A belt conveyor inspection robot positioning method and system

Abstract

The invention provides a belt conveyor inspection robot positioning method and system, the method comprising the following steps: collecting a field image by a camera, setting a road section in which field positioning marks are evenly arranged in the image as a uniform mark section, and setting a road section in which field positioning marks are unevenly arranged in the image as a non-uniform mark section; for the uniform mark section, identifying positioning information by a step-accumulation method; for the non-uniform mark section, identifying positioning information by a method of recording the number of feature recognitions; outputting a positioning result; the system comprising a camera unit, a judgment unit, a step-accumulation positioning unit and a feature recognition positioning unit, the camera unit is respectively connected to the judgment unit and the feature recognition positioning unit, the judgment unit is respectively connected to the step-accumulation positioning unit and the feature recognition positioning unit; the uniform and non-uniform arrangement of field markings are respectively processed, computing resources can be effectively saved, positioning result errors are reduced, and the system is suitable for long-term application in the field.

Description

Technical Field

[0001] The present invention relates to the technical field of belt conveyor inspection, and in particular to a belt conveyor inspection robot positioning method and system. Background Art

[0002] At present, belt conveyors are widely used in the fields of electricity, steel, coal, water conservancy, chemical industry, metallurgy, building materials, etc. At the same time, the belt conveyor system is developing towards large-scale directions with high belt speed, high power, large capacity and long distance.

[0003] In recent years, as various equipment in belt conveyors have become more complex, the requirements for real-time monitoring and inspection have also increased. At present, manual inspection is mainly adopted. However, since the equipment may be in a harsh working environment, manual inspection is dangerous, and manual monitoring may cause human errors. At the same time, the labor cost continues to rise, making it increasingly necessary for machines to replace manual inspections. The positioning system, as an indispensable key system in the inspection robot, is crucial to the accuracy of the inspection. Currently, the commonly used positioning methods include digital matching, QR code recognition, and step accumulation. Among them, the amount of data required for digital matching is huge, and it is easy to cause misidentification due to noise interference; the QR code method is easily damaged or detached in the field environment for a long time, and the life is short; and the step accumulation method has a high accuracy for uniformly arranged positioning information, but it has a low accuracy for non-uniformly arranged positioning information and is prone to errors. Summary of the invention

[0004] The present invention aims to at least solve one of the technical problems in the prior art that the amount of data calculation is large and the step-accumulation method is difficult to apply to the positioning situation where the on-site signs are unevenly arranged, resulting in inaccurate positioning and causing large errors.

[0005] To this end, a first aspect of the present invention provides a positioning method for a belt conveyor inspection robot.

[0006] A second aspect of the present invention provides a belt conveyor inspection robot positioning system.

[0007] The present invention provides a belt conveyor inspection robot positioning method, comprising the following steps:

[0008] S1, collecting on-site images through a camera, setting the road section where the on-site positioning marks are evenly arranged in the image as the evenly marked section, and setting the road section where the on-site positioning marks are unevenly arranged in the image as the unevenly marked section;

[0009] S2. For the uniformly marked segment, the positioning information is identified by a step-by-step accumulation method;

[0010] S3. For the unevenly marked segments, the positioning information is identified by recording the number of feature recognition times;

[0011] S4, output positioning results;

[0012] The method for recording the number of feature recognition times in S3 includes the following steps:

[0013] S31, establishing a feature template for identifying on-site identification;

[0014] S32, establishing a defense area according to the position of the on-site positioning mark in the image;

[0015] S33. Set a number of reference lines within the defense area;

[0016] S34, starting counting from the first reference line that the robot passes through, when passing through the reference line of the defense area corresponding to the next positioning mark, the count is increased by one; and this count is used as positioning information.

[0017] A belt conveyor inspection robot positioning method according to the above technical solution of the present invention may also have the following additional technical features:

[0018] In the above technical solution, each positioning mark in S32 corresponds to a defense area.

[0019] In the above technical solution, the reference line includes a positive direction reference line and a negative direction reference line, and the positive direction reference line and the negative direction reference line are symmetrically arranged on both sides of the center line of the defense area.

[0020] In the above technical solution, in step S34, before the robot passes through the first reference line, it is also necessary to determine the moving direction of the robot.

[0021] In the above technical solution, the direction of movement from the positive direction reference line to the negative direction reference line is stipulated as the positive direction of the robot's movement. When moving in the positive direction, the positioning information is increased by one each time a positive direction reference line is passed; when moving in the negative direction opposite to the positive direction, the positioning information is decreased by one each time a negative direction reference line is passed.

[0022] In any of the above technical solutions, the feature template includes several groups or several pixel points of the on-site identification.

[0023] In any of the above technical solutions, the method for determining whether the on-site markings of a road section are uniform is:

[0024] Compare the distance between the on-site sign and the previous on-site sign and the distance between the on-site sign and the next on-site sign; if the distances between any two adjacent on-site signs in the road section are equal, the road section is a uniformly marked section; otherwise, the road section is an unevenly marked section.

[0025] The invention also provides a belt conveyor inspection robot positioning system.

[0026] A belt conveyor inspection robot positioning system provided by the present invention comprises a camera unit, a judgment unit, a step-accumulation positioning unit and a feature recognition positioning unit, wherein the camera unit is connected to the judgment unit and the feature recognition positioning unit respectively, and the judgment unit is connected to the step-accumulation positioning unit and the feature recognition positioning unit respectively;

[0027] Wherein, the camera unit is used to obtain on-site images of the inspection location of the inspection robot;

[0028] The judgment unit is used to divide the robot inspection route into sections and judge whether the positioning marks in the section are evenly arranged. If they are evenly arranged, a signal is transmitted to the step-accumulation positioning unit to start the step-accumulation positioning unit for positioning; if they are unevenly arranged, a signal is transmitted to the feature recognition positioning unit to start the feature recognition positioning unit for positioning;

[0029] The step-accumulation positioning unit is used to calculate the positioning information by step-accumulation method;

[0030] The feature recognition and positioning unit is used to record the number of feature recognition times as positioning information.

[0031] A belt conveyor inspection robot positioning method according to the above technical solution of the present invention may also have the following additional technical features:

[0032] In the above technical solution, the feature recognition and positioning unit adopts a method as described in any one of the above technical solutions to perform robot positioning.

[0033] In summary, due to the adoption of the above technical features, the beneficial effects of the present invention are:

[0034] A belt conveyor inspection robot positioning method and system adopting the above scheme can realize separate processing of uniform and non-uniform layout of on-site signs. Compared with the existing technology, it can effectively save computing resources and reduce the error of positioning results. It has a simple structure, reasonable algorithm, high positioning accuracy and high positioning efficiency, and is suitable for long-term application in field environments.

[0035] Additional aspects and advantages of the present invention will become apparent from the following description or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0037] Figure 1is a flow chart of a belt conveyor inspection robot positioning method according to an embodiment of the present invention;

[0038] Figure 2 It is a flow chart of a method for recording the number of feature recognition times in a belt conveyor inspection robot positioning method according to an embodiment of the present invention;

[0039] Figure 3 It is a flowchart of a belt conveyor inspection robot positioning method according to an embodiment of the present invention;

[0040] Figure 4 It is a flowchart of a method for recording the number of feature recognition times in a belt conveyor inspection robot positioning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0043] Refer to the following Figures 1 to 4 A belt conveyor inspection robot positioning method provided according to some embodiments of the present invention is described.

[0044] Some embodiments of the present application provide a positioning method for a belt conveyor inspection robot.

[0045] like Figures 1 to 4 As shown, the first embodiment of the present invention proposes a belt conveyor inspection robot positioning method, comprising the following steps:

[0046] S1, collecting on-site images through a camera, setting the road section where the on-site positioning marks are evenly arranged in the image as the evenly marked section, and setting the road section where the on-site positioning marks are unevenly arranged in the image as the unevenly marked section;

[0047] Compare the distance between the on-site sign and the previous on-site sign and the distance between the on-site sign and the next on-site sign; if the distances between any two adjacent on-site signs in the road section are equal, the road section is a uniformly marked section; otherwise, the road section is an unevenly marked section.

[0048] S2. For the uniformly marked segment, the positioning information is identified by a step-by-step accumulation method;

[0049] S3. For the unevenly marked segments, the positioning information is identified by recording the number of feature recognition times;

[0050] The method for recording the number of feature recognition times comprises the following steps:

[0051] S31, establishing a feature template for identifying on-site identification;

[0052] The feature template includes several groups or several pixel points of the site identification.

[0053] S32, establishing a defense area according to the position of the on-site positioning mark in the image;

[0054] Each positioning mark corresponds to a defense area;

[0055] S33. Set a number of reference lines within the defense area;

[0056] The reference lines include a positive direction reference line and a negative direction reference line, and the positive direction reference line and the negative direction reference line are symmetrically arranged on both sides of the center line of the defense area.

[0057] S34, determine the moving direction of the robot, start counting from the first reference line passed by the robot, and when passing the reference line of the defense area corresponding to the next positioning mark, the count is increased by one; and this count is used as the positioning information.

[0058] It is stipulated that the direction of movement from the positive direction reference line to the negative direction reference line is the positive direction of the robot's movement. When moving in the positive direction, the positioning information is increased by one each time a positive direction reference line is passed; when moving in the negative direction opposite to the positive direction, the positioning information is decreased by one each time a negative direction reference line is passed.

[0059] S4. Output the positioning result.

[0060] The second embodiment of the present invention proposes a belt conveyor inspection robot positioning method, and based on the first embodiment, as Figures 1 to 4As shown, the scene image is collected by the camera, and the positioning mark is judged in sections whether it is evenly arranged. If it is evenly arranged, the positioning information is calculated by step accumulation; if it is unevenly arranged, the number of feature recognitions is recorded as the positioning information; wherein, the method of recording the number of feature recognitions is as follows: define the feature template, set the defense area according to the position of the positioning mark in the image, set two vertical reference lines in the defense area and the reference lines whose loudness is symmetrical with the center line of the defense area, the reference line on the left side of the center line of the defense area is defined as the positive direction reference line, and the reference line on the right side of the center line of the defense area is defined as the negative direction reference line; when the robot moves from right to left, the pre-defined feature template recognizes the actual position corresponding to the positive direction reference line when the robot passes through, and starts counting at this time, and uses this count as the positioning information. When the pre-defined feature template recognizes the actual position corresponding to the positive direction reference line in the defense area corresponding to the next scene positioning mark again, 1 is added to the original count as the new positioning information, output and display, and continue to move until the inspection of the unevenly arranged section of the scene mark is completed. When the robot moves from right to left as the positive direction, moving from left to right is the negative direction. When the pre-defined feature template identifies the actual position corresponding to the negative direction reference line, the original count is subtracted by 1 as the new positioning information, which is output and displayed, and the robot continues to move forward.

[0061] The third embodiment of the present invention provides a belt conveyor inspection robot positioning system, and based on any of the above embodiments, as Figures 1 to 4 As shown, it includes a camera unit, a judgment unit, a step-accumulation positioning unit and a feature recognition positioning unit, wherein the camera unit is connected to the judgment unit and the feature recognition positioning unit respectively, and the judgment unit is connected to the step-accumulation positioning unit and the feature recognition positioning unit respectively;

[0062] Wherein, the camera unit is used to obtain on-site images of the inspection location of the inspection robot;

[0063] The judgment unit is used to divide the robot inspection route into sections and judge whether the positioning marks in the section are evenly arranged. If they are evenly arranged, a signal is transmitted to the step-accumulation positioning unit to start the step-accumulation positioning unit for positioning; if they are unevenly arranged, a signal is transmitted to the feature recognition positioning unit to start the feature recognition positioning unit for positioning;

[0064] The step-accumulation positioning unit is used to calculate the positioning information by step-accumulation method;

[0065] The feature recognition and positioning unit is used to record the number of feature recognition times as positioning information.

[0066] The feature recognition and positioning unit uses the method described in any one of the above embodiments to perform robot positioning.

[0067] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0068] Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A belt conveyor inspection robot positioning method, characterized in that: The following steps are involved: S1, collecting on-site images through a camera, setting the road section where the on-site positioning marks are evenly arranged in the image as the evenly marked section, and setting the road section where the on-site positioning marks are unevenly arranged in the image as the unevenly marked section; S2. For the uniformly marked segment, the positioning information is identified by a step-by-step accumulation method; S3. For the unevenly marked segments, the positioning information is identified by recording the number of feature recognition times; S4, output positioning results; The method for recording the number of feature recognition times in S3 includes the following steps: S31, establishing a feature template for identifying on-site identification; S32, establishing a defense area according to the position of the on-site positioning mark in the image; S33. Set a number of reference lines within the defense area; S34, starting counting from the first reference line that the robot passes through, when passing through the reference line of the defense area corresponding to the next positioning mark, the count is increased by one; and this count is used as positioning information.

2. A belt conveyor inspection robot positioning method according to claim 1, characterized in that: Each positioning mark in S32 corresponds to a defense area.

3. A belt conveyor inspection robot positioning method according to claim 2, characterized in that: The reference lines include a positive direction reference line and a negative direction reference line, and the positive direction reference line and the negative direction reference line are symmetrically arranged on both sides of the center line of the defense area.

4. A belt conveyor inspection robot positioning method according to claim 3, characterized in that: In step S34, before the robot passes the first reference line, it is necessary to determine the moving direction of the robot.

5. A belt conveyor inspection robot positioning method according to claim 4, characterized in that: It is stipulated that the direction of movement from the positive direction reference line to the negative direction reference line is the positive direction of the robot's movement. When moving in the positive direction, the positioning information is increased by one each time a positive direction reference line is passed; when moving in the negative direction opposite to the positive direction, the positioning information is decreased by one each time a negative direction reference line is passed.

6. A belt conveyor inspection robot positioning method according to any one of claims 1 to 5, characterized in that: The feature template includes several groups or several pixel points of the site identification.

7. A belt conveyor inspection robot positioning method according to any one of claims 1 to 5, characterized in that: The method to determine whether the road section on-site markings are uniform is: Compare the distance between the on-site sign and the previous on-site sign and the distance between the on-site sign and the next on-site sign; if the distances between any two adjacent on-site signs in the road section are equal, the road section is a uniformly marked section; otherwise, the road section is an unevenly marked section.

8. A belt conveyor inspection robot positioning system, characterized in that: The belt conveyor inspection robot positioning method applied to any one of claims 1 to 6, the system comprising a camera unit, a judgment unit, a step-accumulation positioning unit and a feature recognition positioning unit, the camera unit is respectively connected to the judgment unit and the feature recognition positioning unit, the judgment unit is respectively connected to the step-accumulation positioning unit and the feature recognition positioning unit; Wherein, the camera unit is used to obtain on-site images of the inspection location of the inspection robot; The judgment unit is used to divide the robot inspection route into sections and judge whether the positioning marks in the section are evenly arranged. If they are evenly arranged, a signal is transmitted to the step-accumulation positioning unit to start the step-accumulation positioning unit for positioning; if they are unevenly arranged, a signal is transmitted to the feature recognition positioning unit to start the feature recognition positioning unit for positioning; The step-accumulation positioning unit is used to calculate the positioning information by step-accumulation method; The feature recognition and positioning unit is used to record the number of feature recognition times as positioning information.

Images