Monocular vision deformation monitoring equipment

By monitoring the target displacement with a camera and combining deep learning and edge fitting algorithms, the problem of high-precision monitoring of monocular vision deformation monitoring equipment in complex backgrounds is solved, enabling automation and remote management.

CN223564968UActive Publication Date: 2025-11-18ANHUI ZHONGKEFENG INTELLIGENT TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202422789428.0
Authority / Receiving Office
CN · China
Patent Type
Utility models(China)
Current Assignee / Owner
Filing Date
2024-11-15
Publication Date
2025-11-18
Estimated Expiration
2034-11-15

AI Technical Summary

Technical Problem

Existing monocular vision deformation monitoring equipment struggles to achieve high-precision deformation monitoring in complex backgrounds, and the target installation requirements cannot meet actual needs.

Method used

The system uses a camera to monitor the displacement of the target, combines deep learning algorithms and edge least squares ellipse fitting algorithms for target identification, uses a cloud server for data processing and analysis, and utilizes photovoltaic cells and batteries for power to achieve high-precision automated monitoring.

Benefits of technology

Achieving high-precision target identification and positioning in complex environments reduces deformation value errors, allowing managers to remotely view on-site videos and make quick judgments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN223564968U_ABST
    Figure CN223564968U_ABST
Patent Text Reader

Abstract

The utility model relates to the technical field of machine vision deformation monitoring, and discloses monocular vision deformation monitoring equipment which comprises a first stand column and a second stand column, a photovoltaic cell is installed on the upper portion of the first stand column through a photovoltaic frame, and a camera is installed on the top of the first stand column. According to the monocular vision deformation monitoring equipment, the deformation condition of a monitoring area is reflected through the displacement of the camera vision monitoring target, high-precision automatic monitoring can be achieved, target recognition is completed through a deep learning algorithm, the recognition accuracy is high under the condition that the target imaging background is complex, and the recognition efficiency is high. High-precision positioning of the target can be realized by matching with an edge-based least square ellipse fitting algorithm, the error of a deformation value is reduced, and the cloud server performs data processing and analysis, so that a manager can remotely check a field video and quickly make a correct judgment according to a field condition.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The utility model relates to machine vision deformation monitoring technical field, concretely is a monocular vision deformation monitoring device. BACKGROUND

[0002] Now, with the continuous development of machine vision, the deformation monitoring technology based on machine vision has been widely applied in railway subgrade, bridge, building and other engineering monitoring. However, due to the complex target imaging background, the installation demand of reference target and other problems, sometimes it cannot meet the needs of deformation monitoring. UTILITY MODEL CONTENT

[0003] The utility model discloses a monocular vision deformation monitoring device, the monocular vision deformation monitoring device disclosed by the utility model reacts the deformation situation of monitoring area through the displacement of camera vision monitoring target, can realize high-precision automatic monitoring, uses the deep learning algorithm to complete the identification of target, and the identification accuracy is high under the condition that the target imaging background is complex, and the high-precision positioning of target can be realized by matching the least square ellipse fitting algorithm based on edge, reduces the error of deformation value, and the cloud server carries out data processing and analysis, is favorable for the remote viewing of on-site video of management personnel, makes correct judgment according to the on-site situation, to solve the problems in the above background technology.

[0004] To achieve the above object, the utility model provides the following technical scheme: a monocular vision deformation monitoring device, including first stand and second stand, the first stand upper portion is installed with photovoltaic cell through photovoltaic frame, the first stand top is installed with camera, the second stand top is installed with target through L-shaped pipe, the camera faces target and can gather target image.

[0005] Preferably, the first stand and the second stand bottom are all welded with mounting plate, the mounting plate four corners are all provided with screw hole and are installed on the ground through screw hole and screw.

[0006] Preferably, the first stand middle part is installed with equipment box.

[0007] Preferably, the second stand lower part is installed with battery, and the electric signal output end of the photovoltaic cell is connected with the electric signal input end of the battery through electric wire.

[0008] Preferably, the photovoltaic cell front side faces upwards.

[0009] Preferably, the target front side is provided with square mark area and circular mark area, and the circular mark area is located at the center position of the square mark area.

[0010] Compared with the prior art, the utility model has the beneficial effects that:

[0011] The monocular visual deformation monitoring equipment disclosed by the utility model reflects the deformation condition of the monitoring area through the displacement of the target monitored by the camera vision, can realize high-precision automatic monitoring, uses the deep learning algorithm to complete the identification of the target, has high identification accuracy in the case that the imaging background of the target is complex, can realize high-precision positioning of the target by matching the least square ellipse fitting algorithm based on the edge, reduces the error of the deformation value, the cloud server carries out data processing and analysis, is favorable for the management personnel to remotely view the on-site video, quickly makes correct judgment according to the on-site condition, and solves the problem that the existing monocular visual deformation monitoring equipment cannot meet the requirement of deformation monitoring sometimes. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 It is the whole structure schematic diagram of the utility model;

[0013] Figure 2 It is the whole structure schematic diagram of the utility model.

[0014] In the drawing: 1, first stand; 2, photovoltaic frame; 3, photovoltaic cell; 4, camera; 5, battery; 6, equipment box; 7, mounting plate; 8, screw; 9, second stand; 10, L-shaped pipe; 11, target. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the utility model will be clearly and completely described below with reference to the drawings in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model and not all the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the utility model.

[0016] Please refer to Figure 1 and Figure 2 , a kind of monocular visual deformation monitoring equipment in the drawing, including first stand 1 and second stand 9, photovoltaic cell 3 is installed on first stand 1 upper portion by photovoltaic frame 2, camera 4 is installed on the top of first stand 1, target 11 is installed on the top of second stand 9 by L-shaped pipe 10, camera 4 faces target 11 and can collect image at target 11, the monocular visual deformation monitoring equipment disclosed by the utility model reflects the deformation condition of the monitoring area by the displacement of target 11 monitored by camera 4 vision, can realize high-precision automatic monitoring, uses the deep learning algorithm to complete the identification of target 11, has high identification accuracy in the case that the imaging background of target 11 is complex, can realize high-precision positioning of target 11 by matching the least square ellipse fitting algorithm based on the edge, reduces the error of the deformation value, cloud server carries out data processing and analysis, is favorable for the management personnel to remotely view the on-site video, quickly makes correct judgment according to the on-site condition.

[0017] Further, the first column 1 and the second column 9 are welded with the mounting plate 7 at the bottom, the mounting plate 7 is provided with screw holes at four corners and is installed on the ground through the screw holes and the screws 8, which is convenient for installation; further, the equipment box 6 is installed in the middle of the first column 1; further, the storage battery 5 is installed at the lower part of the second column 9, the electric signal output end of the photovoltaic cell 3 is connected with the electric signal input end of the storage battery 5 through the electric wire, which is convenient for power supply; further, the photovoltaic cell 3 faces upward, which is convenient for collecting solar energy; further, the square mark area and the circular mark area are arranged on the front surface of the target 11, and the circular mark area is located at the center position of the square mark area.

[0018] In the scheme, in use, a pit with a size of 600*600*600mm is dug at a specified position, a formwork is erected, and a vertical rod cage pre-buried part is fixed. Then, concrete is poured and vibrated uniformly, and after the concrete solidifies, the first column 1 and the second column 9 can be installed, the photovoltaic frame 2, the camera 4 and the equipment box 6 are installed on the first column 1 through corresponding supports, the cable is arranged to pass out of the vertical rod, the vertical rod is erected and fixed on the cage pre-buried in the concrete in advance, the screws 8 are tightened, the target 11 is fixed on the second column 9 through the L-shaped pipe 10, the storage battery 5 is installed at the lower part of the second column 9, the front surface of the camera 4 is aligned with the target 11, so that the camera 4 can collect the image of the target 11, the world coordinates of the center point of the target 11 are calculated, the first frame image is taken as a reference to solve the relative deformation of the target 11, and the on-site equipment of the monitoring point is powered by the solar photovoltaic cell 3 and the storage battery 5, the solar photovoltaic cell 3 converts solar energy into electric energy and charges the storage battery 5 at the same time, and then the storage battery 5 is used to supply power to the system to form a stable power supply system.

[0019] It should be noted that, in the present document, the terms such as first and second, etc., are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device.

[0020] Although the embodiments of the present application have been shown and described, it should be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A monocular visual deformation monitoring device comprising a first column (1) and a second column (9), characterized in that: The first column (1) upper part is provided with photovoltaic cell (3) through photovoltaic frame (2), the first column (1) top is provided with camera (4), the second column (9) top is provided with target (11) through L-shaped pipe (10), the camera (4) faces target (11) and can collect the image at target (11).

2. The monocular visual deformation monitoring device of claim 1, wherein: The first column (1) and second column (9) bottom are all welded with mounting plate (7), the mounting plate (7) four corners are all provided with screw hole and are installed on the ground through screw hole and screw (8).

3. The monocular visual deformation monitoring device of claim 1, wherein: The first column (1) middle part is provided with equipment box (6).

4. The monocular visual deformation monitoring device of claim 1, wherein: The second column (9) lower part is provided with battery (5), and the electric signal output end of the photovoltaic cell (3) is connected with the electric signal input end of the battery (5) through the electric wire.

5. The monocular visual deformation monitoring device of claim 1, wherein: The photovoltaic cell (3) front face faces upward.

6. The monocular visual deformation monitoring device of claim 1, wherein: The target (11) front face is provided with square mark area and circular mark area, and the circular mark area is located at the center position of the square mark area.