Binocular image flow measuring instrument of unmanned aerial vehicle

Abstract

The invention relates to an unmanned aerial vehicle binocular image flow measuring instrument, which comprises a lens, an image sensor, an unmanned aerial vehicle, a flight control system RTK, a CPU, an infrared lamp, a 4G communication module and a platform server, and is characterized in that the lens, the image sensor and the CPU are sequentially connected, the flight control system RTK, the unmanned aerial vehicle and the CPU are sequentially connected, the platform server, the 4G communication module and the CPU are sequentially connected, the infrared lamp is connected with the CPU, the lens is used for collecting a current image, and the image sensor is used for sensing the current image. The image sensor is used for processing images collected by the lens. The binocular camera shooting technology is combined with the video AI technology to replace a traditional radar scheme, visual monitoring of the water level, the flow velocity and the flow is achieved, video analysis can be replied afterwards, and the cost is lower than that of a traditional radar mode.

Description

Technical Field

[0001] The present invention belongs to the technical field of water area monitoring, in particular to an unmanned aerial vehicle binocular imaging current measuring instrument. Background Art

[0002] In recent years, AI intelligent recognition technology and unmanned flight control technology have become increasingly mature, and technologies such as video behavior analysis, face recognition, and license plate recognition have been widely used. The application of cameras in hydrology and water conservancy is still in the primary video monitoring stage, and AI recognition technology has not yet been widely used in water conservancy video monitoring. In addition, mountain torrents are sudden, and traditional monitoring equipment is slow to deploy and dangerous to measure. Water level and flow rate monitoring drone equipment is portable, has low scene requirements, and can be put into use immediately. It uses binocular camera shooting technology to measure water level and flow rate, which is more cost-effective than radar measurement of water level and flow rate.

[0003] A flow meter is an instrument used to measure parameters such as fluid velocity and flow rate. Its core function is to achieve non-contact or contact measurement through different technologies. The following are the main categories and characteristics:

[0004] Classification by measurement principle:

[0005] Contact flow meters use the velocity-area method to calculate flow rates by placing the sensor in direct contact with the fluid (such as the center of a pipe).

[0006] Non-contact flow meters use radar beam, microwave or electromagnetic induction technology to measure without contacting the fluid. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the existing technology and propose an unmanned aerial vehicle binocular imaging flow meter, which can use binocular camera shooting technology combined with video AI technology to replace the traditional radar solution, realize visual monitoring of water level, flow rate and flow, and can restore video analysis afterwards, which is lower in cost than traditional radar methods.

[0008] The present invention solves the technical problem by adopting the following technical solutions:

[0009] The UAV binocular image flow meter includes a lens, an image sensor, a UAV, a flight control system RTK, a CPU, an infrared light, and a 4G communication module. The lens, image sensor, and CPU are connected in sequence for collecting and storing images and for video analysis. The flight control system RTK, the UAV, and the CPU are connected in sequence for flight control and high-precision positioning. The 4G communication module and the CPU are connected in sequence for wireless communication. The infrared light is connected to the CPU for nighttime supplementary lighting.

[0010] Moreover, the number of the lenses is two, the number of image sensors corresponds to the number of lenses, and the two lenses are respectively connected to the corresponding image sensors.

[0011] Moreover, the flight control system RTK includes an MCU, an attitude sensor and a brushless motor. The MCU is connected to the attitude sensor and the brushless motor respectively. The attitude sensor is used to obtain the current attitude of the drone. The MCU is used to control the brushless motor according to the acquired current attitude of the drone, complete the attitude adjustment and flight of the drone, and realize multi-point water level and flow velocity monitoring of the river section.

[0012] Moreover, the infrared light is used for nighttime supplementary lighting. When it is nighttime, the light-sensitive sensor on the drone senses that it is dark and turns on the supplementary light. After the supplementary light is turned on, the camera can capture clear images at night. The 4G communication module is used for the drone to communicate with the server of the back-end control center to transmit video recordings and measurement data. The server receives the video recordings and measurement data of the drone.

[0013] A working method of a binocular imaging flow meter for an unmanned aerial vehicle comprises the following steps:

[0014] Step 1: The flight control system RTK controls the drone to take off;

[0015] Step 2: The lens captures the image of the water surface and transmits it to the corresponding image sensor;

[0016] Step 3: The image sensor transmits the image to the CPU;

[0017] Step 4: The CPU processes the image according to the preselected function.

[0018] Moreover, the functions in step 4 include flow rate monitoring and water level detection.

[0019] Furthermore, the flow rate monitoring comprises the following steps:

[0020] Step 4.1.1: Use two image sensors to collect two-channel river surface videos in real time and transmit them to the CPU;

[0021] Step 4.1.2: The intelligent analysis module in the CPU first detects the corner points formed by floating objects or waves in the two frames of the two videos at the same time as feature points. It then matches the feature points of the two frames to identify the same feature point and obtains the pixel coordinates of this feature point in the two images. It also calculates the physical size of the unit pixel on the water surface when the camera is shooting the water surface.

[0022] Step 4.1.3. The intelligent analysis module in the CPU detects the corner points formed by floating objects or waves in the two frames of the video as feature points, matches the feature points of the two frames to identify the same feature point, obtains the pixel coordinates of this feature point in the two frames, and obtains the pixel displacement of this feature point within one frame. Then, the physical displacement of the feature point is calculated based on the physical size corresponding to the unit pixel at the current water surface. Finally, the physical displacement is divided by one frame to obtain the flow velocity of this feature point and the surface flow velocity of the river.

[0023] Moreover, the water level detection comprises the following steps:

[0024] Step 4.2.1, obtain water level data,

[0025] Step 4.2.2, perform calculations based on the acquired water level data;

[0026] The vertical distance from the camera to the water surface is:

[0027] D=F×S / P

[0028] The water level is:

[0029] H1=H2-D

[0030] Where S is the physical size of a unit pixel on the water surface when the camera captures the water surface; F is the focal length of the camera lens; P is the pixel size of the camera image sensor; D is the vertical distance from the camera to the water surface; H1 is the water level; and H2 is the elevation of the camera location, which is obtained using RTK.

[0031] The advantages and positive effects of the present invention are:

[0032] The present invention includes a lens, image sensor, drone, flight control system RTK, CPU, infrared light, 4G communication module and platform server, wherein the lens, image sensor and CPU are connected in sequence, the flight control system RTK, drone and CPU are connected in sequence, the platform server, 4G communication module and CPU are connected in sequence, the infrared light is connected to the CPU, the lens is used to collect the current image, and the image sensor is used to process the image collected by the lens. The present invention can use binocular camera shooting technology combined with video AI technology to replace traditional radar solutions, realize visual monitoring of water level, flow rate and flow, and can return to video analysis afterwards, which is lower in cost than traditional radar methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a structural diagram of the current measuring instrument of the present invention;

[0034] Figure 2 This is a specific implementation method of water level detection of the present invention. DETAILED DESCRIPTION

[0035] The present invention is further described below in conjunction with the accompanying drawings.

[0036] UAV binocular imaging flow meter, such as Figure 1 As shown, it includes a lens, an image sensor, a drone, a flight control system RTK, a CPU, an infrared light, and a 4G communication module. The lens, image sensor, and CPU are connected in sequence for collecting and storing images and for video analysis. The flight control system RTK, the drone, and the CPU are connected in sequence for flight control and high-precision positioning. The 4G communication module and the CPU are connected in sequence for wireless communication. The infrared light is connected to the CPU for nighttime fill light.

[0037] There are two lenses, and the number of image sensors corresponds to the number of lenses. The two lenses are connected to corresponding image sensors respectively.

[0038] The RTK flight control system includes an MCU, an attitude sensor, and a brushless motor. The MCU is connected to the attitude sensor and the brushless motor respectively. The attitude sensor is used to obtain the current attitude of the drone. The MCU is used to control the brushless motor based on the acquired current attitude of the drone, complete the attitude adjustment and flight of the drone, and realize multi-point water level and flow velocity monitoring of the river section.

[0039] Infrared lights are used for nighttime fill-in lighting. When night falls, the photosensitive sensor on the drone senses darkness and turns on the fill-in light. After the fill-in light is turned on, the camera can capture clear images at night. The 4G communication module is used for communication between the drone and the server in the back-end control center to transmit video footage and measurement data. The server receives the video footage and measurement data from the drone.

[0040] A working method of a binocular imaging flow meter for an unmanned aerial vehicle comprises the following steps:

[0041] Step 1: The flight control system RTK controls the drone to take off;

[0042] Step 2: The lens captures the image of the water surface and transmits it to the corresponding image sensor;

[0043] Step 3: The image sensor transmits the image to the CPU;

[0044] Step 4: The CPU processes the image according to the preselected function.

[0045] Functions include flow rate monitoring and water level detection.

[0046] Flow rate monitoring includes the following steps:

[0047] Step 4.1.1: Use two image sensors to collect two-channel river surface videos in real time and transmit them to the CPU;

[0048] Step 4.1.2: The intelligent analysis module in the CPU first detects the corner points formed by floating objects or waves in the two frames of the two videos at the same time as feature points. It then matches the feature points of the two frames to identify the same feature point and obtains the pixel coordinates of this feature point in the two images. It also calculates the physical size of the unit pixel on the water surface when the camera is shooting the water surface.

[0049] Step 4.1.3. The intelligent analysis module in the CPU detects the corner points formed by floating objects or waves in the two frames of the video as feature points, matches the feature points of the two frames to identify the same feature point, obtains the pixel coordinates of this feature point in the two frames, and obtains the pixel displacement of this feature point within one frame. Then, the physical displacement of the feature point is calculated based on the physical size corresponding to the unit pixel at the current water surface. Finally, the physical displacement is divided by one frame to obtain the flow velocity of this feature point and the surface flow velocity of the river.

[0050] like Figure 2 As shown, water level detection includes the following steps:

[0051] Step 4.2.1, obtain water level data,

[0052] Step 4.2.2, perform calculations based on the acquired water level data;

[0053] The vertical distance from the camera to the water surface is:

[0054] D=F×S / P

[0055] The water level is:

[0056] H1=H2-D

[0057] Where S is the physical size of a unit pixel on the water surface when the camera captures the water surface; F is the focal length of the camera lens; P is the pixel size of the camera image sensor; D is the vertical distance from the camera to the water surface; H1 is the water level; and H2 is the elevation of the camera location, which is obtained using RTK.

[0058] It should be emphasized that the embodiments described in the present invention are illustrative rather than restrictive. Therefore, the present invention includes but is not limited to the embodiments described in the specific embodiments. Any other embodiments derived by those skilled in the art based on the technical solutions of the present invention also fall within the scope of protection of the present invention.

Claims

1. UAV binocular imaging flow meter, characterized by: It includes lens, image sensor, drone, flight control system RTK, CPU, infrared light, and 4G communication module. The lens, image sensor and CPU are connected in sequence for collecting and storing images and used for video analysis. The flight control system RTK, drone and CPU are connected in sequence for flight control and high-precision positioning. The 4G communication module and CPU are connected in sequence for wireless communication. The infrared light is connected to the CPU for nighttime fill light.

2. The UAV binocular imaging flow meter according to claim 1, characterized in that: The number of the lenses is two, the number of image sensors corresponds to the number of lenses, and the two lenses are respectively connected to corresponding image sensors.

3. The UAV binocular imaging flow meter according to claim 1, characterized in that: The flight control system RTK includes an MCU, an attitude sensor and a brushless motor. The MCU is connected to the attitude sensor and the brushless motor respectively. The attitude sensor is used to obtain the current attitude of the drone. The MCU is used to control the brushless motor according to the obtained current attitude of the drone, complete the attitude adjustment and flight of the drone, and realize multi-point water level and flow velocity monitoring of the river section.

4. The UAV binocular imaging flow meter according to claim 1, characterized in that: The infrared light is used for nighttime supplementary lighting. When night falls, the light-sensitive sensor on the drone senses that it is dark and turns on the supplementary light. After the supplementary light is turned on, the camera can capture clear images at night. The 4G communication module is used for the drone to communicate with the server of the back-end control center to transmit video recordings and measurement data. The server receives the video recordings and measurement data of the drone.

5. A method for operating the UAV binocular imaging flow meter according to any one of claims 1 to 4, characterized in that: The following steps are involved: Step 1: The flight control system RTK controls the drone to take off; Step 2: The lens captures the image of the water surface and transmits it to the corresponding image sensor; Step 3: The image sensor transmits the image to the CPU; Step 4: The CPU processes the image according to the preselected function.

6. The UAV binocular imaging flow meter according to claim 1, characterized in that: The functions in step 4 include flow rate monitoring and water level detection.

7. The UAV binocular imaging flow meter according to claim 6, characterized in that: The flow rate monitoring comprises the following steps: Step 4.1.1: Use two image sensors to collect two-channel river surface videos in real time and transmit them to the CPU; Step 4.1.2: The intelligent analysis module in the CPU first detects the corner points formed by floating objects or waves in the two frames of the two videos at the same time as feature points. It then matches the feature points of the two frames to identify the same feature point and obtains the pixel coordinates of this feature point in the two images. It also calculates the physical size of the unit pixel on the water surface when the camera is shooting the water surface. Step 4.1.

3. The intelligent analysis module in the CPU detects the corner points formed by floating objects or waves in the two frames of the video as feature points, matches the feature points of the two frames to identify the same feature point, obtains the pixel coordinates of this feature point in the two frames, and obtains the pixel displacement of this feature point within one frame. Then, the physical displacement of the feature point is calculated based on the physical size corresponding to the unit pixel at the current water surface. Finally, the physical displacement is divided by one frame to obtain the flow velocity of this feature point and the surface flow velocity of the river.

8. The UAV binocular imaging flow meter according to claim 6, characterized in that: The water level detection comprises the following steps: Step 4.2.1, obtain water level data, Step 4.2.2, perform calculations based on the acquired water level data; The vertical distance from the camera to the water surface is: D=F×S / P The water level is: H1=H2-D Where S is the physical size of the unit pixel on the water surface when the camera shoots the water surface; F is the focal length of the camera lens; P is the pixel size of the camera image sensor; D is the vertical distance from the camera to the water surface; H1 is the water level; H2 is the elevation of the camera location, and the elevation data is obtained through RTK.

Images