House safety monitoring system based on deep learning

Abstract

The invention relates to the technical field of image monitoring, in particular to a house safety monitoring system based on deep learning, and the system is provided with a safety verification unit, and can obtain a safety evaluation value based on the obtained image definition and a voltage average value in a preset period. Whether the operation of the house monitoring system meets the standard or not can be quickly judged through the safety evaluation value, the operation efficiency of the house safety monitoring system is improved, whether the operation of the house monitoring system meets the standard or not is secondarily determined through the situation that the definition of the obtained image does not meet the standard, and the precision of the monitoring system is improved. Through the safety evaluation value, the reason for inconformity of the operation of the house safety monitoring system can be quickly determined, the misjudgment condition is avoided, the time for searching for the reason is saved, and the system operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image monitoring, and particularly to a house safety monitoring system based on deep learning. Background Art

[0002] A house safety monitoring system transmits video signals within its closed loop using optical fibers, coaxial cables, or microwaves, and forms an independent and complete system from camera shooting to image display and recording. It can reflect the monitored object in real time, vividly, and truly. It not only greatly extends the observation distance of the human eye, but also expands the function of the human eye. It can replace manual long-term monitoring in harsh environments, enabling people to see all actual situations occurring at the monitored site and recording them through a video recorder. At the same time, the alarm system device alarms for illegal intrusion, and the generated alarm signal is input into the alarm host, which triggers the monitoring system to record and save. With the improvement of safety protection awareness, it has become increasingly important to improve the accuracy and efficiency of the monitoring system.

[0003] Chinese Patent Publication No. CN: 215416979U discloses a multifunctional house safety monitoring and warning device, providing a multifunctional house safety monitoring and warning device, including a ceiling, a vibration sensor, a smoke sensor, a temperature and humidity sensor, an adjustable installation position moving frame structure, an adjustable dust-proof protection plate structure, a self-falling buffer protection rod structure, an intelligent control cabinet, a camera, a host, a wireless communication module, and an alarm. The setting of the movable guard plate and the dust-proof diversion piece is beneficial to play a protective role and ensure the monitoring effect. However, the present invention does not address the issue of improving the accuracy and efficiency of the self-check system operation of the monitoring system. Summary of the Invention

[0004] Therefore, the present invention provides a house safety monitoring system based on deep learning to overcome the problem of the efficiency of the existing house safety monitoring system.

[0005] To achieve the above object, the present invention provides a house safety monitoring system based on deep learning, including:

[0006] An image acquisition unit, which includes a camera for acquiring the image contour and image clarity inside the house and a moving bracket for angle adjustment;

[0007] A cleaning control unit, which is used to acquire the area of the light-blocking part of the camera lens;

[0008] A protection device unit, which is used to acquire voltage data;

[0009] An analysis and detection unit, which is respectively connected to the image acquisition unit, the cleaning control unit and the protection device unit, and is used for real-time monitoring of the operation of the house monitoring system based on the acquired image contour, image clarity, bracket angle and voltage data;

[0010] A safety verification unit, which is connected to the analysis and detection unit, and is used for determining that the operation of the house monitoring system does not meet the standard based on the safety evaluation value calculated from the acquired image clarity and the average voltage within a preset period. When it is determined that the operation of the house monitoring system does not meet the standard based on the acquired image clarity for the second time, re-determine the safety evaluation value benchmark, and determine the reason why the operation of the house monitoring system does not meet the standard based on the safety evaluation value.

[0011] Further, the safety evaluation value formula is:

[0012]

[0013] Where ω represents the safety evaluation value, A represents the image clarity value detected by the analysis and detection unit within a preset period, A0 represents the image clarity benchmark preset by the safety verification unit; V represents the average voltage detected by the analysis and detection unit during the preset period, and V0 represents the voltage value benchmark preset by the safety verification unit.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can obtain the safety evaluation value based on the acquired image clarity and the average voltage within a preset period by providing a safety verification unit. Through the safety evaluation value, it can quickly determine whether the operation of the house monitoring system meets the standard, improving the operation efficiency of the house safety monitoring system. By re-determining whether the operation of the house monitoring system meets the standard based on the acquired image clarity that does not meet the standard, the accuracy of the monitoring system is improved. Through the safety evaluation value, the reason why the operation of the house safety monitoring system does not meet the standard can be quickly determined, avoiding the occurrence of misjudgment, saving the time for finding the reason, and improving the operation efficiency of the system.

[0015] Further, the present invention can quickly determine the safety evaluation value through the acquired image clarity and the average voltage within a preset period, improving the operation accuracy of the system.

[0016] Further, the present invention can quickly preliminarily determine whether the operation of the house monitoring system meets the standard through the acquired safety evaluation value, and can quickly re-determine whether it meets the standard through the image clarity, improving the accuracy of the system. Through the safety evaluation value, the reason why the house monitoring system does not meet the standard can be quickly determined, saving the time for finding the reason, and improving the operation efficiency of the system.

[0017] Furthermore, through the obtained image clarity, the present invention can quickly re-determine that the reason for the non-compliance of the house security monitoring system is the problem of the safety evaluation value benchmark, improving the efficiency of the system. Through the obtained average voltage, the safety evaluation value benchmark can be quickly re-determined, improving the accuracy of the system.

[0018] Furthermore, the present invention can improve the accuracy of the system by correcting the safety evaluation value benchmark.

[0019] Furthermore, when the reason is the problem of the camera focal length in the present invention, the camera focal length is re-determined based on the image clarity; when the reason is the problem of the moving bracket angle, the moving bracket angle is re-determined based on the integrity of the image contour; when the reason is the problem of dust on the camera mirror surface, it is re-determined whether to clean the camera mirror surface based on the area of the light-impermeable part of the camera mirror surface. The efficiency of the system operation is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the structural block diagram of the house security monitoring system described in the present invention;

[0021] Figure 2 is the flowchart for determining whether the house security monitoring system described in the present invention meets the standards;

[0022] Figure 3 is the flowchart for re-determining whether the house security monitoring system described in the present invention meets the standards;

[0023] Figure 4 is the flowchart for correcting the safety evaluation value benchmark described in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to make the objectives and advantages of the present invention clearer, the present invention will be 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.

[0025] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0026] 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 an indirect connection through an intermediate medium, and it can be the communication inside 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.

[0027] Please refer to Figure 1 as shown, which is the structural block diagram of the house safety monitoring system of the present invention. The house safety monitoring system of the present invention includes:

[0028] An image acquisition unit, which includes a camera for acquiring the image contour and image clarity inside the house and a bracket for angle adjustment;

[0029] A cleaning control unit, which is used to acquire the area of the opaque part of the camera mirror surface;

[0030] A protection device unit, which is used to acquire voltage data;

[0031] An analysis and detection unit, which is respectively connected to the image acquisition unit, the cleaning control unit and the protection device unit, and is used to perform real-time monitoring on the operation of the house monitoring system based on the acquired image contour, image clarity, bracket angle and voltage data;

[0032] A safety verification unit, which is connected to the analysis and detection unit, and is used to re-determine the safety evaluation value benchmark when it is determined that the house monitoring system does not meet the standard based on the evaluation value calculated from the acquired image clarity and voltage data, and when it is determined that the operation of the house monitoring system does not meet the standard based on the image clarity for the second time, and to determine the reason why the operation of the house monitoring system does not meet the standard based on the safety evaluation value.

[0033] Specifically, the safety evaluation value formula is:

[0034]

[0035] where ω represents the safety evaluation value, A represents the image clarity value detected by the analysis and detection unit within a preset period, A0 represents the image clarity benchmark preset by the safety verification unit; V represents the average voltage detected by the analysis and detection unit in the preset period, and V0 represents the voltage value benchmark preset by the safety verification unit.

[0036] Please refer to Figure 2 as shown, which is the decision flow chart for determining whether the house safety monitoring system of the present invention meets the standard. The safety verification unit of the present invention determines whether the house monitoring system meets the standard based on the acquired safety evaluation value, where:

[0037] If the safety evaluation value is less than or equal to a preset first benchmark, the safety verification unit determines that the operation of the house monitoring system meets the standard and continues to monitor;

[0038] If the safety evaluation value is greater than the preset first benchmark and less than or equal to the preset second benchmark, the safety verification unit preliminarily determines that the operation of the house monitoring system does not meet the standard, and re-determines whether the operation of the house monitoring system meets the standard based on the image clarity;

[0039] If the safety evaluation value is greater than the preset second benchmark, the safety verification unit determines that the house monitoring system does not meet the standard, and determines the reason why the operation of the house monitoring system does not meet the standard based on the safety evaluation value.

[0040] Please refer to Figure 3 as shown, which is the flowchart for re-determining whether the house safety monitoring system of the present invention meets the standard; the safety verification unit of the present invention re-determines whether the operation of the house safety monitoring system meets the standard based on the obtained image clarity, where:

[0041] If the image clarity is less than or equal to the preset benchmark, the safety verification unit determines that the house safety monitoring system does not meet the standard, and re-determines the correction method of the safety evaluation value benchmark based on the average voltage;

[0042] If the image clarity is greater than the preset benchmark, the safety verification unit determines that the house safety monitoring system meets the standard and continues the detection.

[0043] Please refer to Figure 4 as shown, which is the correction flowchart of the safety evaluation value benchmark of the present invention. The safety verification unit of the present invention has several correction methods for the safety evaluation value benchmark based on the difference between the obtained average voltage and the preset benchmark, where:

[0044] If the difference is less than or equal to the preset first difference benchmark, the safety verification unit uses the first correction coefficient α1 to correct the safety evaluation value button to the corresponding value;

[0045] If the difference is greater than the preset first difference benchmark and less than or equal to the preset second difference benchmark, the safety verification unit uses the second correction coefficient α2 to correct the safety evaluation value button to the corresponding value;

[0046] If the difference is greater than the preset second difference benchmark, the safety verification unit uses the third correction coefficient α3 to correct the safety evaluation value button to the corresponding value;

[0047] Among them, the correction formula adopted by the present invention is K = k×α n , where k is the preset safety evaluation value benchmark before correction, K is the safety evaluation value benchmark after correction, n is a positive integer, and α n is the preset correction coefficient. The present invention sets α1 = 0.99; α2 = 0.98; α3 = 0.97.

[0048] Specifically, the safety verification unit of the present invention determines the reason why the house monitoring system does not meet the standard based on the difference between the obtained safety evaluation value and the preset evaluation value benchmark, where:

[0049] If the difference is less than or equal to the preset first benchmark, the safety verification unit determines that the reason why the house monitoring system does not meet the standard is the camera focal length problem, and re-determines the adjustment method for the camera focal length based on the image clarity;

[0050] If the difference is greater than the preset first benchmark and less than or equal to the preset second benchmark, the safety verification unit determines that the reason why the house monitoring system does not meet the standard is the problem of the mobile rack, and re-determines the adjustment method for the moving angle of the mobile bracket based on the image contour integrity;

[0051] If the difference is greater than the preset second benchmark, the safety verification unit determines that the reason why the house monitoring system does not meet the standard is the problem of dust on the camera mirror surface, and re-determines whether to clean the camera mirror surface based on the area of the light-blocking part of the camera mirror surface.

[0052] Specifically, the safety verification unit of the present invention has several adjustment methods for the camera focal length based on the obtained image clarity, where:

[0053] If the image clarity is less than or equal to the preset first benchmark, the safety verification unit uses the first adjustment coefficient β1 to adjust the camera focal length button to the corresponding value;

[0054] If the image clarity is greater than the preset first benchmark and less than or equal to the preset second benchmark, the safety verification unit uses the second adjustment coefficient β2 to adjust the camera focal length button to the corresponding value;

[0055] If the image clarity is greater than the preset second benchmark, the safety verification unit uses the third adjustment coefficient β3 to adjust the camera focal length button to the corresponding value.

[0056] Among them, the adjustment formula adopted by the present invention is, G = g×β n , where, g is the preset camera focal length benchmark before adjustment, G is the adjusted camera focal length, n is a positive integer, β n is the preset adjustment coefficient, and the present invention sets, β1 = 0.98; β2 = 0.96; β3 = 0.94.

[0057] Specifically, the safety verification unit of the present invention has several adjustment methods for the angle of the mobile bracket based on the difference between the obtained image integrity and the preset integrity benchmark, where:

[0058] If the difference is less than or equal to the preset first benchmark, the safety verification unit uses the first adjustment coefficient γ1 to adjust the angle of the mobile bracket to the corresponding value;

[0059] If the difference is greater than a preset first reference and less than or equal to a preset second reference, the safety verification unit uses a second adjustment coefficient γ2 to adjust the angle of the mobile support to a corresponding value;

[0060] If the difference is greater than the preset second reference, the safety verification unit uses a third adjustment coefficient γ3 to adjust the angle of the mobile support to a corresponding value.

[0061] Among them, the adjustment formula adopted by the present invention is R = r×β n , where r is the preset angle reference of the mobile support before adjustment, R is the angle of the mobile support after adjustment, n is a positive integer, and γ n is the preset adjustment coefficient. The present invention sets γ1 = 1.08; γ2 = 0.99; γ3 = 0.89.

[0062] Specifically, the safety verification unit of the present invention determines the cleaning method for cleaning the camera mirror surface based on the ratio of the area of the light-blocking part of the camera mirror surface obtained to the preset reference, where:

[0063] If the ratio is less than or equal to the preset reference, the safety verification unit starts the self-cleaning mode for cleaning;

[0064] If the ratio is greater than the preset reference, the safety verification unit issues an alarm for manual cleaning.

[0065] Specifically, the safety verification unit of the present invention determines whether to start the voltage protection to quickly remove the system fault based on the difference between the obtained average voltage value and the preset reference, where,

[0066] If the difference is less than or equal to the preset reference, the safety verification unit determines not to start the voltage protection;

[0067] If the difference is greater than the preset reference, the safety verification unit determines to start the voltage protection, quickly remove the system fault, and enable the secondary standby voltage protection device.

[0068] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the 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 all fall within the protection scope of the present invention.

[0069] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention; for those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A house safety monitoring system based on deep learning, characterized in that Including: An image acquisition unit, which includes a camera for acquiring the image contour and image clarity inside the house and a moving bracket for angle adjustment; A cleaning control unit, which is used to acquire the area of the light-blocking part of the camera mirror; A protection device unit, which is used to acquire voltage data; An analysis and detection unit, which is respectively connected to the image acquisition unit, the cleaning control unit and the protection device unit, and is used to perform real-time monitoring on the operation of the house monitoring system based on the acquired image contour, image clarity, bracket angle and voltage data; A safety verification unit, which is connected to the analysis and detection unit, and is used to re-determine the safety evaluation value benchmark when it is determined that the operation of the house monitoring system does not meet the standard based on the safety evaluation value calculated based on the acquired image clarity and the average voltage within a preset period, and when it is determined that the operation of the house monitoring system does not meet the standard based on the acquired image clarity for the second time, and to determine the reason why the operation of the house monitoring system does not meet the standard based on the safety evaluation value.

2. The house security monitoring system based on deep learning according to claim 1 is characterized in that: The formula for the safety evaluation value is: Where, ω represents the safety evaluation value, A represents the image clarity value detected by the analysis and detection unit within a preset period, A0 represents the image clarity benchmark preset by the safety verification unit; V represents the average voltage detected by the analysis and detection unit during the preset period, and V0 represents the voltage value benchmark preset by the safety verification unit.

3. The house safety monitoring system based on deep learning according to claim 2, wherein, The safety verification unit determines whether the house monitoring system meets the standard based on the acquired safety evaluation value, where: If the safety evaluation value is less than or equal to the preset first benchmark, the safety verification unit determines that the operation of the house monitoring system meets the standard and continues to monitor; If the safety evaluation value is greater than the preset first benchmark and less than or equal to the preset second benchmark, the safety verification unit preliminarily determines that the operation of the house monitoring system does not meet the standard, and determines whether the operation of the house monitoring system meets the standard based on the image clarity for the second time; If the safety evaluation value is greater than the preset second benchmark, the safety verification unit determines that the house monitoring system does not meet the standard and determines the reason why the operation of the house monitoring system does not meet the standard based on the safety evaluation value.

4. The house safety monitoring system based on deep learning according to claim 3, characterized in that, The safety verification unit determines whether the operation of the house security monitoring system meets the standard based on the acquired image clarity for the second time, where: If the image clarity is less than or equal to the preset benchmark, the safety verification unit determines that the reason why the house security monitoring system does not meet the standard is the safety evaluation value benchmark problem, and re-determines the safety evaluation value benchmark based on the acquired average voltage value; If the image clarity is greater than the preset benchmark, the safety verification unit determines that the house security monitoring system meets the standard and continues to detect.

5. The house security monitoring system based on deep learning according to claim 4 is characterized in that: The safety verification unit has several correction methods for the safety evaluation value benchmark based on the difference between the acquired average voltage value and the preset benchmark, and the correction amplitude of each correction method for the safety evaluation value benchmark is different.

6. The house security monitoring system based on deep learning according to claim 5, characterized in that: The safety verification unit determines the reason why the house monitoring system does not meet the standard based on the difference between the acquired safety evaluation value and the preset evaluation value benchmark, where: If the difference is less than or equal to the preset first benchmark, the safety verification unit determines that the reason why the house monitoring system does not meet the standard is the camera focal length problem, and re-determines the camera focal length based on the image clarity; If the difference is greater than a preset first benchmark and less than or equal to a preset second benchmark, the safety verification unit determines that the reason for the housing monitoring system not meeting the standard is the problem of the angle of the mobile bracket, and re-determines the angle of the mobile bracket based on the integrity of the image contour; If the difference is greater than the preset second benchmark, the safety verification unit determines that the reason for the housing monitoring system not meeting the standard is the problem of dust on the camera mirror surface, and re-determines whether to clean the camera mirror surface based on the area of the light-blocking part of the camera mirror surface.

7. The house safety monitoring system based on deep learning according to claim 6, characterized in that, Based on the obtained image clarity, the safety verification unit has several adjustment methods for the camera focal length, and the adjustment range of each adjustment method for the camera focal length is different.

8. The house safety monitoring system based on deep learning according to claim 7, characterized in that, Based on the difference between the obtained image integrity and the preset integrity benchmark, the safety verification unit has several adjustment methods for the angle of the mobile bracket, and the adjustment range of each adjustment method for the angle of the mobile bracket is different.

9. The house safety monitoring system based on deep learning according to claim 8, characterized in that The safety verification unit determines the cleaning method for cleaning the camera mirror surface based on the ratio of the area of the light-blocking part of the obtained camera mirror surface to the preset benchmark.

10. The house safety monitoring system based on deep learning according to claim 9, wherein, The safety verification unit determines whether to start the voltage protection to quickly remove the system fault based on the difference between the obtained average voltage and the preset benchmark.

Images