River channel bank slope monitoring system and method based on three-dimensional binocular recognition

Abstract

The invention discloses a river channel bank slope monitoring system and method based on three-dimensional binocular recognition. The river channel bank slope monitoring system comprises a telescopic supporting part and a monitoring part. The telescopic supporting part comprises a vertical pipe, a sliding pipe and a transverse pipe, the lower end of the sliding pipe is slidably connected to an inner cavity of the vertical pipe, and a microcomputer is fixed to the outer wall of the sliding pipe; the outer wall of the transverse pipe is vertically fixed at the upper end of the sliding pipe; the two ends of the transverse pipe are slidably connected with mounting pipes; the monitoring part comprises a supporting tube and a camera; the lower end of the supporting pipe is vertically fixed to the end, away from the transverse pipe, of the mounting pipe, the camera is rotationally connected to the upper end of the supporting pipe, a lens corresponds to a monitoring area on a bank slope, and the microcomputer is in communication connection with the camera to control the shooting period. According to the invention, the coordinates of the monitoring points in the monitoring area are corrected and converted through the internal and external parameters of the camera, and the deformation of each monitoring point is calculated through the European algorithm, so that the non-contact automatic monitoring of the deformation of the river channel bank slope and the real-time feedback of data can be effectively realized.

Description

Technical Field

[0001] The present invention relates to the technical field of bank protection engineering monitoring, and more particularly to a river channel bank slope monitoring system and method based on three-dimensional binocular recognition. Background Art

[0002] Taking advantage of the natural advantages of dense water networks and crisscrossing waters, and relying on the common technical means used in waterway engineering when establishing waterways and ports to develop inland waterway transportation.

[0003] Compared with other modes of transportation, water transport has advantages such as large transport capacity and low costs. Waterways are the foundation of water transport and are important public transportation infrastructure.

[0004] Deformation of these waterways could not only affect water transport but also threaten the safety of people nearby. Therefore, monitoring the bank slopes of these waterways is particularly important. However, in situ monitoring of these bank slopes is not easy.

[0005] Therefore, how to provide a non-contact monitoring method that can monitor the deformation of river channel slopes in real time is an urgent problem that needs to be solved by those skilled in the art. Summary of the Invention

[0006] In view of this, the present invention provides a river channel bank slope monitoring system and method based on three-dimensional binocular recognition, which solves the safety problem of river channel bank slopes in areas with abundant rainfall and achieves real-time monitoring and real-time feedback.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A river channel bank slope monitoring system based on three-dimensional binocular recognition, comprising a telescopic support part and a monitoring part;

[0009] The telescopic support portion includes a vertical tube, a sliding tube, and a horizontal tube. The lower end of the sliding tube is slidably connected to the inner cavity of the vertical tube, and a microcomputer is fixed to the outer wall of the sliding tube; the outer wall of the horizontal tube is vertically fixed to the upper end of the sliding tube; both ends of the horizontal tube are slidably connected to the mounting tube;

[0010] The monitoring unit includes a support tube and a camera; the lower end of the support tube is vertically fixed to the end of the mounting tube away from the horizontal tube, the camera is rotatably connected to the upper end of the support tube and its lens corresponds to the monitoring area on the slope, and the microcomputer is communicatively connected to the camera to control its shooting cycle.

[0011] The beneficial effect of the technical solution of the present invention is that the camera is used to collect images of the monitoring area. According to the comparison of images collected at different periods, the displacement of the monitoring points in the monitoring area can be obtained, thereby realizing real-time monitoring of the river channel bank slope; the camera can adjust its position up and down through the sliding tube, can adjust its position left and right through the mounting tube, and can adjust its angle through the support tube. The camera can better collect image data of the monitoring area through multi-dimensional posture adjustment.

[0012] Preferably, a rotary motor is fixed within the support tube, a rotating shaft is coaxially fixed to the output shaft of the rotary motor, and an end of the rotating shaft remote from the rotary motor is fixed to the camera body; the rotary motor is electrically connected to the microcomputer. The microcomputer drives the rotary motor, and when the rotary motor is activated, the camera's rotation angle can be adjusted.

[0013] Preferably, a rotation angle sensor is fixed on the rotating shaft, and the rotation angle sensor is communicatively connected to the microcomputer. The rotation angle sensor can calculate the relative rotation angle when adjusting the camera posture and transmit the data to the microcomputer.

[0014] Preferably, a rain-sensing wiper is hingedly connected to the outer wall of the camera lens; a rain sensor is fixed within the camera body; and both the rain-sensing wiper and the rain sensor are communicatively connected to the microcomputer. During rainy days, the probability of damage to river channel slopes increases, and rain significantly affects the clarity of images captured by the camera. The rain sensor senses rainfall, transmits it to the microcomputer, and calculates and adjusts the camera's posture to achieve a shooting angle suitable for light rain, and adjusts the speed of the rain-sensing wiper to ensure the clarity of the images captured by the camera.

[0015] Preferably, a slide rail is slidably connected to the inner wall of the vertical tube, and the upper end of the slide rail is fixed to the lower end of the sliding tube. The slide rail drives the sliding tube to extend and retract relative to the vertical tube, thereby adjusting the height position of the camera.

[0016] Preferably, the apparatus further comprises a telescopic motor, the telescopic motor being fixed to the outer wall of the vertical tube; the output shaft of the telescopic motor being in driving connection with the slide rail; and the telescopic motor being electrically connected to the microcomputer. The telescopic motor drives the slide rail to slide, thereby achieving movement of the sliding tube.

[0017] Preferably, a magnetostrictive sensor is fixed to the vertical tube, with a sensing end of the magnetostrictive sensor located within the inner cavity of the sliding tube and communicatively connected to the microcomputer. The magnetostrictive sensor calculates the displacement generated by the sliding tube adjusting the position of the camera in three-dimensional space and transmits the calculated displacement to the microcomputer.

[0018] Preferably, a base is fixed to the lower end of the vertical pipe, which supports the vertical pipe and ensures stability during use.

[0019] Preferably, the system further comprises a photovoltaic panel, the photovoltaic panel being electrically connected to the microcomputer; the microcomputer being communicatively connected to a remote control center. By using the photovoltaic panel for power supply and monitoring by the remote center, the bank slope of the river channel can be monitored in real time and data can be fed back promptly.

[0020] The present invention also provides a river channel bank slope monitoring method based on three-dimensional binocular recognition, which uses the monitoring system in the above technical solution and includes the following steps:

[0021] S1. Adjust the telescopic support part and the monitoring part to the standard position;

[0022] S2. Adjust the camera posture according to the distance between the monitoring system and the bank slope and the scope of the monitoring area;

[0023] S3, correct the camera's epipolar and distortion;

[0024] S4. Calculate the displacement of the monitoring points within the monitoring area and generate a displacement curve for the monitoring period.

[0025] It can be seen from the above technical solution that compared with the existing technology, the present invention discloses a river channel bank slope monitoring system and method based on three-dimensional binocular recognition. The coordinates of the monitoring points in the monitoring area are corrected and converted by the internal and external parameters of the camera, and the deformation of each monitoring point is calculated by the Euclidean algorithm. It can effectively achieve non-contact automatic monitoring of the river channel bank slope deformation and real-time feedback of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0027] Figure 1 A schematic diagram of the monitoring system provided by the present invention;

[0028] Figure 2 A schematic diagram of the structure of the monitoring unit provided by the present invention;

[0029] Figure 3 A schematic structural diagram of the telescopic support portion provided by the present invention;

[0030] Figure 4 This is a flow chart for river channel slope monitoring provided by the present invention.

[0031] in,

[0032] 1-bank slope; 2-monitoring area; 21-monitoring point; 3-photovoltaic panel; 4-telescopic support; 41-riser; 42-slide rail; 43-telescopic motor; 44-magnetic sensor; 45-slide tube; 46-riser; 5-base; 6-monitoring unit; 61-support tube; 62-rotating motor; 63-rotation angle sensor; 64-rotating shaft; 65-camera; 66-rain sensor; 67-inductive wiper; 7-microcomputer; 8-remote control center; DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] Example 1:

[0035] See attached Figures 1 to 3 , the embodiment of the present invention discloses a river channel bank slope monitoring system based on three-dimensional binocular recognition, including a telescopic support part 4 and a monitoring part 6;

[0036] The telescopic support portion 4 includes a vertical tube 41, a sliding tube 45, and a horizontal tube 46. The lower end of the sliding tube 45 is slidably connected to the inner cavity of the vertical tube 41, and the microcomputer 7 is fixed to the outer wall of the sliding tube 45; the outer wall of the horizontal tube 46 is vertically fixed to the upper end of the sliding tube 45; and the two ends of the horizontal tube 46 are slidably connected to the mounting tube.

[0037] The monitoring unit 6 includes a support tube 61 and a camera 65; the lower end of the support tube 61 is vertically fixed to the end of the mounting tube away from the horizontal tube 46, the camera 65 is rotatably connected to the upper end of the support tube 61 and its lens corresponds to the monitoring area 2 on the slope 1, and the microcomputer 7 communicates with the camera 65 to control its shooting cycle.

[0038] like Figure 1 As shown, a monitoring area 2 is divided at a weak point of the bank slope 1, and a number of monitoring points 21 are arranged in the monitoring area 2. At the same time, the monitoring points 21 within the edge of the monitoring area 2 are densely arranged. The height of the camera 65 is adjusted by the telescopic support part 4, the relative distance between the two cameras 65 is adjusted by the mounting tube, the rotation angle of the camera 65 is adjusted by the support tube 61, and the posture of the camera 65 is adjusted in multiple dimensions. The shooting cycle of the camera 65 is set by the microcomputer 7, and the image data shot by the camera 65 is compared to obtain the displacement data of the monitoring point 21, and then understand the deformation of the waterway bank slope 1, realize real-time monitoring of the river waterway bank slope 1, and facilitate the subsequent maintenance of the river waterway bank slope 1 by technical personnel.

[0039] In order to further optimize the above technical solution, a rotating motor 62 is fixed in the support tube 61, and a rotating shaft 64 is coaxially fixed to the output shaft of the rotating motor 62. The end of the rotating shaft 64 away from the rotating motor 62 is fixed to the body of the camera 65; the rotating motor 62 is electrically connected to the microcomputer 7.

[0040] like Figure 2 As shown, the support tube and the rotating shaft are coaxially arranged, and the rotating motor is fixed in the support tube. The rotating motor drives the rotating shaft to realize the rotation of the camera, thereby adjusting the camera angle.

[0041] In order to further optimize the above technical solution, the relative rotation angle when adjusting the postures of the two cameras is calculated and the data is transmitted to the microcomputer. A rotation angle sensor 63 is fixed on the rotating shaft 64, and the rotation angle sensor 63 is communicatively connected to the microcomputer 7.

[0042] In order to further optimize the above technical solution and perform non-contact real-time monitoring of the bank slope on rainy days, the outer wall of the lens of the camera 65 is hinged with a sensing wiper 67; a rain sensor 66 is fixed in the body of the camera 65; the sensing wiper 67 and the rain sensor 66 are both communicatively connected to the microcomputer 7.

[0043] The rain-sensing wipers can be activated on rainy days to ensure the clarity of the lens shooting; the rain sensor can sense the amount of rainfall. After the rain sensor transmits the rainfall data to the microcomputer, it uses an intelligent algorithm to calculate the camera's turning angle towards the side with less rain, while ensuring that the camera can shoot the monitored area. After the data is fed back to the angle sensor, the rotation motor is controlled to start to adjust the rotation angle of the two cameras, and the speed of the inductive wipers and the camera's shooting cycle are adjusted to ensure that the camera's shooting image and the inductive wiper action do not conflict with each other.

[0044] In order to further optimize the above technical solution and ensure the effective extension and contraction of the sliding tube along the vertical tube, the inner wall of the vertical tube 41 is slidably connected with a sliding rail 42, and the upper end of the sliding rail 42 is fixed to the lower end of the sliding tube 45.

[0045] In order to further optimize the above technical solution, the sliding rail is driven to move, and a telescopic motor 43 is also included. The telescopic motor 43 is fixed to the outer wall of the vertical tube 41; the output shaft of the telescopic motor 43 is connected to the sliding rail 42; the telescopic motor 43 is electrically connected to the microcomputer 7.

[0046] like Figure 3 As shown, the telescopic motor drives the slide rail to slide up and down along the inner wall of the vertical tube. During the sliding process of the slide rail, it can drive the movement of the sliding tube to realize the telescopic operation and then adjust the height of the camera.

[0047] In other specific embodiments, there are multiple sliding tubes, which are coaxially arranged in sequence, and a limit piece is provided between the upper end of the sliding tube located at the bottom and the lower end of the sliding tube located at the top to prevent the two adjacent sliding tubes from detaching; the sliding rail is fixed to the bottom end of the innermost sliding rail tube through a connecting rod, and the movement of the innermost sliding tube is driven by the sliding rail. When the innermost sliding tube is extended or retracted, the lower end of the innermost sliding tube contacts the limit piece, which drives the outer sliding tube to move upward, thereby realizing multi-stage extension and retraction.

[0048] In order to further optimize the above technical solution, there is a sliding gap between the inner and outer walls of multiple sliding tubes, and there is also a sliding gap between the outer wall of the outermost sliding tube and the inner wall of the vertical tube, to ensure that the innermost sliding tube can drive the remaining sliding tubes to perform passive expansion and contraction during the active expansion and contraction of the sliding rail.

[0049] In order to further optimize the above technical solution and better monitor the telescopic displacement of the sliding tube, a magnetostrictive sensor 44 is fixed on the vertical tube 41. The sensing end of the magnetostrictive sensor 44 is located in the inner cavity of the sliding tube 45 and is communicatively connected to the microcomputer 7.

[0050] In this embodiment, if Figure 1 As shown, the support tube and the installation tube are made into an L-shaped tube in one piece. The sliding mode of the installation tube along the crossbar is the same as the movement mode of the sliding tube along the vertical tube, which will not be described in detail here.

[0051] In order to further optimize the above technical solution and ensure the stability of the telescopic support part during use, a base 5 is fixed to the lower end of the vertical pipe 41.

[0052] In order to further optimize the above technical solution and realize remote real-time monitoring of the river channel bank slope, it also includes a photovoltaic panel 3, which is electrically connected to a microcomputer 7; the microcomputer 7 is communicatively connected to a remote control center 8.

[0053] Example 2:

[0054] like Figure 1 and 4 As shown, this embodiment provides a river channel bank slope monitoring method based on three-dimensional binocular recognition, which uses the monitoring system in Example 1 to monitor the river channel bank slope, including the following steps:

[0055] S1. Adjust the telescopic support part and the monitoring part to the standard position;

[0056] After the monitoring system is laid out, the sliding tube does not extend out of the vertical tube, and the axis of the camera and the axis of the horizontal tube are arranged perpendicular to each other;

[0057] S2. Adjust the camera posture according to the distance between the monitoring system and the bank slope and the scope of the monitoring area;

[0058] Adjust the postures of the two cameras according to the distance between the base and the river channel bank and the scope of the monitoring area;

[0059] The telescopic motor drives the slide rail to adjust the camera height and the distance between the two cameras, that is, to adjust the spatial position of the camera, and the camera displacement is recorded by the magnetostrictive sensor and transmitted to the microcomputer;

[0060] The rotation angle of the camera is adjusted by the rotation motor, and the camera angle is recorded by the angle sensor and transmitted to the microcomputer;

[0061] By adjusting the camera posture, both cameras can cover the monitoring area to collect image data of the monitoring area;

[0062] S3, correct the camera's epipolar and distortion;

[0063] After adjusting the camera posture, the two camera epipolar lines are not horizontal and need to be corrected to be horizontal. The irregular changes in the curvature of the camera lens cause radial distortion, and the installation makes the lens non-parallel to the lens plane, which causes tangential distortion and needs to be corrected.

[0064] The intrinsic parameter matrix A, extrinsic parameter matrix [R|T] and distortion coefficients [k1, k2, k3, p1, p2] of camera 6 are calibrated using a black and white chessboard calibration board;

[0065] The calibration reference object (chessboard) is photographed at different angles, and the vertices of the chessboard are extracted. The camera's distortion coefficients and internal and external parameters are then analyzed. Finally, the parameters are optimized based on maximum likelihood estimation.

[0066] Use the homography matrix to correct the two-phase epipolar lines so that the epipolar lines of the two cameras are collinear and parallel to the x-axis of the phase plane, thus satisfying the epipolar line constraint;

[0067] Then, the source image pixel coordinate system is converted into the camera coordinate system through the intrinsic parameter matrix (compared with the image physical coordinate system, it has more scaling and Z-axis). The epipolar lines are corrected using the rotation matrices R1 and R2. The camera coordinates of the image are then corrected using the distortion coefficients. After correction, the camera coordinate system is converted into the image pixel coordinate system through the intrinsic parameter matrix, and the new image coordinates are assigned according to the pixel values ​​of the source image coordinates.

[0068] S4. Calculate the displacement of the monitoring points within the monitoring area and generate a displacement curve for the monitoring period.

[0069] The image data captured by the two cameras are processed to calculate the displacement of the monitoring points of the two cameras in the same cycle, and the displacement of the monitoring points in multiple cycles are summarized to generate a displacement curve for the monitoring period;

[0070] The original image pixel coordinate system is converted into the camera coordinate system through the intrinsic parameter matrix. The epipolar lines are corrected using the rotation matrix and then the camera coordinates of the image are corrected using the distortion coefficient. After correction, the camera coordinate system is converted into the image pixel coordinate system through the intrinsic parameter matrix and the new image coordinates are assigned according to the pixel values ​​of the original image coordinates.

[0071] Then convert the pixel coordinates into image physical coordinates, then convert the image physical coordinates into camera coordinates, and then convert the camera coordinates into world coordinates;

[0072] After obtaining the pixel coordinates of each monitoring point in each captured image, its world coordinates can be obtained. Then, the Euclidean algorithm is used to calculate the displacement of each monitoring point and draw a displacement curve for the monitoring period.

[0073] In order to further optimize the above technical solution, when it rains, the probability of damage to the river channel bank slope increases, and rain has a great impact on the clarity of the camera's images. The rainfall is sensed by the rain sensor and transmitted to the microcomputer, which calculates and adjusts the camera posture to meet the small amount of rainfall, adjusts the speed of the inductive wiper, and adjusts the cycle of the camera's image shooting to ensure that the camera and the rotation of the inductive wiper do not affect each other during shooting, ensuring the clarity and completeness of the captured images.

[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0075] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A river channel slope monitoring system based on three-dimensional binocular recognition, characterized in that: It comprises a telescopic support portion (4) and a monitoring portion (6); The telescopic support portion (4) comprises a vertical tube (41), a sliding tube (45) and a horizontal tube (46); the lower end of the sliding tube (45) is slidably connected to the inner cavity of the vertical tube (41); a microcomputer (7) is fixed to the outer wall of the sliding tube (45); the outer wall of the horizontal tube (46) is vertically fixed to the upper end of the sliding tube (45); both ends of the horizontal tube (46) are slidably connected to mounting tubes; The monitoring unit (6) includes a support tube (61) and a camera (65); the lower end of the support tube (61) is vertically fixed to an end of the mounting tube away from the transverse tube (46); the camera (65) is rotatably connected to the upper end of the support tube (61) and its lens corresponds to the monitoring area (2) on the bank slope (1); and the microcomputer (7) is communicatively connected to the camera (65) to control its shooting cycle.

2. A river channel slope monitoring system based on three-dimensional binocular recognition according to claim 1, characterized in that: A rotating motor (62) is fixed in the support tube (61), and a rotating shaft (64) is coaxially fixed to the output shaft of the rotating motor (62), and one end of the rotating shaft (64) away from the rotating motor (62) is fixed to the body of the camera (65); the rotating motor (62) is electrically connected to the microcomputer (7).

3. A river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 2, characterized in that: A rotation angle sensor (63) is fixed on the rotating shaft (64), and the rotation angle sensor (63) is communicatively connected to the microcomputer (7).

4. A river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 1, characterized in that: The outer wall of the lens of the camera (65) is hinged with a rain sensor (67); a rain sensor (66) is fixed in the body of the camera (65); the rain sensor (67) and the rain sensor (66) are both communicatively connected to the microcomputer (7).

5. The river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 1 is characterized in that: The inner wall of the vertical pipe (41) is slidably connected to a slide rail (42), and the upper end of the slide rail (42) is fixed to the lower end of the slide pipe (45).

6. A river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 5, characterized in that: It also includes a telescopic motor (43), which is fixed to the outer wall of the vertical tube (41); the output shaft of the telescopic motor (43) is connected to the slide rail (42); and the telescopic motor (43) is electrically connected to the microcomputer (7).

7. The river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 1 is characterized in that: A magnetostrictive sensor (44) is fixed on the vertical pipe (41), and the sensing end of the magnetostrictive sensor (44) is located in the inner cavity of the sliding pipe (45) and is communicatively connected to the microcomputer (7).

8. The river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 1 is characterized in that: A base (5) is fixed to the lower end of the vertical pipe (41).

9. The river channel bank slope monitoring system based on three-dimensional binocular recognition according to claim 1 is characterized in that: It also includes a photovoltaic panel (3), wherein the photovoltaic panel (3) is electrically connected to the microcomputer (7); and the microcomputer (7) is communicatively connected to a remote control center (8).

10. A river channel slope monitoring method based on three-dimensional binocular recognition, characterized in that: The method for monitoring river channel slopes based on three-dimensional binocular recognition according to any one of claims 1 to 9 comprises the following steps: S1. Adjust the telescopic support part and the monitoring part to the standard position; S2. Adjust the camera posture according to the distance between the monitoring system and the bank slope and the scope of the monitoring area; S3, correct the camera's epipolar and distortion; S4. Calculate the displacement of the monitoring points within the monitoring area and generate a displacement curve for the monitoring period.

Images