Monitoring system integrated with artificial intelligence

Abstract

The invention discloses a monitoring system integrated with artificial intelligence, and relates to the technical field of environment monitoring. The system comprises a data acquisition unit, a transmission unit, a data processing unit, an app reminding unit and an alarm unit. The system replaces manual monitoring of any regional environment, reduces the consumption of human resources, improves the working efficiency, judges whether the measured data exceeds the standard or not through the collection and comparison of the temperature data, gas data, wind speed data, noise data and dust particles in the regional environment, timely issues an alarm prompt, provides a better safety guarantee, and improves the safety of the regional environment. The temperature data, the gas data, the wind speed data, the noise data and the dust particle data of any area can be accurately monitored in real time, the environmental protection standard emission of the monitored area is ensured, and the influence on the surrounding environment is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of environmental monitoring, and in particular, relates to a monitoring system integrated with artificial intelligence. Background Art

[0002] At present, environmental pollution has become a very concerned issue in the field of environmental protection technology in the world today. Pollution not only destroys the ecological balance of nature, but also endangers human survival and health. Therefore, people are now constantly strengthening their awareness of environmental protection and have also taken some effective measures.

[0003] However, the current environmental pollution monitoring technology has certain defects, such as insufficient monitoring range, inability to conduct quantitative analysis of pollution information, lack of systematic analysis of external factors such as air visibility and wind speed, and failure to organically link computer network information systems, resulting in deficiencies in the accuracy and real-time performance of the current monitoring methods. Therefore, a monitoring system that integrates artificial intelligence is needed.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a monitoring system integrated with artificial intelligence, thereby solving the problems raised in the above-mentioned background technology.

[0006] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0007] A monitoring system integrated with artificial intelligence, comprising:

[0008] Data collection unit: used to collect the environmental data around the monitoring area in real time and send the collected environmental data of the monitoring area;

[0009] Transmission unit: used to receive the monitoring area environmental data collected by the data collection unit and transmit it;

[0010] Data processing unit: used to receive the monitoring area environmental data transmitted by the transmission unit, and compare the monitoring area environmental data with the preset regional environmental data threshold, determine whether the environmental data around the monitoring area exceeds the standard, and send an alarm instruction according to the judgment result;

[0011] App reminder unit: used to receive the alarm instruction sent by the data processing unit, and send the alarm instruction to the terminal app to remind the operation and maintenance unit;

[0012] Alarm unit: used to receive the alarm instruction sent by the data processing unit and issue an alarm.

[0013] Optionally, the data acquisition unit includes a drone acquisition module, a temperature acquisition module, a gas acquisition module, a wind speed acquisition module and a noise acquisition module. The temperature acquisition module is used to collect temperature data around the monitoring area, and the gas acquisition module is used to collect gas data around the monitoring area; the wind speed acquisition module is used to collect wind speed data around the monitoring area, and the noise acquisition module is used to collect noise data around the monitoring area.

[0014] Optionally, the UAV acquisition module includes a video acquisition submodule and an image acquisition submodule, the video acquisition submodule includes a function of acquiring video data around the monitoring area, and the image acquisition submodule is used to acquire image data around the monitoring area; the UAV acquisition module is connected to a path planning submodule and a task planning submodule, the task planning submodule is used to set periodic inspection tasks for the UAV around the monitoring area, and transmit the task instructions to the path planning module, and the path planning submodule is used to formulate the path of the UAV in the monitoring area according to the inspection task.

[0015] Optionally, the transmission unit is used to transmit the collected temperature data, gas data, wind speed data, noise data, video data and image data in the monitoring area to the data processing unit; the data processing unit compares the temperature data, gas data, wind speed data and noise data with thresholds of temperature data, gas data, wind speed data and noise data to determine whether the temperature data, gas data, wind speed data and noise data around the monitoring area exceed the standard.

[0016] Optionally, the data processing unit is connected to a dust particle identification module, which is used to process video data and image data to identify dust particles and determine whether the dust particles exceed the standard; the specific process of analyzing and processing the received data is dust image video recognition, and the specific process of dust image video recognition is: image and video enhancement processing, the computer performs image and video enhancement processing on the dust image video based on Retinex theory, the computer uses a histogram equalization algorithm to perform image and video enhancement processing on the dust image video, image and video segmentation processing, the computer uses a regional growing segmentation algorithm to perform image and video segmentation processing on the dust image video obtained by the enhanced processing, separates dust overlapping particles, identifies dust particles, the computer performs binarization processing on the dust image video to obtain a binarized image video, the computer uses a SIFT algorithm to extract feature points from the binarized image video, extracts feature points of the edge curve of the dust overlapping particle image video, the computer uses a calling overlapping particle intersection extraction module to extract overlapping particle intersections in the feature points of the edge curve of the dust overlapping particle image video, and the computer uses a fruit fly algorithm to separate dust overlapping particles and identify dust particles.

[0017] Optionally, the data processing unit is further connected to a preset module, and the preset module is used to set thresholds of temperature data, gas data, wind speed data and noise data, and an alarm level of dust particles.

[0018] Optionally, the data processing unit includes a periodic inspection module and a special inspection module, the periodic inspection module and the special inspection module are connected to the path planning sub-module, the periodic inspection module and the path planning sub-module are connected to set periodic trigger conditions, and inspection tasks of the monitoring area are issued within a certain period to formulate the path of the UAV in the monitoring area; the special inspection module and the path planning sub-module are connected to trigger special detection commands, and single-point, multi-point detection or comprehensive detection designated tasks are manually set to formulate the path of the UAV in the monitoring area.

[0019] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all the advantages described below at the same time:

[0020] The present invention can replace manual monitoring of the environment of any area, reduce the consumption of human resources, and improve work efficiency. By collecting and comparing the temperature data, gas data, wind speed data, noise data and dust particles in the regional environment, it is determined whether the measured data exceeds the standard, and an alarm prompt is issued in time to provide better safety protection. The temperature data, gas data, wind speed data, noise data and dust particle data of any area can be monitored accurately and in real time to ensure that the environmental protection emission in the monitored area meets the standard and reduce the impact on the surrounding environment.

[0021] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described below are only some embodiments. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0023] In the figure:

[0024] Figure 1 This is a flowchart of the artificial intelligence monitoring system;

[0025] Figure 2 Figure 2 is a flow chart of the data acquisition unit.

[0026] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but are intended to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0027] The present invention will now be described in further detail with reference to the accompanying drawings.

[0028] See also Figure 1-2 As shown, in this embodiment, a monitoring system integrated with artificial intelligence is provided, including:

[0029] Data collection unit: used to collect the environmental data around the monitoring area in real time and send the collected environmental data of the monitoring area;

[0030] Transmission unit: used to receive the monitoring area environmental data collected by the data collection unit and transmit it;

[0031] Data processing unit: used to receive the monitoring area environmental data transmitted by the transmission unit, and compare the monitoring area environmental data with the preset regional environmental data threshold, determine whether the environmental data around the monitoring area exceeds the standard, and send an alarm instruction according to the judgment result;

[0032] App reminder unit: used to receive the alarm instruction sent by the data processing unit, and send the alarm instruction to the terminal app to remind the operation and maintenance unit;

[0033] Alarm unit: used to receive the alarm instructions sent by the data processing unit and issue an alarm.

[0034] like Figure 1 As shown, the data acquisition unit of this embodiment includes a drone acquisition module, a temperature acquisition module, a gas acquisition module, a wind speed acquisition module and a noise acquisition module. The temperature acquisition module is used to collect temperature data around the monitoring area, and the gas acquisition module is used to collect gas data around the monitoring area; the wind speed acquisition module is used to collect wind speed data around the monitoring area, and the noise acquisition module is used to collect noise data around the monitoring area.

[0035] like Figure 1 As shown, the drone acquisition module of this embodiment includes a video acquisition submodule and an image acquisition submodule. The video acquisition submodule includes collecting video data around the monitoring area, and the image acquisition submodule is used to collect image data around the monitoring area; the drone acquisition module is connected to a path planning submodule and a task planning submodule. The task planning submodule is used to set the drone's periodic inspection task around the monitoring area and transmit the task instruction to the path planning module. The path planning submodule is used to formulate the path of the drone in the monitoring area according to the inspection task;

[0036] Among them, the UAV collection module is connected to the machine nest module, which is used to execute automatic take-off and landing of the UAV according to the monitoring mission and to store and charge the UAV after the mission is completed. Among them, the machine nest module includes a take-off and landing platform and charging facilities. The take-off and landing platform provides a safe and stable take-off and landing place, and the charging facilities provide power supply for the UAV.

[0037] The flight of the drone can cover all monitoring areas and can reach locations that are difficult for humans to access for inspection; the detection data is transmitted to the central control unit in real time, making data processing more timely and accurate, and being able to quickly determine whether it exceeds the standard, and issue early warning prompts in a timely manner to provide better safety protection; the machine nest module provides a safe and stable take-off and landing platform and charging function, ensuring that the drone's continuous inspection mission can continue.

[0038] like Figure 1 As shown, the transmission unit of this embodiment is used to transmit the collected temperature data, gas data, wind speed data, noise data, video data and image data in the monitoring area to the data processing unit; the data processing unit compares the temperature data, gas data, wind speed data and noise data with the threshold values ​​of the temperature data, gas data, wind speed data and noise data to determine whether the temperature data, gas data, wind speed data and noise data around the monitoring area exceed the standard.

[0039] like Figure 1 As shown, the data processing unit of this embodiment is connected to a dust particle identification module, which is used to process video data and image data to identify dust particles and determine whether the dust particles exceed the standard; the specific process of analyzing and processing the received data is dust image video recognition, and the specific process of dust image video recognition is: image and video enhancement processing, the computer performs image and video enhancement processing on the dust image video based on Retinex theory, the computer uses a histogram equalization algorithm to perform image and video enhancement processing on the dust image video, image and video segmentation processing, the computer uses a regional growing segmentation algorithm to perform image and video segmentation processing on the dust image video obtained by the enhancement processing, separates dust overlapping particles, identifies dust particles, the computer performs binarization processing on the dust image video to obtain a binarized image video, the computer uses a SIFT algorithm to extract feature points from the binarized image video, extracts feature points of the edge curve of the dust overlapping particle image video, the computer uses a calling overlapping particle intersection extraction module to extract overlapping particle intersections in the feature points of the edge curve of the dust overlapping particle image video, and the computer uses a fruit fly algorithm to separate dust overlapping particles and identify dust particles.

[0040] The specific process of image enhancement processing of dust image video by computer based on Retinex theory is as follows: first, the dust image video is grayed, and then, according to Retinex theory, the dust image video S(x, y) is decomposed into the reflection object image R(x, y) and the incident light image L(x, y);

[0041] The logarithmic method is used to separate the irradiated light component and the reflected light, which can be expressed as follows:

[0042] S(x,y)=log(R(x,y))+log(L(x,y);

[0043] Among them, S(x, y) is the dust image function, R(x, y) is the function of the reflected object image, and L(x, y) is the function of the incident light image.

[0044] The dust image video S(x, y) is convolved with a Gaussian template to perform low-pass filtering, and the low-pass filtered image D(x, y) is obtained, which can be expressed as:

[0045] D(x,y)=S(x,y)*F(x,y);

[0046] Wherein, F(x, y) represents the Gaussian filter function;

[0047] In the logarithmic domain, the low-pass filtered image D(x, y) is subtracted from the original image R(x, y) to obtain the high-frequency enhanced image G(x, y), which can be expressed as:

[0048] G(x,y)=R(x,y)-log(D(x,y));

[0049] Among them, G(x, y) is the image function of high frequency enhancement, and D(x, y)) is the image function of low pass filtering.

[0050] Take the antilogarithm of the high-frequency enhanced image G(x, y) to obtain the enhanced dust image video R′(x, y):

[0051] R'(x, y)=exp(G(x, y));

[0052] Among them, G(x, y) is the high-frequency enhanced image function, and R′(x, y) is the enhanced dust image function.

[0053] The computer uses the fruit fly algorithm to separate the overlapping dust particles. The specific process of identifying the dust particles is as follows: 6 feature points are randomly selected from the intersections of each two adjacent overlapping areas, and an ellipse is fitted to the feature points between the intersections of each two adjacent overlapping areas to obtain a set of values ​​of the 6 parameters a, b, c, d, e, and h in the ellipse expression ax2+bxy+cy2+dx+ey+h=0;

[0054] Initialize the position of the fruit fly group; the position of the fruit fly group is a set of values ​​of the six parameters a, b, c, d, e, and h in the expression of the ellipse obtained in step 401;

[0055] Assign a random direction and distance for fruit fly individuals to search for food using their sense of smell, calculate the distance D from the origin, and then calculate the taste concentration judgment value S. Substitute S into the taste concentration judgment function to find the fruit fly with the highest taste concentration in this fruit fly group, record the concentration value and the X, Y coordinate values, and determine whether the preset maximum number of iterations has been reached. When the maximum number of iterations has been reached, end the process and determine the six parameters of the ellipse corresponding to the position of the fruit fly group determined by the last iteration as the six parameters a, b, c, d, e, h in the expression of the ellipse for the final ellipse fitting, ax2+bxy+cy2+dx+ey+h=0; otherwise, return to execute the above steps.

[0056] like Figure 1 As shown, the data processing unit of this embodiment is also connected to a preset module, which is used to set the thresholds of temperature data, gas data, wind speed data and noise data and the alarm level of dust particles.

[0057] like Figure 2 As shown, the data processing unit of this embodiment includes a periodic inspection module and a special inspection module, and the periodic inspection module and the special inspection module are connected to the path planning submodule, and the periodic inspection module is connected to the path planning submodule for setting periodic trigger conditions, and issuing inspection tasks of the monitoring area within a certain period to formulate the path of the UAV in the monitoring area. Generally, the period can be selected from days, weeks or months, which can be selected according to the actual situation of the monitoring area;

[0058] The special inspection module is connected to the path planning submodule to trigger special detection commands. Single-point, multi-point detection or comprehensive detection designated tasks are manually set to formulate the path of the UAV in the monitoring area. Instructions can also be triggered by special trigger conditions, such as abnormal detection data and abnormal alarm signals. The special inspection module will send the detection task to the path planning submodule. The path planning submodule determines the output planning path based on the inspection task of the task planning submodule based on the bio-inspired neural network algorithm, plans multi-point detection paths according to special inspection tasks, and plans paths within the full area coverage detection range according to periodic inspection tasks.

[0059] Instead of manually monitoring the environment of any area, it reduces the consumption of human resources and improves work efficiency. By collecting and comparing the temperature data, gas data, wind speed data, noise data and dust particles in the regional environment, it determines whether the measurement data exceeds the standard and issues alarm prompts in time to provide better safety protection. It can accurately and real-time monitor the temperature data, gas data, wind speed data, noise data and dust particle data of any area to ensure that the environmental protection emission in the monitored area meets the standard and reduce the impact on the surrounding environment.

[0060] The present invention is not limited to the above-mentioned embodiments. Anyone should be aware that any structural changes made under the enlightenment of the present invention, and any technical solutions that are the same or similar to the present invention, fall within the protection scope of the present invention. The technology, shape, and structural parts not described in detail in the present invention are all well-known technologies.

Claims

1. A monitoring system integrated with artificial intelligence, characterized in that: include: Data collection unit: used to collect the environmental data around the monitoring area in real time and send the collected environmental data of the monitoring area; Transmission unit: used to receive the monitoring area environmental data collected by the data collection unit and transmit it; Data processing unit: used to receive the monitoring area environmental data transmitted by the transmission unit, and compare the monitoring area environmental data with the preset regional environmental data threshold, determine whether the environmental data around the monitoring area exceeds the standard, and send an alarm instruction according to the judgment result; App reminder unit: used to receive the alarm instruction sent by the data processing unit, and send the alarm instruction to the terminal app to remind the operation and maintenance unit; Alarm unit: used to receive the alarm instruction sent by the data processing unit and issue an alarm.

2. A monitoring system integrated with artificial intelligence according to claim 1, characterized in that: The data acquisition unit includes a drone acquisition module, a temperature acquisition module, a gas acquisition module, a wind speed acquisition module and a noise acquisition module. The temperature acquisition module is used to collect temperature data around the monitoring area, the gas acquisition module is used to collect gas data around the monitoring area, the wind speed acquisition module is used to collect wind speed data around the monitoring area, and the noise acquisition module is used to collect noise data around the monitoring area.

3. A monitoring system integrated with artificial intelligence according to claim 2, characterized in that: The drone acquisition module includes a video acquisition submodule and an image acquisition submodule. The video acquisition submodule is used to acquire video data around the monitoring area, and the image acquisition submodule is used to acquire image data around the monitoring area.

4. A monitoring system integrated with artificial intelligence according to claim 3, characterized in that: The UAV acquisition module is connected to a path planning submodule and a task planning submodule. The task planning submodule is used to set the periodic inspection tasks of the UAV around the monitoring area and transmit the task instructions to the path planning module. The path planning submodule is used to formulate the path of the UAV in the monitoring area according to the inspection tasks.

5. The monitoring system integrated with artificial intelligence according to claim 3, characterized in that: The transmission unit is used to transmit the collected temperature data, gas data, wind speed data, noise data, video data and image data in the monitoring area to the data processing unit.

6. A monitoring system integrated with artificial intelligence according to claim 5, characterized in that: The data processing unit compares the temperature data, gas data, wind speed data and noise data with the threshold values ​​of the temperature data, gas data, wind speed data and noise data to determine whether the temperature data, gas data, wind speed data and noise data around the monitoring area exceed the standard.

7. A monitoring system integrated with artificial intelligence according to claim 6, characterized in that: The data processing unit is connected to a dust particle identification module, and the dust particle identification module is used to process the video data and the image data to identify the dust particles and determine whether the dust particles exceed the standard.

8. A monitoring system integrated with artificial intelligence according to claim 7, characterized in that: The specific process of the dust particle identification module analyzing and processing the data it receives is dust image video identification. The specific process of dust image video identification is: image and video enhancement processing, the computer performs image and video enhancement processing on the dust image video based on the Retinex theory, the computer uses a histogram equalization algorithm to perform image and video enhancement processing on the dust image video, image and video segmentation processing, the computer uses a regional growing segmentation algorithm to perform image and video segmentation processing on the dust image video obtained by the enhancement processing, separates the dust overlapping particles, and identifies the dust particles. The computer performs binarization processing on the dust image video to obtain a binarized image video, the computer uses the SIFT algorithm to extract feature points from the binarized image video, extracts the feature points of the edge curve of the dust overlapping particle image video, the computer uses the overlapping particle intersection extraction module to extract the overlapping particle intersection points in the feature points of the edge curve of the dust overlapping particle image video, and the computer uses the fruit fly algorithm to separate the dust overlapping particles and identify the dust particles.

9. A monitoring system integrated with artificial intelligence according to claim 8, characterized in that: The data processing unit is also connected to a preset module, which is used to set thresholds of temperature data, gas data, wind speed data and noise data and an alarm level of dust particles.

10. A monitoring system integrated with artificial intelligence according to claim 4, characterized in that: The data processing unit includes a periodic inspection module and a special inspection module, the periodic inspection module and the special inspection module are connected to the path planning submodule, the periodic inspection module and the path planning submodule are connected to set periodic trigger conditions, and the inspection tasks of the monitoring area are issued within a certain period to formulate the path of the UAV in the monitoring area. The special inspection module is connected to the path planning submodule to trigger special detection commands, and artificially set single-point, multi-point detection or comprehensive detection designated tasks to formulate the path of the UAV in the monitoring area.

Images