Regional big data monitoring and alarm system

By using the Hofitter neural network to intelligently identify the contact between life jackets and humans in the big data monitoring and alarm system in the water surface operation area, the problem of identifying staff without wearing life jackets is solved, safety monitoring and voice alarms are realized, and on-site safety is improved.

CN118470906BActive Publication Date: 2024-11-08HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410617728.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-17
Publication Date
2024-11-08
Estimated Expiration
2044-05-17

AI Technical Summary

Technical Problem

During surface operations, there is a great risk that the staff did not wear life jackets, and it is difficult to accurately identify and call the police in the existing technology.

Method used

Design an area big data monitoring and alarm system, using customized camera mechanisms, sharpening processing equipment, cassette filtering equipment, signal processing equipment and continuous processing mechanisms, combined with Hofitter neural network, intelligently identify whether the life jacket and the human body are in contact, and Perform voice alarm when not in contact, and suspend alarm when contact.

Benefits of technology

It realizes safety monitoring of whether the human body is wearing a life jacket in the water surface operation area, improves the reliability and stability of the identification results, and ensures on-site safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118470906B_ABST
    Figure CN118470906B_ABST
Patent Text Reader

Abstract

The present invention relates to a regional big data monitoring and alarm system, the system comprising: a continuous processing mechanism, for introducing a Hoffitt neural network that has completed multiple trainings to intelligently identify whether a life jacket is in contact with a human body based on various visual data of a content-filtered image; a voice alarm mechanism, connected to the continuous processing mechanism, for deciding whether to execute a corresponding on-site voice alarm based on the identification result of the continuous processing mechanism. The regional big data monitoring and alarm system of the present invention operates intelligently, safely and reliably. Since it is possible to execute an on-site voice alarm action that a human body is not wearing a life jacket when it is intelligently identified that the life jacket and the human body are not in contact, and to temporarily suspend the execution of the on-site voice alarm action that a human body is not wearing a life jacket when it is intelligently identified that the life jacket and the human body are in contact, it is possible to achieve safe monitoring of whether a human body is wearing a life jacket in a water operation area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of regional monitoring, and in particular to a regional big data monitoring and alarm system. Background Art

[0002] Water surface operations, also known as water operations, have the following forms of conventional water operations, but are not limited to the following forms:

[0003] (1) installing or removing above-water and underwater facilities;

[0004] (2) Construction of docks, shipyards, slipways, dams, and various types of embankments or artificial islands;

[0005] (3) erecting bridges, cableways, and building underwater tunnels;

[0006] (4) Salvaging sunken ships and sunken objects;

[0007] (5) Laying, removing and repairing overhead and underwater cables or pipelines;

[0008] (6) Setting up fixed nets and facilities for fishing and breeding;

[0009] (vii) installing mooring buoys, floating pontoons, mooring bollards for bamboo or wooden rafts and similar facilities;

[0010] (8) Conducting oceanographic and meteorological observations, hydrological surveys, geological surveys, scientific research and other activities that affect water traffic safety;

[0011] (9) Removing garbage from the water surface;

[0012] (10) Sea sweeping, dredging, blasting, piling, pile extraction, landfilling, sand excavation, gold panning, quarrying, mud and gravel dumping;

[0013] (11) Rescue ships in distress, or urgently remove pollutants on the water surface or underwater;

[0014] (XII) Other construction operations that affect traffic safety in navigable waters or have an impact on the navigation environment.

[0015] During surface operations, workers are required to wear life jackets to provide protection for human safety. However, due to discomfort or other reasons, some workers do not wear life jackets, resulting in greater risks in surface operations. How to perform precise identification of workers who are not wearing life jackets based on the relative state of the human body and the life jacket is one of the technical problems that need to be solved at present. Summary of the invention

[0016] In order to solve the technical problems in related fields, the present invention provides a regional big data monitoring and alarm system, which can execute an on-site voice alarm action that the human body is not wearing a life jacket when it is intelligently identified that the life jacket and the human body are not in contact, and temporarily suspend the execution of the on-site voice alarm action that the human body is not wearing a life jacket when it is intelligently identified that the life jacket and the human body are in contact, thereby realizing safe monitoring of whether the human body in the water surface operation area is wearing a life jacket.

[0017] According to the present invention, a regional big data monitoring and alarm system is provided, the system comprising:

[0018] The customized camera mechanism is used to perform an imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame. The imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame includes: performing the imaging action at a set frame rate, and the value of the set frame rate is positively correlated with the resolution of the regional camera frame;

[0019] A sharpening processing device is arranged in an instrument box body corresponding to the shore of the water surface operation area and connected to the customized camera mechanism, and is used to perform a sharpening process based on a USM filter on the received regional camera frame to obtain and output a corresponding instant sharpened image;

[0020] A box filter device, connected to the sharpening processing device, for performing a box filter process on the received instant sharpened image to obtain and output a corresponding box filter image;

[0021] a signal processing device connected to the box filter device, for performing Butterworth low-pass filtering on the received box filter image to obtain and output a corresponding content filter image;

[0022] A continuous processing mechanism is arranged in an instrument box body corresponding to the shore of the water surface operation area and connected to the signal processing device, comprising a pixel detection unit, a quantity analysis unit and an identification conversion unit, which are connected in sequence, and the continuous processing mechanism is used to detect each constituent pixel of the life jacket in the content filtering image and each constituent pixel of the human body in the content filtering image based on the imaging characteristics of the life jacket and the human body, respectively, and introduce a Hoffet neural network that has completed multiple trainings to intelligently identify whether the life jacket and the human body are in contact based on the number of noise types in the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each constituent pixel of the life jacket in the content filtering image, and the color component values ​​of each constituent pixel of the human body in the content filtering image, and the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image;

[0023] A voice alarm mechanism is connected to the continuous processing mechanism and is used to execute an on-site voice alarm action indicating that the person is not wearing a life jacket when the life jacket and the person are not in contact with each other through intelligent identification;

[0024] Among them, a Hoffet neural network that has completed multiple trainings is introduced to intelligently identify whether a life jacket is in contact with a human body based on the number of noise types in a content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each pixel constituting the life jacket in the content filtering image, and the color component values ​​of each pixel constituting the human body in the content filtering image. The number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image, including: using a numerical simulation mode to complete multiple trainings of the Hoffet neural network to obtain a Hoffet neural network that has completed multiple trainings.

[0025] It can be seen that the present invention mainly has the following significant technical effects:

[0026] First, a continuous processing mechanism including a pixel detection unit, a quantity analysis unit and an identification conversion unit is introduced to complete the intelligent identification of whether the life jacket is in contact with the human body, wherein the pixel detection unit, the quantity analysis unit and the identification conversion unit are connected in sequence;

[0027] Second, a Hoffet neural network that has completed multiple trainings is introduced to intelligently identify whether a life jacket is in contact with a human body based on the number of noise types in the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each pixel constituting the life jacket in the content filtering image, and the color component values ​​of each pixel constituting the human body in the content filtering image. The number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image, thereby ensuring the reliability and stability of the identification results of the Hoffet neural network that has completed multiple trainings.

[0028] The third point: when the intelligent identification life jacket and the human body are not in contact, the on-site voice alarm action of the human body not wearing a life jacket is executed; and when the intelligent identification life jacket and the human body are in contact, the on-site voice alarm action of the human body not wearing a life jacket is temporarily suspended, thereby realizing the safe monitoring of whether the human body in the water operation area is wearing a life jacket.

[0029] The regional big data monitoring and alarm system of the present invention operates intelligently, safely and reliably. Since it can execute the on-site voice alarm action of the person not wearing a life jacket when the life jacket and the person are not in contact with each other, and suspend the on-site voice alarm action of the person not wearing a life jacket when the life jacket and the person are in contact with each other, it can realize the safe monitoring of whether the person is wearing a life jacket in the water surface operation area. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0031] Figure 1 Schematic diagram of the internal structure of a regional big data monitoring and alarm system according to the first embodiment of the present invention.

[0032] Figure 2 Schematic diagram of the internal structure of a regional big data monitoring and alarm system according to the second embodiment of the present invention.

[0033] Figure 3 Schematic diagram of the internal structure of a regional big data monitoring and alarm system according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following is a detailed description of an embodiment of the regional big data monitoring and alarm system of the present invention with reference to the accompanying drawings.

[0035] Figure 1 This is a schematic diagram of the internal structure of a regional big data monitoring and alarm system according to a first embodiment of the present invention, wherein the system comprises:

[0036] The customized camera mechanism is used to perform an imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame. The imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame includes: performing the imaging action at a set frame rate, and the value of the set frame rate is positively correlated with the resolution of the regional camera frame;

[0037] For example, the custom camera mechanism has a built-in frame rate adjustment unit, which is used to receive the resolution of the regional camera frame and adjust the value of the set frame rate based on the resolution of the regional camera frame;

[0038] A sharpening processing device is arranged in an instrument box body corresponding to the shore of the water surface operation area and connected to the customized camera mechanism, and is used to perform a sharpening process based on a USM filter on the received regional camera frame to obtain and output a corresponding instant sharpened image;

[0039] A box filter device, connected to the sharpening processing device, for performing a box filter process on the received instant sharpened image to obtain and output a corresponding box filter image;

[0040] a signal processing device connected to the box filter device, for performing Butterworth low-pass filtering on the received box filter image to obtain and output a corresponding content filter image;

[0041] A continuous processing mechanism is arranged in an instrument box body corresponding to the shore of the water surface operation area and connected to the signal processing device, comprising a pixel detection unit, a quantity analysis unit and an identification conversion unit, which are connected in sequence, and the continuous processing mechanism is used to detect each constituent pixel of the life jacket in the content filtering image and each constituent pixel of the human body in the content filtering image based on the imaging characteristics of the life jacket and the human body, respectively, and introduce a Hoffet neural network that has completed multiple trainings to intelligently identify whether the life jacket and the human body are in contact based on the number of noise types in the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each constituent pixel of the life jacket in the content filtering image, and the color component values ​​of each constituent pixel of the human body in the content filtering image, and the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image;

[0042] A voice alarm mechanism is connected to the continuous processing mechanism and is used to execute an on-site voice alarm action indicating that the person is not wearing a life jacket when the life jacket and the person are not in contact with each other through intelligent identification;

[0043] Among them, introducing a Hoffet neural network that has completed multiple trainings to intelligently identify whether a life jacket and a human body are in contact based on the number of noise types of the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each pixel constituting the life jacket in the content filtering image, and the color component values ​​of each pixel constituting the human body in the content filtering image, and the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image, including: using a numerical simulation mode to complete multiple trainings of the Hoffet neural network to obtain the Hoffet neural network that has completed multiple trainings;

[0044] The voice alarm mechanism is also used to temporarily suspend the on-site voice alarm action of the human body not wearing a life jacket when intelligently identifying that the life jacket is in contact with the human body.

[0045] Figure 2 Schematic diagram of the internal structure of a regional big data monitoring and alarm system according to the second embodiment of the present invention.

[0046] Compared to Figure 1 According to the second embodiment of the present invention, the regional big data monitoring and alarm system may further include:

[0047] a vibration measuring mechanism, connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, respectively, for measuring the current vibration amplitude of each of the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism;

[0048] Wherein, the vibration measuring mechanism is connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism respectively, and is used to measure the current vibration amplitude of each of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism respectively, including: the vibration measuring mechanism includes a plurality of vibration measuring units, which are used to be connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism respectively, so as to complete the measurement of the current vibration amplitude of each of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism respectively;

[0049] Wherein, the vibration measuring mechanism comprises a plurality of vibration measuring units, which are respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism to complete the respective measurement of the current vibration amplitude of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism, including: the plurality of vibration measuring units are a plurality of vibration sensing circuits, which are respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism to complete the respective measurement of the current vibration amplitude of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism;

[0050] Wherein, the plurality of vibration measuring units are a plurality of vibration sensing circuits, which are used to be connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism respectively, so as to complete the respective measurement of the current vibration amplitude of each of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism, including: the structures of the plurality of vibration sensing circuits are the same;

[0051] Among them, the multiple vibration measuring units are multiple vibration sensing circuits, which are used to be connected to the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism respectively to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism. It also includes: the multiple vibration sensing circuits have the same vibration measurement upper limit value and vibration measurement lower limit value.

[0052] Figure 3 Schematic diagram of the internal structure of a regional big data monitoring and alarm system according to the third embodiment of the present invention.

[0053] Compared to Figure 1 According to the third embodiment of the present invention, the regional big data monitoring and alarm system may further include:

[0054] a data caching device, arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively, and used to provide data caching services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively;

[0055] Wherein, the data cache device is arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and is respectively connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, and is used to provide data cache services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively, including: the data cache device is connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism through different data cache interfaces;

[0056] And wherein, the data cache device is arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and is respectively connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, and is used to provide data cache services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively, and also includes: the data transmission bandwidth of different data cache interfaces used by the data cache device is the same.

[0057] In addition, in the regional big data monitoring and alarm system, a Hoffet neural network that has completed multiple trainings is introduced to intelligently identify whether a life jacket is in contact with a human body based on the number of noise types in the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each pixel constituting the life jacket in the content filtering image, and the color component values ​​of each pixel constituting the human body in the content filtering image. The number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image, and further includes: using a numerical mapping function to represent a numerical mapping relationship in which the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image.

[0058] Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art will appreciate that various modifications and substitutions may be made thereto without departing from the spirit and scope of the invention as set forth in the appended claims.

Claims

1. A regional big data monitoring and alarm system, characterized in that: The system comprises: The customized camera mechanism is used to perform an imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame. The imaging action of the surface operation area facing the surface operation area to obtain and output a corresponding regional camera frame includes: performing the imaging action at a set frame rate, and the value of the set frame rate is positively correlated with the resolution of the regional camera frame; A sharpening processing device is arranged in an instrument box body corresponding to the shore of the water surface operation area and connected to the customized camera mechanism, and is used to perform a sharpening process based on a USM filter on the received regional camera frame to obtain and output a corresponding instant sharpened image; A box filter device, connected to the sharpening processing device, for performing a box filter process on the received instant sharpened image to obtain and output a corresponding box filter image; a signal processing device connected to the box filter device, for performing Butterworth low-pass filtering on the received box filter image to obtain and output a corresponding content filter image; A continuous processing mechanism is arranged in an instrument box body corresponding to the shore of the water surface operation area and is connected to the signal processing device, comprising a pixel detection unit, a quantity analysis unit and an identification conversion unit, which are connected in sequence, and the continuous processing mechanism is used to detect each constituent pixel of the life jacket in the content filtering image and each constituent pixel of the human body in the content filtering image based on the imaging characteristics of the life jacket and the human body, respectively, and introduce a Hoffet neural network that has completed multiple trainings to intelligently identify whether the life jacket and the human body are in contact based on the number of noise types in the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each constituent pixel of the life jacket in the content filtering image, and the color component values ​​of each constituent pixel of the human body in the content filtering image, and the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image; A voice alarm mechanism is connected to the continuous processing mechanism and is used to execute an on-site voice alarm action indicating that the human body is not wearing a life jacket when the life jacket and the human body are not in contact with each other through intelligent identification; Among them, introducing a Hoffet neural network that has completed multiple trainings to intelligently identify whether a life jacket and a human body are in contact based on the number of noise types of the content filtering image, the maximum noise amplitude of the content filtering image, the color component values ​​of each pixel constituting the life jacket in the content filtering image, and the color component values ​​of each pixel constituting the human body in the content filtering image, and the number of training times of the Hoffet neural network is proportional to the maximum noise amplitude of the content filtering image, including: using a numerical simulation mode to complete multiple trainings of the Hoffet neural network to obtain the Hoffet neural network that has completed multiple trainings; The voice alarm mechanism is also used to temporarily suspend the on-site voice alarm action of the human body not wearing a life jacket when the life jacket is intelligently identified to be in contact with the human body; a vibration measuring mechanism, connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, respectively, for measuring the current vibration amplitude of each of the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism; Among them, the vibration measuring mechanism is respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism, and is used to respectively measure the current vibration amplitudes of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism. The vibration measuring mechanism includes a plurality of vibration measuring units, which are respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism.

2. The regional big data monitoring and alarm system according to claim 1, characterized in that: The vibration measuring mechanism includes a plurality of vibration measuring units, which are respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism. The plurality of vibration measuring units are a plurality of vibration sensing circuits, which are respectively connected to the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box-type filtering device, the signal processing device and the continuous processing mechanism.

3. The regional big data monitoring and alarm system according to claim 2, characterized in that: The multiple vibration measuring units are multiple vibration sensing circuits, which are used to be connected to the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism respectively to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism, including: the structures of the multiple vibration sensing circuits are the same.

4. The regional big data monitoring and alarm system according to claim 3, characterized in that: The multiple vibration measuring units are multiple vibration sensing circuits, which are used to be connected to the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism respectively to complete the respective measurements of the current vibration amplitudes of the sharpening processing device, the box filtering device, the signal processing device and the continuous processing mechanism. It also includes: the multiple vibration sensing circuits have the same vibration measurement upper limit value and vibration measurement lower limit value.

5. The regional big data monitoring and alarm system according to any one of claims 1 to 4, characterized in that: The system further comprises: A data cache device is arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and is respectively connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, and is used to provide data cache services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively.

6. The regional big data monitoring and alarm system according to claim 5, characterized in that: A data cache device is arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and is respectively connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, and is used to provide data cache services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively, including: the data cache device is connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism through different data cache interfaces.

7. The regional big data monitoring and alarm system according to claim 6, characterized in that: A data cache device is arranged near the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism and is respectively connected to the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism, and is used to provide data cache services for the sharpening processing device, the box filter device, the signal processing device and the continuous processing mechanism respectively. The data transmission bandwidth of different data cache interfaces used by the data cache device is the same.

Citation Information

Patent Citations

  • Life jacket with intelligent wear state identification function

    CN109131783A

  • A passenger lifejacket wearing identification system of a shared water vehicle

    CN109190569A

  • Alarm system and method for behavior recognition and remote monitoring based on multiple targets

    CN116863640A

  • Life jacket for maritime accident and rescue system using the same

    KR101979638B1