crashing the UAV when passing through the thermal airflow.

[0006] To achieve the above object, on the one hand, the present invention provides a remote security assessment method, comprising:

[0007] Determine a heat source risk assessment value, and determine an early warning of the heat source according to the heat source risk assessment value, or determine to record a video at a preset height above the heat source;

[0008] Determining the preset height according to a first relative difference between the heat source risk assessment value and a first preset heat source risk assessment value;

[0009] Determining whether to save two adjacent frames of images as a group of image pairs according to the structural similarity between the two adjacent frames of images in the recorded video;

[0010] Determining a sampling method for sampling the image pair according to a second relative difference between the structural similarity and a preset structural similarity;

[0011] A thermal flow evaluation value is determined, and a warning for the thermal flow is determined according to the thermal flow evaluation value, or a correction to the second preset heat source risk evaluation value is determined according to a third relative difference between the thermal flow evaluation value and the first preset thermal flow evaluation value.

[0012] Furthermore, the heat source risk assessment value is calculated according to the following formula:

[0013]

[0014] Among them, R represents the heat source risk assessment value, W represents the maximum temperature of the heat source, M0 represents the total pixel area of ​​the thermal imaging image of the heat source, and M represents the pixel area of ​​the area where the temperature is greater than 100°C in the thermal imaging image of the heat source.

[0015] Furthermore, based on the comparison result that the heat source risk assessment value is greater than the second preset heat source risk assessment value, it is determined to issue an early warning for the heat source; and based on the comparison result that the heat source risk assessment value is less than or equal to the second preset heat source risk assessment value and greater than or equal to the first preset heat source risk assessment value, it is determined to record a video at a preset height above the heat source.

[0016] Further, according to the comparison result that the first relative difference is less than or equal to the first preset relative difference, the preset height is determined to be the first preset height G1=G0×ln(△R1+1), and according to the comparison result that the first relative difference is greater than the first preset relative difference, the preset height is determined to be the second preset height G2=G0×ln(△R1+1.5).

[0017] Furthermore, according to the comparison result that the structural similarity SSIM between two adjacent frames of images in the recorded video is greater than a preset structural similarity SSIM0, it is determined that the two adjacent frames of images are saved as a group of image pairs.

[0018] Further, based on the comparison result that the second relative difference is less than or equal to the second preset relative difference, it is determined that the image pair is sampled in a first sampling manner, and the first sampling manner is to collect sub-area images with a size of 50×50 pixels in the upper left corner of the image in the image pair to form a first sub-area image pair, collect sub-area images with a size of 50×50 pixels in the center of the image in the image pair to form a second sub-area image pair, and collect sub-area images with a size of 50×50 pixels in the lower right corner of the image in the image pair to form a third sub-area image pair.

[0019] Further, based on the comparison result that the second relative difference is greater than the second preset relative difference, it is determined that the image pair is sampled in a second sampling manner, and the second sampling manner is to collect sub-area images of 100×100 pixels in the upper left corner of the image in the image pair to form a first sub-area image pair, collect sub-area images of 100×100 pixels in the center of the image in the image pair to form a second sub-area image pair, and collect sub-area images of 100×100 pixels in the lower right corner of the image in the image pair to form a third sub-area image pair.

[0020] Furthermore, the thermal flow evaluation value is calculated according to the following formula:

[0021]

[0022] Wherein, P represents the thermal airflow evaluation value, Ai1 represents the normalized cross-correlation of the two sub-area images of the first sub-area image pair in the i-th image pair of the video, Ai2 represents the normalized cross-correlation of the two sub-area images of the second sub-area image pair in the i-th image pair of the video, Ai3 represents the normalized cross-correlation of the two sub-area images of the third sub-area image pair in the i-th image pair of the video, and n represents the number of image pairs in the video;

[0023] According to the comparison result that the thermal flow evaluation value is greater than the second preset thermal flow evaluation value, it is determined to give an early warning for the thermal flow; according to the comparison result that the thermal flow evaluation value is less than or equal to the second preset thermal flow evaluation value and greater than or equal to the first preset thermal flow evaluation value, it is determined whether to correct the second preset heat source risk evaluation value according to the third relative difference between the thermal flow evaluation value and the first preset thermal flow evaluation value;

[0024] The correction coefficient is determined according to the comparison result that the third relative difference is greater than the third preset relative difference. The second preset heat source risk assessment value is revised.

[0025] On the other hand, the present invention also provides a device applied to the method of remote security assessment, comprising: a drone, a gimbal arranged below the drone, and an image acquisition module arranged on the gimbal;

[0026] The image acquisition module is provided with a thermal imager for collecting thermal images and an industrial camera for recording videos.

[0027] On the other hand, the present invention also provides a system for a method for remote security assessment, comprising:

[0028] A data acquisition unit, connected to the image acquisition module, for acquiring the thermal image of the heat source collected by the thermal imager and the video recorded by the industrial camera;

[0029] a first warning unit, which is connected to the data acquisition unit, and is used to determine a heat source risk assessment value according to the data acquired by the data acquisition unit, and to determine a warning for the heat source according to the heat source risk assessment value, or to determine to perform video recording at a preset height above the heat source;

[0030] a sampling unit, which is connected to the data acquisition unit and the first warning unit respectively, and is used to determine whether to save the two adjacent frames of images as a group of image pairs according to the structural similarity between the two adjacent frames of images in the recorded video, and determine a sampling method for sampling the image pairs according to a second relative difference between the structural similarity and a preset structural similarity;

[0031] A second warning unit is respectively connected to the first warning unit and the sampling unit, and is used to determine a thermal airflow evaluation value, and determine a warning for the thermal airflow according to the thermal airflow evaluation value, or determine a correction to a second preset heat source risk evaluation value according to a third relative difference between the thermal airflow evaluation value and the first preset thermal airflow evaluation value.

[0032] Compared with the prior art, the present invention has the advantage that the present invention calculates the heat source risk assessment value through the maximum temperature of the heat source, the total pixel area of ​​the thermal imaging image of the heat source, and the pixel area of ​​the area with a temperature greater than 100°C in the thermal imaging image of the heat source to accurately evaluate the risk situation of the heat source.

[0033] Furthermore, the present invention remotely determines whether to issue an early warning for the heat source through a comparison result between the heat source risk assessment value and a preset heat source risk assessment value. Accurately issuing an early warning based on the risk situation of the heat source helps to optimize the flight path of the UAV and avoid flying over the area, thereby ensuring the safety of the flight. When the heat source risk assessment value is between the first preset heat source risk assessment value and the second preset heat source risk assessment value, it is determined to record a video at a preset height above the heat source to further accurately remotely judge whether the air above the heat source is suitable for flying through the video.

[0034] Furthermore, the present invention determines the preset height by comparing the first relative difference between the heat source risk assessment value and the first preset heat source risk assessment value with the first preset relative difference, and further calculates the precise and appropriate height according to the formula. If the preset height is too high or too low, the video cannot accurately record the thermal airflow conditions above the heat source, thereby affecting the detection of the thermal airflow.

[0035] Furthermore, the present invention determines whether to save the two adjacent frames of images as a group of image pairs by comparing the structural similarity SSIM between the two adjacent frames of images in the recorded video with a preset structural similarity SSIM0, and accurately selects a high-quality background image with smaller picture changes as the background of the thermal airflow, thereby improving the accuracy of thermal airflow detection.

[0036] Furthermore, the present invention determines a sampling method for sampling the image pair according to a second relative difference between the structural similarity and a preset structural similarity, so as to select a sub-area image pair of appropriate size, thereby avoiding waste of computing resources and computing delays caused by oversampling while ensuring the thermal airflow detection effect.

[0037] Furthermore, the thermal flow evaluation value of the present invention indirectly evaluates the intensity of the thermal flow based on the normalized cross-correlation of three sub-area image pairs of several image pairs in the video. Since the thermal flow cannot be directly detected by a remote instrument, the refraction of light by the thermal flow can cause image deformation, and the intensity of the thermal flow can be evaluated at a longer distance.

[0038] Furthermore, the present invention accurately warns of thermal airflow in advance based on the comparison result of the thermal airflow evaluation value with the preset thermal airflow evaluation value, thereby avoiding the occurrence of drone crashes. At the same time, when the thermal airflow evaluation value is in the middle range, the third relative difference between the thermal airflow evaluation value and the first preset thermal airflow evaluation value is determined to determine whether to correct the second preset heat source risk evaluation value, thereby further improving the sensitivity of heat source warning.

[0039] Furthermore, the present invention determines whether to correct the second preset heat source risk assessment value by comparing the third relative difference with the third preset relative difference, and accurately judges whether the sensitivity to the heat source warning needs to be corrected.

[0040] Furthermore, the present invention calculates the correction coefficient according to the formula so that the correction of the second preset heat source risk assessment value is more accurate and controllable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method based on remote security assessment according to an embodiment of the present invention;

[0042] Figure 2 A structural diagram of a device for applying a remote security assessment method according to an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a system for applying a remote security assessment method according to an embodiment of the present invention;

[0044] In the figure, 1-UAV, 2-Gimbal, 3-Image acquisition module, 4-Thermal imager, 5-Industrial camera. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with 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.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0047] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0048] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] See also Figure 1-3 As shown, Figure 1 A flowchart of a method based on remote security assessment according to an embodiment of the present invention; Figure 2 A structural diagram of a device for applying a remote security assessment method according to an embodiment of the present invention; Figure 3 The present invention is a schematic diagram of the structure of a system for applying a remote security assessment method according to an embodiment of the present invention.

[0050] The method based on remote security assessment in an embodiment of the present invention includes:

[0051] Step S1, determining a heat source risk assessment value R, and determining an early warning of the heat source according to the heat source risk assessment value R, or determining to perform video recording at a preset height above the heat source;

[0052] Step S2, when it is determined to record a video at a preset height above the heat source, the preset height is determined according to a first relative difference ΔR1 between the heat source risk assessment value R and a first preset heat source risk assessment value R1;

[0053] Step S3, when the video recording at the preset height above the heat source is completed, determining whether to save the two adjacent frames of images as a group of image pairs according to the structural similarity SSIM between the two adjacent frames of images in the recorded video;

[0054] Step S4, when the image pair in the video is saved, determining a sampling method for sampling the image pair according to a second relative difference ΔSSIM between the structural similarity SSIM and a preset structural similarity SSIM0;

[0055] Step S5, when the sampling of the image pair is completed, the thermal airflow evaluation value P is determined, and the warning of the thermal airflow is determined according to the thermal airflow evaluation value P, or the correction of the second preset heat source risk evaluation value R2 is determined according to the third relative difference ΔP between the thermal airflow evaluation value P and the first preset thermal airflow evaluation value P1.

[0056] Specifically, the heat source risk assessment value R is calculated according to the following formula:

[0057]

[0058] Wherein, W represents the maximum temperature of the heat source, M0 represents the total pixel area of ​​the thermal imaging image of the heat source, and M represents the pixel area of ​​the area where the temperature is greater than 100° C. in the thermal imaging image of the heat source.

[0059] Specifically, the present invention calculates the heat source risk assessment value through the maximum temperature of the heat source, the total pixel area of ​​the thermal imaging image of the heat source, and the pixel area of ​​the area with a temperature greater than 100°C in the thermal imaging image of the heat source to accurately evaluate the risk situation of the heat source.

[0060] Specifically, when the heat source risk assessment value R is calculated, it is determined whether to issue an early warning for the heat source according to the comparison result between the heat source risk assessment value R and the preset heat source risk assessment value, wherein the preset heat source risk assessment value includes a first preset heat source risk assessment value R1 and a second preset heat source risk assessment value R2, R1<R2;

[0061] When R<R1, it is determined that no early warning is issued for the heat source;

[0062] When R1≤R≤R2, it is determined to record the video at the preset height above the heat source;

[0063] When R>R2, it is determined to issue an early warning to the heat source;

[0064] In an embodiment of the present invention, the first preset heat source risk assessment value R1 is 0.28, which is obtained when the maximum temperature W of the heat source is 100 degrees Celsius and the ratio of the regional pixel area to the total pixel area is 0.3. The second preset heat source risk assessment value R2 is 0.5, which is obtained when the maximum temperature W of the heat source is 200 degrees Celsius and the ratio of the regional pixel area to the total pixel area is 0.5. Those skilled in the art can adjust the first preset heat source risk assessment value R1 and the second preset heat source risk assessment value R2 according to specific circumstances.

[0065] Specifically, the present invention remotely determines whether to issue an early warning for a heat source through a comparison result between the heat source risk assessment value and a preset heat source risk assessment value. Accurately issuing an early warning based on the risk situation of the heat source helps to optimize the flight path of the UAV and avoid flying over the area, thereby ensuring the safety of the flight. When the heat source risk assessment value is between a first preset heat source risk assessment value and a second preset heat source risk assessment value, it is determined to record a video at a preset height above the heat source to further accurately remotely judge through the video whether the air above the heat source is suitable for flying.

[0066] Specifically, when it is determined to record a video at a preset height above the heat source, a first relative difference △R1 between the heat source risk assessment value R and the first preset heat source risk assessment value R1 is calculated, and the preset height is determined according to the comparison result of the first relative difference △R1 and the first preset relative difference △R01, and △R1=(R-R1) / R1 is set;

[0067] When △R1≤△R01, the preset height is determined to be the first preset height G1;

[0068] When △R1>△R01, the preset height is determined to be the second preset height G2;

[0069] Among them, the first preset height G1 = G0×ln(△R1+1), the second preset height G2 = G0×ln(△R1+1.5), and G0 represents the vertical distance between the UAV and the heat source.

[0070] In the embodiment of the present invention, the first preset relative difference △R01 is set to 0.43. The first preset relative difference △R01 is obtained when the heat source risk assessment value R is 0.4. Those skilled in the art can adjust the first preset relative difference △R01 according to specific circumstances.

[0071] Specifically, the present invention determines the preset height by comparing the first relative difference between the heat source risk assessment value and the first preset heat source risk assessment value with the first preset relative difference, and further calculates the precise and appropriate height according to the formula. If the preset height is too high or too low, the video cannot accurately record the thermal airflow conditions above the heat source, thereby affecting the detection of the thermal airflow.

[0072] Specifically, when the video recording at the preset height above the heat source is completed, it is determined whether to save the two adjacent frames of images as a group of image pairs according to the comparison result of the structural similarity SSIM between the two adjacent frames of images in the recorded video and the preset structural similarity SSIM0;

[0073] When SSIM≤SSIM0, it is determined not to save the two adjacent frames of images as a group of image pairs;

[0074] When SSIM>SSIM0, it is determined that the two adjacent frames of images are saved as a group of image pairs;

[0075] In the embodiment of the present invention, the preset structural similarity SSIM0 is set to 0.9, and those skilled in the art may adjust the preset structural similarity SSIM0 according to specific circumstances.

[0076] Specifically, the present invention determines whether to save the two adjacent frames of images as a group of image pairs by comparing the structural similarity SSIM between the two adjacent frames of images in the recorded video with the preset structural similarity SSIM0, accurately selects a high-quality background image with small picture changes as the background of the thermal airflow, and improves the accuracy of thermal airflow detection.

[0077] Specifically, when the image pair in the video is saved, a second relative difference △SSIM between the structural similarity SSIM and a preset structural similarity SSIM0 is calculated, and a sampling method for sampling the image pair is determined according to a comparison result of the second relative difference △SSIM and a second preset relative difference △SSIM0, and △SSIM=(SSIM-SSIM0) / SSIM0 is set;

[0078] When △SSIM≤△SSIM0, it is determined to sample the image pair in a first sampling manner;

[0079] When ΔSSIM>ΔSSIM0, it is determined to sample the image pair in a second sampling manner;

[0080] The first sampling mode is to collect sub-region images of 50×50 pixels at the upper left corner of the image in the image pair to form a first sub-region image pair, collect sub-region images of 50×50 pixels at the center of the image in the image pair to form a second sub-region image pair, and collect sub-region images of 50×50 pixels at the lower right corner of the image in the image pair to form a third sub-region image pair;

[0081] The second sampling method is to collect sub-area images with a size of 100×100 pixels at the upper left corner of the image in the image pair to form a first sub-area image pair, collect sub-area images with a size of 100×100 pixels at the center of the image in the image pair to form a second sub-area image pair, and collect sub-area images with a size of 100×100 pixels at the lower right corner of the image in the image pair to form a third sub-area image pair.

[0082] In the embodiment of the present invention, the second preset relative difference △SSIM0 is set to 0.06. The second preset relative difference △SSIM0 is obtained when the structural similarity SSIM is 0.95. Those skilled in the art may adjust the second preset relative difference △SSIM0 according to specific circumstances.

[0083] Specifically, the present invention determines the sampling method for sampling the image pair according to the second relative difference between the structural similarity and the preset structural similarity, so as to select a sub-area image pair of appropriate size, thereby avoiding the waste of computing resources and computing delay caused by oversampling while ensuring the thermal airflow detection effect.

[0084] Specifically, when the sampling of the image pair is completed, the thermal airflow evaluation value P is calculated according to the following formula, and is set:

[0085]

[0086] Among them, Ai1 represents the normalized cross-correlation of the two sub-area images of the first sub-area image pair in the i-th image pair of the video, Ai2 represents the normalized cross-correlation of the two sub-area images of the second sub-area image pair in the i-th image pair of the video, Ai3 represents the normalized cross-correlation of the two sub-area images of the third sub-area image pair in the i-th image pair of the video, and n represents the number of image pairs in the video.

[0087] Specifically, the thermal flow evaluation value of the present invention indirectly evaluates the intensity of the thermal flow based on the normalized cross-correlation of three sub-area image pairs of several image pairs in the video. Since the thermal flow cannot be directly detected by a remote instrument, the refraction of light by the thermal flow can cause image deformation, and the intensity of the thermal flow can be evaluated at a longer distance.

[0088] Specifically, when the thermal flow evaluation value P is calculated, it is determined whether to issue a warning for the thermal flow according to a comparison result between the thermal flow evaluation value P and a preset thermal flow evaluation value, wherein the preset thermal flow evaluation value includes a first preset thermal flow evaluation value P1 and a second preset thermal flow evaluation value P2, where P1<P2;

[0089] When P<P1, it is determined that no warning will be issued for the thermal airflow;

[0090] When P1≤P≤P2, determining whether to modify the second preset heat source risk assessment value R2 is based on a third relative difference ΔP between the thermal flow assessment value P and the first preset thermal flow assessment value P1;

[0091] When P>P2, it is determined to issue a warning for the thermal airflow;

[0092] In the embodiment of the present invention, the first preset thermal airflow evaluation value P1 is 0.04, and the second preset thermal airflow evaluation value P2 is 0.1. Those skilled in the art can adjust the first preset thermal airflow evaluation value P1 and the second preset thermal airflow evaluation value P2 according to specific circumstances.

[0093] Specifically, the present invention accurately warns of thermal airflow in advance based on the comparison result between the thermal airflow evaluation value and the preset thermal airflow evaluation value, thereby avoiding the occurrence of drone crashes. At the same time, when the thermal airflow evaluation value is in the middle range, the third relative difference between the thermal airflow evaluation value and the first preset thermal airflow evaluation value is determined to determine whether to correct the second preset heat source risk evaluation value, thereby further improving the sensitivity of heat source warning.

[0094] Specifically, when determining whether to correct the second preset heat source risk assessment value R2 according to the third relative difference △P between the thermal flow assessment value P and the first preset thermal flow assessment value P1, determining whether to correct the second preset heat source risk assessment value R2 according to the comparison result of the third relative difference △P and the third preset relative difference △P0, setting △P=(P-P1) / P1;

[0095] When △P≤△P0, it is determined that the second preset heat source risk assessment value R2 is not to be corrected;

[0096] When △P>△P0, it is determined to correct the second preset heat source risk assessment value R2;

[0097] In the embodiment of the present invention, the third preset relative difference △P0 is set to 1. The third preset relative difference △P0 is obtained when the first preset thermal airflow evaluation value P1 is 0.08. Those skilled in the art can adjust the third preset relative difference △P0 according to specific circumstances.

[0098] Specifically, the present invention determines whether to correct the second preset heat source risk assessment value by comparing the third relative difference with the third preset relative difference, and accurately judges whether the sensitivity to the heat source warning needs to be corrected.

[0099] Specifically, when it is determined to correct the second preset heat source risk assessment value R2, the second preset heat source risk assessment value R2 is corrected according to the following correction coefficient X, which is set:

[0100]

[0101] The corrected second preset heat source risk assessment value is set to Rr2=R2×X.

[0102] Specifically, the present invention calculates the correction coefficient according to the formula so that the correction of the second preset heat source risk assessment value is more accurate and controllable.

[0103] The device for applying the remote security assessment method in the embodiment of the present invention includes:

[0104] A drone 1, a gimbal 2 disposed below the drone, and an image acquisition module 3 disposed on the gimbal;

[0105] The image acquisition module is provided with a thermal imager 4 for collecting thermal images and an industrial camera 5 for recording videos.

[0106] A system for applying a remote security assessment method according to an embodiment of the present invention includes:

[0107] A data acquisition unit, connected to the image acquisition module, for acquiring the thermal image of the heat source collected by the thermal imager and the video recorded by the industrial camera;

[0108] A first warning unit, which is connected to the data acquisition unit, is used to determine a heat source risk assessment value R according to the data acquired by the data acquisition unit, and to determine a warning for the heat source according to the heat source risk assessment value R, or to determine to perform video recording at a preset height above the heat source;

[0109] a sampling unit, which is connected to the data acquisition unit and the first warning unit respectively, and is used to determine whether to save the two adjacent frames of images as a group of image pairs according to the structural similarity SSIM between the two adjacent frames of images in the recorded video, and determine a sampling method for sampling the image pairs according to a second relative difference ΔSSIM between the structural similarity SSIM and a preset structural similarity SSIM0;

[0110] The second warning unit is respectively connected to the first warning unit and the sampling unit, and is used to determine a thermal airflow evaluation value P, and determine a warning for the thermal airflow according to the thermal airflow evaluation value P, or determine a correction to the second preset heat source risk evaluation value R2 according to a third relative difference ΔP between the thermal airflow evaluation value P and the first preset thermal airflow evaluation value P1.

[0111] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote security assessment method, characterized in that: include: Determine a heat source risk assessment value, and determine an early warning of the heat source according to the heat source risk assessment value, or determine to record a video at a preset height above the heat source; Determining the preset height according to a first relative difference between the heat source risk assessment value and a first preset heat source risk assessment value; Determining whether to save two adjacent frames of images as a group of image pairs according to the structural similarity between the two adjacent frames of images in the recorded video; Determining a sampling method for sampling the image pair according to a second relative difference between the structural similarity and a preset structural similarity; Determine a thermal flow evaluation value, and determine a warning for the thermal flow according to the thermal flow evaluation value, or determine a correction to a second preset heat source risk evaluation value according to a third relative difference between the thermal flow evaluation value and the first preset thermal flow evaluation value; Calculate the heat source risk assessment value according to the following formula, setting: Where R represents the heat source risk assessment value, W represents the maximum temperature of the heat source, M0 represents the total pixel area of ​​the thermal imaging image of the heat source, and M represents the pixel area of ​​the area where the temperature is greater than 100°C in the thermal imaging image of the heat source; The thermal flow evaluation value is calculated according to the following formula, setting: Among them, P represents the thermal airflow evaluation value, Ai1 represents the normalized cross-correlation of the two sub-area images of the first sub-area image pair in the i-th image pair of the video, Ai2 represents the normalized cross-correlation of the two sub-area images of the second sub-area image pair in the i-th image pair of the video, Ai3 represents the normalized cross-correlation of the two sub-area images of the third sub-area image pair in the i-th image pair of the video, and n represents the number of image pairs in the video.

2. The remote security assessment method according to claim 1, characterized in that: Based on the comparison result that the heat source risk assessment value is greater than the second preset heat source risk assessment value, it is determined to issue an early warning for the heat source; based on the comparison result that the heat source risk assessment value is less than or equal to the second preset heat source risk assessment value and greater than or equal to the first preset heat source risk assessment value, it is determined to record a video at a preset height above the heat source.

3. The remote security assessment method according to claim 2, characterized in that: According to the comparison result that the first relative difference is less than or equal to the first preset relative difference, the preset height is determined to be the first preset height , according to the comparison result that the first relative difference is greater than the first preset relative difference, the preset height is determined to be the second preset height , where G0 represents the vertical distance between the UAV and the heat source, and △R1 ​​represents the first relative difference.

4. The remote security assessment method according to claim 3, characterized in that: According to the comparison result that the structural similarity SSIM between two adjacent frames of images in the recorded video is greater than the preset structural similarity SSIM0, it is determined that the two adjacent frames of images are saved as a group of image pairs.

5. The remote security assessment method according to claim 4, characterized in that: According to the comparison result that the second relative difference is less than or equal to the second preset relative difference, it is determined that the image pair is sampled in a first sampling manner, wherein the first sampling manner is to collect sub-area images with a size of 50×50 pixels in the upper left corner of the image in the image pair to form a first sub-area image pair, to collect sub-area images with a size of 50×50 pixels in the center of the image in the image pair to form a second sub-area image pair, and to collect sub-area images with a size of 50×50 pixels in the lower right corner of the image in the image pair to form a third sub-area image pair.

6. The remote security assessment method according to claim 4, characterized in that: According to the comparison result that the second relative difference is greater than the second preset relative difference, it is determined that the image pair is sampled in a second sampling manner, and the second sampling manner is to collect sub-area images with a size of 100×100 pixels in the upper left corner of the image in the image pair to form a first sub-area image pair, collect sub-area images with a size of 100×100 pixels in the center of the image in the image pair to form a second sub-area image pair, and collect sub-area images with a size of 100×100 pixels in the lower right corner of the image in the image pair to form a third sub-area image pair.

7. The remote security assessment method according to claim 1, characterized in that: According to the comparison result that the thermal flow evaluation value is greater than the second preset thermal flow evaluation value, it is determined to give an early warning for the thermal flow; according to the comparison result that the thermal flow evaluation value is less than or equal to the second preset thermal flow evaluation value and greater than or equal to the first preset thermal flow evaluation value, it is determined whether to correct the second preset heat source risk evaluation value according to the third relative difference between the thermal flow evaluation value and the first preset thermal flow evaluation value; The correction coefficient is determined according to the comparison result that the third relative difference is greater than the third preset relative difference. The second preset heat source risk assessment value is corrected, wherein ΔP represents the third relative difference.

8. A device applied to the remote security assessment method according to any one of claims 1 to 7, characterized in that: include: A drone, a gimbal disposed below the drone, and an image acquisition module disposed on the gimbal; The image acquisition module is provided with a thermal imager for collecting thermal images and an industrial camera for recording videos.

9. A system applied to the remote security assessment method according to any one of claims 1 to 7, characterized in that: include: A data acquisition unit, which is connected to the image acquisition module and is used to obtain the thermal image of the heat source collected by the thermal imager and the video recorded by the industrial camera; a first warning unit, which is connected to the data acquisition unit, and is used to determine a heat source risk assessment value according to the data acquired by the data acquisition unit, and to determine a warning for the heat source according to the heat source risk assessment value, or to determine to perform video recording at a preset height above the heat source; a sampling unit, which is connected to the data acquisition unit and the first warning unit respectively, and is used to determine whether to save the two adjacent frames of images as a group of image pairs according to the structural similarity between the two adjacent frames of images in the recorded video, and determine a sampling method for sampling the image pairs according to a second relative difference between the structural similarity and a preset structural similarity; A second warning unit is respectively connected to the first warning unit and the sampling unit, and is used to determine a thermal airflow evaluation value, and determine a warning for the thermal airflow according to the thermal airflow evaluation value, or determine a correction to a second preset heat source risk evaluation value according to a third relative difference between the thermal airflow evaluation value and the first preset thermal airflow evaluation value.

Images