阅读说明：本技术 一种基于深度学习的新型水位高度测量系统 (Novel water level height measurement system based on deep learning ) 是由 丁勇 袁羽 孙英豪 崔何亮 于 2021-01-13 设计创作，主要内容包括：本发明公开一种基于深度学习的新型水位高度测量系统,其特征在于,包含三个模块：1、水位尺模块,水位尺模块由浮子、刻度板组成。刻度板通过连接杆安装在构筑物上,浮子中间开孔串在刻度板上；2、图像采集模块,刻度板上端口正前方设置一架摄像机,用于采集水位尺的图像,采集到的水位尺图像通过网络传输到服务器；3、图像处理模块,图像处理模块预置神经网络算法,用于识别浮子位置,再通过浮子位置计算出水位高度,继而判断水位高度变化。本发明的抗环境影响能力强,可以满足恶劣天气下的水位监测,并且消除了刻度板倒影对水位识别的不利影响,极大的提高了水位监测的灵活性和准确性。(The invention discloses a novel water level height measuring system based on deep learning, which is characterized by comprising three modules: 1. the water level gauge module consists of a floater and a scale plate. The scale plate is arranged on a structure through a connecting rod, and the middle opening of the floater is connected with the scale plate in series; 2. the image acquisition module is characterized in that a camera is arranged right in front of an upper port of the scale plate and used for acquiring images of the water level gauge, and the acquired images of the water level gauge are transmitted to the server through a network; 3. and the image processing module is used for presetting a neural network algorithm and is used for identifying the position of the floater, calculating the height of the water level according to the position of the floater and then judging the change of the height of the water level. The invention has strong environment influence resistance, can meet the requirement of water level monitoring in severe weather, eliminates the adverse effect of scale plate reflection on water level identification, and greatly improves the flexibility and accuracy of water level monitoring.)

1. The utility model provides a novel water level height measurement system based on degree of deep learning which characterized in that: the device comprises seven parts, namely a floater (1), a scale plate (2), a connecting rod (3), a structure (4), a horizontal plane (5), a camera (6) and a network server (7); the central line of the floater (1) is superposed with the horizontal plane (5); the middle of the floater (1) is provided with a hole which is connected with the scale plate (2) in series, the scale plate (2) is arranged on a structure (4), and the structure (4) is a certain pier in the embodiment; the lower half part of the scale plate (2) is inserted into the horizontal plane (5), the upper half part of the scale plate is exposed out of the horizontal plane (5), and the top end of the scale plate is marked with an elevation by a leveling instrument; the camera (6) is opposite to the measuring surface of the scale plate (2), and the included angle between the shooting center line of the camera and the perpendicular line on the surface of the scale plate (2) is not more than +/-60 degrees; images of the floater (1) and the scale plate (2) shot by the camera (6) are transmitted to a network server (7) through a network.

2. The novel water level height measuring system based on deep learning of claim 1, wherein: the water gauge comprises a water gauge module, an image acquisition module and an image processing module which are sequentially connected.

3. The novel water level height measuring system based on deep learning of claim 1, wherein: the water level gauge comprises a floater (1), a scale plate (2) and a pair of connecting rods (3).

4. The novel water level height measuring system based on deep learning of claim 1, wherein: the floater (1) is composed of a hard plastic cylinder, the volume of the floater (1) is V, the density of water is rho, and the mass of the floater (1) is M, so that the central line of the floater (1) in the vertical direction can be ensured to be coincident with the plane of a horizontal plane (5) only by ensuring that M =1/2 rho V.

5. The novel water level height measuring system based on deep learning of claim 1, wherein: the scale plate (2) is arranged on a structure to be monitored, the central line of the vertical plane of the scale plate is perpendicular to the ground, and the top end of the scale plate is used for marking out the elevation by using a level gauge.

6. The novel water level height measuring system based on deep learning of claim 1, wherein: connecting rod (3) are made by the aluminum alloy, and two connecting rod (3) one end are passed through welding mode and are connected with the upper end and the lower extreme of scale plate, and the other end passes through welding mode and is connected with the structure, and two connecting rod (3) are parallel with horizontal plane (5), connect through welding mode and can guarantee that scale plate (3) do not receive the influence that the rivers are strikeed, and stability is high.

7. The novel water level height measuring system based on deep learning of claim 1, wherein: the image acquisition module comprises a camera (6) fixed in the front of the scale plate (2), the included angle between the shooting center line and the surface perpendicular line of the scale plate (2) is not more than +/-60 degrees, the image of the water level gauge is shot in the maximum range of the camera (6), and the water level gauge image acquired by the camera (6) is sent to the network server (7).

8. The novel water level height measuring system based on deep learning of claim 1, wherein: the image processing module comprises a network server (7), a convolutional neural network algorithm is arranged in the network server (7) and is used for receiving and processing the image of the water gauge sent by the image acquisition module and storing the processing result into a database of the network server (7).

9. The novel water level height measuring system based on deep learning of claim 1, wherein: the image processing module carries out image recognition on the image of the water level gauge, extracts the position of the floater (1) in the image through the convolutional neural network, calculates the height of the water level, and then compares the height of the water level with a water level height threshold value built in the network server (7), so that whether the real-time height of the water level reaches a warning line or not is judged.

10. The novel water level height measuring system based on deep learning as claimed in claim 1, characterized by comprising the following steps:

step 1, installing a floater (1), a scale plate (2) and a connecting rod (3) to a place needing to be monitored; the top end of the scale plate (2) is used for marking out the elevation by a level gauge;

step 2, the image acquisition module utilizes a camera (6) to photograph the water level gauge;

step 3, sending the image of the water level gauge obtained by the shooting of the camera (6) to a network server (7);

step 4, the image processing module receives the image containing the water level gauge sent by the image acquisition module, stores the image on a network server (7), then performs image recognition on the image of the water level gauge, recognizes the position of the floater (1) through a convolutional neural network, knows that the height of the floater (1) is H, coincides with a horizontal plane (5) by a central line in the vertical direction of the floater (1), corresponds to a horizontal line parallel to the top of the floater (1) and has a total number m of complete E in a scale on the scale plate (6), the ratio of the incomplete E to the complete E is n, and the top of the scale plate (6) has an elevation H marked through a level; the final water level reading x = H-H/2-5 (m + n) and stores the result in the network server (7);

and 5, carrying out real-time monitoring alarm according to the obtained water level reading.

Technical Field

The invention relates to a novel water level height measuring system based on deep learning, and belongs to the field of water level monitoring.

Background

Currently, water resource and water safety issues have become one of the important factors affecting social, economic and ecological development, wherein water level data is a very critical hydrological data that can reflect these issues.

There are many methods for detecting water level in the water level station, the personal safety of monitoring personnel needs to be considered when the water level is manually measured, and the real-time performance of data is poor; the existing automatic monitoring aspect has a water level detector installed on site, and the water level height cannot be correctly identified due to reflection formed by the water surface under the interference of light. The other method is to install an image water level gauge and a camera aligned with the water level gauge, the image of the water level gauge is collected through the camera and is identified by a computer after being transmitted in a wireless or wired mode, and the method also has the problem that the interference of light forms a reflection on the water surface and the height of the water level cannot be identified correctly.

With the development of science and technology, it is a necessary trend that these traditional water level measuring methods are replaced by automatic intelligent water level monitoring methods. Based on the above, the image recognition technology is comprehensively utilized, a novel water level height measuring system based on deep learning is designed and developed, and the water level height is calculated by processing the water level gauge image through the image recognition technology. The water level gauge consists of a floater, a scale plate and two connecting rods, and the problem of recognizing the scales of the scale plate is ingeniously converted into the problem of recognizing the position change of the floater. The acquired pictures of the floater and the graduated scale are transmitted to a network server through a network, and then the position of the floater is identified through a convolutional neural network and the height of the water level is calculated, so that the remote real-time automatic monitoring of the water level can be realized, and the problem of adverse influence on the identification of the height of the water level due to reflection of the water level scale is solved.

Disclosure of Invention

Aiming at the defects of the prior art, a novel water level height measuring system based on deep learning is provided. The utility model provides a water level gauge of water level height measurement based on degree of depth study, its technical scheme as follows: it includes float, scale plate and connecting rod. The floater consists of a hard plastic cylinder, a hole is formed in the middle of the floater and is connected with the scale plate in series, and the scale plate is arranged on a structure through a connecting rod; the front surface of the scale plate is used as a measuring surface for acquiring images by the camera.

Furthermore, the drainage mass of half of the floater is equal to the mass of the whole floater, so that the floater can keep the center line in the vertical direction to be superposed with the water level, and the water level height can be known and calculated only by identifying the position of the floater when identifying the water level. The scale plate penetrates through the center of the floater, and the central hole of the floater is large enough, so that the friction between the scale plate and the floater can be ignored, and the water level measurement is more reliable.

The utility model provides a novel water level height measurement system based on degree of depth study, its technical scheme is for including water gauge module, image acquisition module, image processing module. The water level gauge module is characterized in that the graduated plate is arranged at a place to be monitored and is vertical to the ground, the lower end of the graduated plate enters the water surface, and the top end of the graduated plate is used for marking out the elevation by using a level gauge; the image acquisition module is used for photographing the water level gauge and transmitting the photographed water level gauge to the network server; and the image processing module is used for receiving the sent water level gauge image, storing the water level gauge image into the network server, carrying out image recognition on the water level gauge image, extracting the position of a floater in the water level gauge image through a convolutional neural network, and storing the result into the network server. Furthermore, the image acquisition module selects a camera for shooting, and the included angle between the shooting center line of the image acquisition module and the vertical line on the surface of the scale plate is not more than +/-60 degrees.

A novel water level monitoring method based on computer image recognition comprises the following technical scheme:

step 1: installing a scale plate at a place needing to be monitored; the top end of the scale plate is used for marking out the elevation by a level gauge;

step 2: the image acquisition module utilizes the camera to photograph the water level gauge;

and step 3: the water level gauge image shot and acquired by the camera is transmitted and uploaded to a network server through a network;

and 4, step 4: the image processing module receives the sent water level gauge image, stores the water level gauge image in a network server, then performs image recognition on the water level gauge image, recognizes the position of a floater in the water level gauge through a convolutional neural network, knows the height of the floater as H, corresponds to a horizontal line parallel to the top point of the floater to obtain the total number m of complete E in a scale on a scale plate, the ratio of incomplete E to complete E is n, and the top end of the scale plate is marked with an elevation H through a level gauge; the final water level reading x = H-H/2-5 (m + n) and stores the result in the database of the network server;

and 5: and carrying out real-time monitoring alarm according to the obtained water level reading.

The invention has the beneficial effects that: by the method, monitoring points can be quickly distributed to realize full-automatic urban waterlogging and river, and the reservoir water level is monitored in real time; the water level gauge is strong in environment influence resistance, monitoring under severe weather can be met, and adverse effects of scale plate reflection on water level identification can be eliminated.

Drawings

FIG. 1 is a schematic view of the installation of the water gauge of the present invention;

FIG. 2 is a front view of the water gauge of the present invention;

FIG. 3 is a side view of the water gauge of the present invention;

FIG. 4 is a top view of the water gauge of the present invention;

fig. 5 is a large scale view of the water gauge of the present invention.

Detailed Description

The present invention is further illustrated by the following figures and specific examples, which are to be understood as illustrative only and not as limiting the scope of the invention, which is to be given the full breadth of the appended claims and any and all equivalent modifications thereof which may occur to those skilled in the art upon reading the present specification.

The invention relates to a novel water level height measuring system based on deep learning, which comprises a floater (1), a scale plate (2), a connecting rod (3), a structure (4), a horizontal plane (5), a camera (6) and a network server (7):

the floater (1) is composed of a hard plastic cylinder, the volume of the floater (1) is known to be V, the mass of the floater (1) is known to be M, and the central line of the floater (1) in the vertical direction can be ensured to coincide with the water surface only by ensuring that M =1/2 rho V;

the water level gauge module comprises a floater (1), a graduated plate (2) and two connecting rods (3), wherein the graduated plate (2) is arranged at a place to be monitored and is vertical to the ground, and the top end of the graduated plate is used for marking out the height by using a level gauge;

the image acquisition module comprises a camera (6) for photographing the water level gauge and uploading the water level gauge image to the network server (7);

the image processing module comprises a network server (7) and is used for receiving the sent image of the water level gauge, storing the image of the water level gauge into the network server (7), carrying out image recognition on the image of the water level gauge, extracting the position of the floater (1) in the image through a convolutional neural network, and storing the result into a database of the network server (7).

Wherein, a novel water level height measurement system's water level gauge based on degree of depth study, its technical scheme as follows: the device comprises a floater (1), a scale plate (2) and a connecting rod (3), wherein the scale plate (2) faces a camera (6) and serves as a measuring surface for acquiring images, and the other surface back to the camera (6) is called as a mounting surface;

as shown in figure 1, the lower half part of the scale plate (2) is vertically inserted into water, and the upper half part is exposed out of the water surface. The top end of the water level is used for marking out the elevation. The camera (6) is over against the measuring surface of the scale plate (2), and the included angle between the shooting center line of the camera and the perpendicular line on the surface of the scale plate (2) is not more than +/-60 degrees. The specific measurement method is as follows:

step 1, mounting a hard plastic cylinder (1), a scale plate (2) and a connecting rod (3) to a place to be monitored; the top end of the scale plate (2) is used for marking out the elevation by a level gauge;

step 2, the image acquisition module utilizes a camera to photograph the water level gauge;

step 3, the image of the water level ruler obtained by photographing is transmitted and uploaded to a network server (7) through a network;

step 4, the image processing module receives the sent image containing the water level gauge, stores the image into a network server (7), then performs image recognition on the image containing the water level gauge, recognizes the position of the floater (1) through a convolutional neural network, knows that the height of the floater (1) is H, coincides the central line of the floater (1) in the vertical direction with the horizontal plane (5), corresponds to the horizontal line parallel to the top of the floater (1) and has the total number m of complete E in the scale on the scale plate (6), the ratio of the incomplete E to the complete E is n, and the top of the scale plate (6) has the height H marked through a level; the final water level reading x = H-H/2-5 (m + n) and the result is stored in the network server (7).

And 5, carrying out real-time monitoring alarm according to the obtained water level reading.

The invention only needs one water level gauge, can quickly lay the water level gauge to a place to be monitored, lays a camera (6) opposite to the graduated plate (2), transmits the water level gauge to a network server (7) through a network, is received by the network server (7), displays and applies the water level gauge after image recognition, is different from the prior automatic monitoring water level gauge and recognition method, has high recognition precision requirement of a computer on the water level gauge, is difficult to keep the stability of a shot image under the influence of natural factors and in severe weather environment so as to lead the computer to be difficult to recognize, solves the problem by a novel water level height measuring system based on deep learning, and has no characters on the whole graduated plate (2) and only a floater (1) which is strung on the graduated plate. In the embodiment, the standard diameter of the floater (1) is 0.2m, the height of the floater is 0.3m, only the total number m of the complete E on the scale plate (2) corresponding to a horizontal line parallel to the top point of the floater (1) needs to be identified, the ratio of the incomplete E to the complete E is n, the height H printed by the top end of the scale plate (2) through a level gauge is high, and the final water level reading x = H-0.15-5(m + n).

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.