WO2023160188A1 - 一种cctv管道在线检测系统 - Google Patents

一种cctv管道在线检测系统 Download PDF

Info

Publication number
WO2023160188A1
WO2023160188A1 PCT/CN2022/140686 CN2022140686W WO2023160188A1 WO 2023160188 A1 WO2023160188 A1 WO 2023160188A1 CN 2022140686 W CN2022140686 W CN 2022140686W WO 2023160188 A1 WO2023160188 A1 WO 2023160188A1
Authority
WO
WIPO (PCT)
Prior art keywords
pipeline
image
subunit
result
preset
Prior art date
Application number
PCT/CN2022/140686
Other languages
English (en)
French (fr)
Inventor
朱艳
韦玉祥
胡彩浩
Original Assignee
盐城笃诚建设有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 盐城笃诚建设有限公司 filed Critical 盐城笃诚建设有限公司
Priority to US18/197,132 priority Critical patent/US20230281782A1/en
Publication of WO2023160188A1 publication Critical patent/WO2023160188A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/954—Inspecting the inner surface of hollow bodies, e.g. bores
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/50—Constructional details
    • H04N23/555—Constructional details for picking-up images in sites, inaccessible due to their dimensions or hazardous conditions, e.g. endoscopes or borescopes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30184—Infrastructure

Definitions

  • the invention relates to the technical fields of CCTV pipelines, detection robots and artificial intelligence, in particular to an online detection system for CCTV pipelines.
  • a detection system for urban underground pipe network is provided with an adjustable tire diameter, which can meet the detection of sewage pipes of different diameters and reduce the detection cost.
  • the control box realizes the detection of sewage pipes with different diameters, improves the versatility of adjusting the wheels, and reduces the overall manufacturing cost and detection cost, but only modifies the structure of the detection robot itself.
  • the present invention provides a CCTV pipeline on-line detection system to solve the above problems in the background technology.
  • the present invention provides a CCTV pipeline online detection system, including a control terminal, a detection robot and a CCTV pipeline detection system adapted to the detection robot, and the CCTV pipeline detection system is installed inside the detection robot; wherein,
  • the control terminal is electrically connected to the detection robot and the adapted CCTV pipeline detection system through the control system, and the control system is installed inside the preset control terminal.
  • the CCTV pipeline detection system includes a GTR8600 monitoring module, a driving module and a power driving module; wherein,
  • the GTR8600 monitoring module is installed on the detection robot
  • the drive control module drives the drive control device to move through the control terminal
  • a power drive system is provided inside the power drive device, and the power drive system is controlled by the control system to control the drive device of the power drive system to move normally.
  • the GTR8600 monitoring module includes an industry-level high-resolution color camera unit, a motion posture monitoring unit, a video recording processing terminal, and a transmission unit; wherein,
  • the industry-level high-resolution color camera unit is used to collect external images, and obtain resolution images through the external images;
  • the motion posture monitoring unit is used to identify and monitor the internal conditions of the pipeline in real time through the resolution image, and infer the motion posture of the detection robot through the monitoring internal conditions of the pipeline, and determine the inference result;
  • the camera recording processing terminal is used to record and process the collected external images and the corresponding internal conditions of the pipeline, and determine the recording results;
  • the transmission unit is used for transmitting the inference result and the recording result to the control terminal.
  • the industry-level high-resolution color camera unit includes:
  • Image acquisition sub-unit used to collect the external image in the pipeline in real time through the preset camera equipment
  • Recognition image subunit used to perform feature extraction and feature recognition on the external image based on a preset color image space conversion mechanism, and obtain a recognition image;
  • Resolving image subunit used to perform high-resolution on the recognition image based on a preset high-resolution reconstruction mechanism to obtain a resolving image.
  • the motion posture monitoring unit includes:
  • Offset angle subunit used to receive the resolution image, transmit the resolution image to a preset balance detection mechanism, and calculate the offset angle of the resolution image;
  • Detecting robot status subunit used for real-time identification and monitoring of detecting robot status through the offset angle;
  • Status information subunit used to receive resolution images according to a preset cycle, record the internal status of the pipeline, and generate corresponding status information through the status of the robot and the internal status of the pipeline;
  • Inference subunit used to extract the distinguishing feature points of the distinguishing image based on the status information, transmit the distinguishing feature points to a preset big data center for analysis, infer the motion posture of the detection robot, and determine the inference result.
  • the camera recording processing terminal includes:
  • Acquisition result unit used for real-time acquisition of external images and corresponding internal conditions of the pipeline to determine the acquisition results
  • Judging unit used for judging in real time whether there is abnormality in the internal condition of the pipeline based on the collection result, and determining the judgment result;
  • Abnormality-free unit used to record the corresponding external image when the judgment result is normal, compress the recorded external image, upload it to the preset cloud storage for storage, and determine the normal recording result;
  • Abnormal unit used to obtain the internal status of the status pipeline when the judgment result is abnormal, based on the preset time range, retrieve the historical normal record results from the preset cloud storage library, and compare the internal status of the status pipeline with the status pipeline The internal conditions are transmitted to the big data center for analysis and recording, and the abnormal recording results are determined;
  • Early warning unit used to transmit the abnormal record results to the control terminal in real time for early warning
  • Recording result unit used to determine the recording result based on the normal recording result and the abnormal recording result.
  • the status information subunit includes:
  • Image processing subunit used to receive the resolution image according to a preset period, perform grayscale processing and normalization processing on the image pixels of the resolution image, and determine the processing image;
  • Partial image subunit used to stretch and segment the processed image to determine a partial image
  • Recognition result subunit used to identify the type of pipeline damage through the partial image, and determine the recognition result
  • Statistical subunit used to count the damaged position of the pipeline and the corresponding damaged type of the pipeline in the preset detection area based on the identification result;
  • Pipeline internal condition subunit used to determine the internal condition of the pipeline based on the damaged location of the pipeline and the corresponding type of pipeline damage;
  • Status information subunit used to obtain the receiving time corresponding to the internal status of the pipeline, trace the corresponding robot status through the receiving time, and generate corresponding status information;
  • the inference subunit includes:
  • the status information type subunit used to transmit the status information to a preset type filter for classification, and determine the status information type;
  • Classification subunit used for extracting the distinguishing feature points of the distinguishing image through the type of status information, and at the same time classifying the distinguishing feature points to determine the classification result;
  • D(S) represents the classification result after classifying the status information types
  • g i represents the distinguishing feature points of the i-th status information type
  • R(g i ) represents the main points of the distinguishing feature points of the i-th status information type.
  • Action model subunit used to transmit the classification results and distinguishing feature points to a preset big data center for analysis, and construct a corresponding action model
  • Inference result subunit used to infer the movement posture of the detection robot based on the action model, and determine the inference result.
  • the drive control device is provided with a drive system and an obstacle avoidance system inside, and the drive system controls the drive control device through the control system, so that the drive control device starts to generate power, and drives the drive control the device moves;
  • the obstacle avoidance system receives the control signal of the control system, and drives the control device to advance and avoid obstacles.
  • a power drive system is provided inside the power drive device, and the power drive system is controlled by a control system to control the drive device of the power drive system to move normally.
  • the embodiment of the present invention provides an online inspection system for CCTV pipelines, including a control terminal, a detection robot and a CCTV pipeline detection system adapted to the detection robot.
  • the CCTV pipeline detection system is installed inside the detection robot; the detection robot is running During the process, the pipeline is inspected and checked, and the inspection robot is controlled through the control terminal at the outer end, which can carry out key or non-key inspections on different areas of the pipeline to reduce the inspection cost.
  • the control terminal is electrically connected to the detection robot and the adapted CCTV pipeline detection system through the control system.
  • the control system is installed inside the preset control terminal to control the robot.
  • This technical solution provides a detection method for a CCTV pipeline online detection robot.
  • the detection robot is controlled to check the urban pipeline. Since the cost of the detection robot is relatively high, real-time measurement can be carried out in the pipeline, thereby reducing Detecting robot damage, due to the large and complex urban pipelines and changing structures, manual inspection is not only time-consuming and labor-intensive, but also wastes time and cost.
  • the time cost of staff can be reduced and work efficiency can be improved.
  • Fig. 1 is a kind of CCTV pipeline online detection system block diagram in the embodiment of the present invention
  • Fig. 2 is a block diagram of a CCTV pipeline online detection system in an embodiment of the present invention
  • Fig. 3 is a block diagram of a CCTV pipeline online detection system in an embodiment of the present invention.
  • an embodiment of the present invention provides an online CCTV pipeline detection system, including a control terminal, a detection robot, and a CCTV pipeline detection system adapted to the detection robot, and the CCTV pipeline detection system is installed on the Detect the inside of the robot;
  • the control terminal is electrically connected to the detection robot and the adapted CCTV pipeline detection system through the control system, and the control system is installed inside the preset control terminal.
  • An embodiment of the present invention provides a CCTV pipeline online detection system, including a control terminal, a detection robot and a CCTV pipeline detection system adapted to the detection robot.
  • the CCTV pipeline detection system is installed inside the detection robot; the detection robot is running During the process, the pipeline is inspected and checked, and the inspection robot is controlled through the control terminal at the outer end, which can carry out key or non-key inspections on different areas of the pipeline to reduce the inspection cost.
  • the control terminal is electrically connected to the detection robot and the adapted CCTV pipeline detection system through the control system.
  • the control system is installed inside the preset control terminal to control the robot.
  • This technical solution provides a detection method for a CCTV pipeline online detection robot.
  • the detection robot is controlled to check the urban pipeline. Since the cost of the detection robot is relatively high, real-time measurement can be carried out in the pipeline, thereby reducing Detecting robot damage, due to the large and complex urban pipelines and changing structures, manual inspection is not only time-consuming and labor-intensive, but also wastes time and cost.
  • the time cost of staff can be reduced and work efficiency can be improved.
  • the CCTV pipeline detection system includes a GTR8600 monitoring module, a driving module and a power driving module; wherein,
  • the GTR8600 monitoring module is installed on the detection robot
  • the drive control module drives the drive control device to move through the control terminal
  • a power drive system is provided inside the power drive device, and the power drive system is controlled by the control system to control the drive device of the power drive system to move normally.
  • the CCTV pipeline detection system of this technical solution includes a GTR8600 monitoring module, a driving module and a power driving module; Monitoring of pipelines, timely investigation of hidden dangers of pipelines in cities and enterprises, the drive control module drives the drive control device to move through the control terminal, through the control terminal, a power drive system is installed inside the power drive device of the detection robot, through the control system Operate the power drive system and control the power drive system drives for routine movement.
  • This technical solution not only improves the obstacle avoidance ability of the robot, but also reduces the damage of the robot through the control of the control terminal instead of the routine setting route. At the same time, it can equip the detection robot with simple functions, and the pipeline can be easily cleaned. For example, the drive wheel of the robot crushes the horizontally blocked sticks in the pipeline, making it easier to dredge the pipeline.
  • the GTR8600 monitoring module includes an industry-level high-resolution color camera unit, a motion posture monitoring unit, a video recording processing terminal, and a transmission unit; wherein,
  • the industry-level high-resolution color camera unit is used to collect external images, and obtain resolution images through the external images;
  • the motion posture monitoring unit is used to identify and monitor the internal conditions of the pipeline in real time through the resolution image, and infer the motion posture of the detection robot through the monitoring internal conditions of the pipeline, and determine the inference result;
  • the camera recording processing terminal is used to record and process the collected external images and the corresponding internal conditions of the pipeline, and determine the recording results;
  • the transmission unit is used for transmitting the inference result and the recording result to the control terminal.
  • the GTR8600 monitoring module of this technical solution includes an industry-level high-resolution color camera unit, a motion posture monitoring unit, a camera recording processing terminal, and a transmission unit; wherein, the industry-level high-resolution color camera unit is used to collect external images, and through the external Image, to obtain a resolution image; the motion posture monitoring unit is used to identify and monitor the internal condition of the pipeline in real time through the resolution image, and infer the motion posture of the detection robot through the monitoring internal condition of the pipeline to determine the inference result;
  • the camera recording processing terminal is used to collect the collected external images and the corresponding internal conditions of the pipeline;
  • the transmission unit is used to transmit the inference results to the control terminal, and comprehensively analyze the state analysis of the robot and the external environment. What's going on inside the pipeline and whether it needs repairs, thus providing accurate condition information.
  • the industry-level high-resolution color camera unit includes:
  • Image acquisition sub-unit used to collect the external image in the pipeline in real time through the preset camera equipment
  • Recognition image subunit used to perform feature extraction and feature recognition on the external image based on a preset color image space conversion mechanism, and obtain a recognition image;
  • Resolving image subunit used to perform high-resolution on the recognition image based on a preset high-resolution reconstruction mechanism to obtain a resolving image.
  • the image acquisition sub-unit is used to collect the external image in the pipeline in real time through the preset camera equipment; the influence of the pipeline is collected in real time, and the image recognition sub-unit is used based on the preset
  • the color image space conversion mechanism is used to perform feature extraction and feature recognition on the external image, obtain the recognition image, and provide original data for the classification of different types of problems in the pipeline through the recognition image
  • the resolution image subunit is used for high-resolution based on preset
  • the high-resolution reconstruction mechanism performs high-resolution on the identification image to obtain a high-resolution image, and the high-resolution image can finely distinguish the size and position of hidden pipeline hazards in the image.
  • the motion posture monitoring unit includes:
  • Offset angle subunit used to receive the resolution image, transmit the resolution image to a preset balance detection mechanism, and calculate the offset angle of the resolution image;
  • Detecting robot status subunit used for real-time identification and monitoring of detecting robot status through the offset angle;
  • Status information subunit used to receive resolution images according to a preset cycle, record the internal status of the pipeline, and generate corresponding status information through the status of the robot and the internal status of the pipeline;
  • Inference subunit used to extract the distinguishing feature points of the distinguishing image based on the status information, transmit the distinguishing feature points to a preset big data center for analysis, infer the motion posture of the detection robot, and determine the inference result.
  • the motion posture monitoring unit includes: an offset angle subunit: used to receive a resolution image, transmit the resolution image to a preset balance detection mechanism, and calculate the offset angle of the resolution image; pipeline Internal status subunit: used to identify and monitor the internal status of the pipeline in real time through the offset angle; status information subunit: used to record the internal status of the pipeline according to a preset cycle, and generate corresponding status information; the inference subunit A unit: for extracting the distinguishing feature points of the distinguishing image based on the status information, transmitting the distinguishing feature points to a preset big data center for analysis, inferring the motion posture of the detection robot, and determining the inference result,
  • the technical solution judges the damage type of the pipeline comprehensively by distinguishing the image, obtaining the image information and the robot information, so as to prevent the pipeline from being repaired for a long time, causing the pipeline to cause urban hidden dangers.
  • Embodiment 6 is a diagrammatic representation of Embodiment 6
  • the camera recording processing terminal includes:
  • Acquisition result unit used for real-time acquisition of external images and corresponding internal conditions of the pipeline to determine the acquisition results
  • Judging unit used to judge in real time whether the internal condition of the pipeline is abnormal based on the collection result, and determine the judgment result;
  • Abnormality-free unit used to record the corresponding external image when the judgment result is normal, compress the recorded external image, upload it to the preset cloud storage for storage, and determine the normal recording result;
  • Abnormal unit used to obtain the internal status of the status pipeline when the judgment result is abnormal, based on the preset time range, retrieve the historical normal record results from the preset cloud storage library, and compare the internal status of the status pipeline with the status pipeline The internal conditions are transmitted to the big data center for analysis and recording, and the abnormal recording results are determined;
  • Early warning unit used to transmit the abnormal record results to the control terminal in real time for early warning
  • Recording result unit used to determine the recording result based on the normal recording result and the abnormal recording result.
  • the video recording processing terminal of the technical solution includes a collection result unit: used to determine the collection result based on the external image and the corresponding internal condition of the pipeline collected in real time; a judging unit: used to judge the inside of the pipeline in real time based on the collection result Whether the situation is abnormal, determine the judgment result; no abnormality unit: used to record the corresponding external image when the judgment result is normal, compress the recorded external image, and upload it to the preset cloud storage library for storage, Determine the normal record result; abnormal unit: used to obtain the internal status of the state pipeline when the judgment result is abnormal, based on the preset time range, retrieve the historical normal record result from the preset cloud storage library, and store the state pipeline Internal condition and state The internal condition of the pipeline is transmitted to the big data center for analysis and recording, and the abnormal record result is determined; early warning unit: used to transmit the abnormal record result to the control terminal in real time for early warning; record result unit: used to pass the normal record Results and abnormal record results, determine the record results, roughly find out the situation in the pipeline through the initial
  • Embodiment 7 is a diagrammatic representation of Embodiment 7:
  • the status information subunit includes:
  • Image processing subunit used to receive the resolution image according to the preset cycle, perform grayscale processing and normalization processing on the image pixels of the resolution image, and determine the processing image;
  • Partial image subunit used to stretch and segment the processed image to determine a partial image
  • Recognition result subunit used to identify the type of pipeline damage through the partial image, and determine the recognition result
  • Statistical subunit used to count the damaged position of the pipeline and the corresponding damaged type of the pipeline in the preset detection area based on the identification result;
  • Pipeline internal condition subunit used to determine the internal condition of the pipeline based on the damaged location of the pipeline and the corresponding type of pipeline damage;
  • Status information subunit used to obtain the receiving time corresponding to the internal status of the pipeline, trace the corresponding robot status through the receiving time, and generate corresponding status information.
  • the status information subunit of the technical solution includes: the processing image subunit is used to receive the resolution image according to a preset cycle, perform grayscale processing and normalization processing on the image pixels of the resolution image, and determine the processing image, because The light in the pipeline is dark and the noise is relatively large, so noise processing is required to prevent the image from being unclear when the image is just received.
  • the local image subunit is used to stretch and segment the processed image to determine the partial image. For image recognition, The background area of the image is easy to identify, but where the image needs to be identified, it needs to be distinguished.
  • the identification result subunit is used to identify the type of pipeline damage through the partial image, and determine the identification result.
  • the pipeline has silt clogging, leakage, pipeline deformation, etc.
  • the statistics subunit is used to count the location of pipeline damage and the corresponding pipeline damage type in the preset detection area through the identification results, and can detect the pipeline damage through the preset positioning system of the control terminal Positioning
  • the internal condition subunit of the pipeline is used to determine the internal condition of the pipeline based on the damaged position of the pipeline and the corresponding type of pipeline damage
  • the condition information subunit is used to obtain the receiving time corresponding to the internal condition of the pipeline, and trace the corresponding robot through the receiving time status, and generate corresponding status information.
  • Embodiment 8 is a diagrammatic representation of Embodiment 8
  • the inferring subunit includes:
  • the status information type subunit used to transmit the status information to a preset type filter for classification, and determine the status information type;
  • Classification subunit used for extracting the distinguishing feature points of the distinguishing image through the type of status information, and at the same time classifying the distinguishing feature points to determine the classification result;
  • D(S) represents the classification result after classifying the status information types
  • g i represents the distinguishing feature points of the i-th status information type
  • R(g i ) represents the main points of the distinguishing feature points of the i-th status information type.
  • Action model subunit used to transmit the classification results and distinguishing feature points to a preset big data center for analysis, and construct a corresponding action model
  • Inference result subunit used to infer the movement posture of the detection robot based on the action model, and determine the inference result.
  • the inference subunit of the technical solution includes: a status information type subunit: used to transmit the status information to a preset type filter for classification, determine the status information type S i , and the classification subunit is used to pass the status information
  • the status information type extracts the distinguishing feature points of the distinguishing image, and at the same time, classifies the distinguishing feature points to determine the classification result
  • the action model subunit is used to transmit the classification result and the distinguishing feature points to the preset big data center Perform analysis to construct a corresponding action model
  • the inference result subunit is used to infer the motion posture of the detection robot based on the action model, and determine the inference result.
  • Embodiment 9 is a diagrammatic representation of Embodiment 9:
  • the drive control device is provided with a drive system and an obstacle avoidance system, and the drive system controls the drive control device through the control system, so that the drive control device starts to generate power, and drives the drive control device to move;
  • the obstacle avoidance system receives the control signal of the control system, and drives the control device to advance and avoid obstacles.
  • a power drive system is provided inside the power drive device, and the power drive system is controlled by a control system to control the drive device of the power drive system to move normally.
  • the power driving device of this technical solution is provided with a power driving system inside, and the power driving system is controlled through the control system to control the driving device of the power driving system to move normally, and the power driving device is used to generate power to control the driving control device to move.
  • the drive can control the direction and speed, so as to control the inspection robot.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Immunology (AREA)
  • Chemical & Material Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Remote Sensing (AREA)
  • Computing Systems (AREA)
  • Automation & Control Theory (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

一种CCTV管道在线检测系统，包括检测机器人、与检测机器人适配的CCTV管道检测系统和控制终端，CCTV管道检测系统包括GTR8600监测模块、驱动模块和动力驱动模块；控制终端通过控制系统和GTR8600监测模块、驱动模块和动力驱动模块分别电连接，控制系统安装在预设的控制终端内部。

Description

一种CCTV管道在线检测系统 技术领域
本发明涉及CCTV管道、检测机器人、人工智能技术领域，特别涉及一种CCTV管道在线检测系统。
背景技术
目前城镇、社区等场所的管道处承担各种商业、工业和人民日常排放污水的排放，但管道难以监管，目前有一种专门针对管道排查的机器人，针对管道的检查进行定期采集图像进行维修排查，随着城市社会的结构越来越大，许多管道的淤泥破损等需要及时的清理，及时发现并减少人民的生活中的隐匿的安全隐患，避免导致城市经济造成巨大的损失。
在已经公开的专利CN 211738405U中，提供了一种用于城市地下管网的检测系统轮胎直径可调节，满足不同直径的污水管检测，降低了检测成本，通过摄像主体、数据传输线、调节车轮和控制箱，实现了满足不同直径的污水管检测，提高了调节车轮的通用性，降低了整体的制造成本和检测成本的目的，但是仅针对检测机器人的本身结构做修改。
发明内容
本发明提供一种CCTV管道在线检测系统，用以解决以上背景技术中出现的情况。
本发明提供一种CCTV管道在线检测系统，包括控制终端、检测 机器人和与所述检测机器人适配的CCTV管道检测系统，所述CCTV管道检测系统安装在所述检测机器人内部；其中，
所述控制终端通过控制系统和检测机器人及适配的CCTV管道检测系统电连接，所述控制系统安装在预设的控制终端内部。
作为本技术方案的一种实施例，所述CCTV管道检测系统包括GTR8600监测模块、驱动模块和动力驱动模块；其中，
所述GTR8600监测模块安装在所述检测机器人上；
所述驱动控制模块通过控制终端驱使驱动控制装置进行移动；
所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
作为本技术方案的一种实施例，所述GTR8600监测模块包括业级高分辨彩色摄像单元、运动姿态监测单元、摄像录制处理终端和传输单元；其中，
所述业级高分辨彩色摄像单元用于采集外界影像，通过所述外界影像，获取分辨图像；
所述运动姿态监测单元用于通过所述分辨图像，实时识别和监控管道内部状况，通过所述监控管道内部状况，对检测机器人的运动姿态进行推断，确定推断结果；
所述摄像录制处理终端用于记录并处理采集到的外界影像及对应的管道内部状况，确定记录结果；
所述传输单元用于将所述推断结果和记录结果传输至控制终端。
作为本技术方案的一种实施例，所述业级高分辨彩色摄像单元， 包括：
影像采集子单元：用于通过预设的摄像设备，实时采集管道内的外界影像；
识别图像子单元：用于基于预设的彩色图像空间转换机制，对所述外界影像进行特征提取和特征识别，获取识别图像；
分辨图像子单元：用于基于预设的高分辨率重建机制，对所述识别图像进行高分辨，获取分辨图像。
作为本技术方案的一种实施例，所述运动姿态监测单元，包括：
偏移角度子单元：用于接收分辨图像，将所述分辨图像传输至预设的平衡检测机制，计算分辨图像的偏移角度；
检测机器人状况子单元：用于通过所述偏移角度，实时识别和监控检测机器人状况；
状况信息子单元：用于按照预设的周期，接收分辨图像，记录管道内部状况，通过所述机器人状况和管道内部状况，生成对应的状况信息；
推断子单元：用于基于所述状况信息，提取所述分辨图像的分辨特征点，将所述分辨特征点传输至预设的大数据中心进行分析，对检测机器人的运动姿态进行推断，确定推断结果。
作为本技术方案的一种实施例，所述摄像录制处理终端，包括：
采集结果单元：用于实时采集到的外界影像及对应的管道内部状况，确定采集结果；
判断单元：用于基于所述采集结果，实时判断所述管道内部状况 是否有异常，确定判断结果；
无异常单元：用于当所述判断结果无异常，记录对应的外界影像，并将记录后的外界影像进行压缩，上传至预设的云端存储库进行存储，确定正常记录结果；
异常单元：用于当所述判断结果有异常，获取状态管道内部状况，基于预设时间范围内，从预设的云端存储库调取历史正常记录结果，将所述状态管道内部状况和状态管道内部状况传输至大数据中心进行分析和记录，确定异常记录结果；
预警单元：用于将异常记录结果实时传输至控制终端进行预警；
记录结果单元：用于通过所述正常记录结果和异常记录结果，确定记录结果。
作为本技术方案的一种实施例，所述状况信息子单元，包括：
处理图像子单元：用于按照预设的周期，接收分辨图像，将所述分辨图像的图像像素进行灰度处理和归一化处理，确定处理图像；
局部图像子单元：用于对所述处理图像进行拉伸和分割，确定局部图像；
识别结果子单元：用于通过所述局部图像，对管道损坏类型进行识别，确定识别结果；
统计子单元：用于通过所述识别结果，统计预设的检测区域内的管道损坏位置和对应的管道损坏类型；
管道内部状况子单元：用于基于所述管道损坏位置和对应的管道损坏类型，确定管道内部状况；
状况信息子单元：用于获取所述管道内部状况对应的接收时间，通过所述接收时间，追溯对应的机器人状况，并生成对应的状况信息；
作为本技术方案的一种实施例，所述推断子单元，包括：
状况信息类型子单元：用于将所述状况信息传输至预设的类型筛选器中进行分类，确定状况信息类型；
Figure PCTCN2022140686-appb-000001
其中，S i代表第i种状况信息类型，i＝1,2,…,m，m代表接收到状况信息的总批数，f i代表第i批状况信息，j＝1,2,…,n，n代表类型筛选器的总个数，a j代表第j种类型筛选器，p(f i,a j)代表第i批状况信息在第j种类型筛选器的筛选概率，w i,j代表第i批状况信息进入第j种类型筛选器产生的权值，L代表筛选器的影响系数，Δt代表状况信息的接收时刻，
Figure PCTCN2022140686-appb-000002
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的分离函数，
Figure PCTCN2022140686-appb-000003
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的最大化分离函数，
Figure PCTCN2022140686-appb-000004
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的最小化分离函数；
分类子单元：用于通过所述状况信息类型，提取所述分辨图像的分辨特征点，同时，对分辨特征点进行分类，确定分类结果；
Figure PCTCN2022140686-appb-000005
其中，D(S)代表对状况信息类型分类后的分类结果，g i代表第i种状况信息类型的分辨特征点，R(g i)代表关于第i种状况信息类型的分 辨特征点的主特征分类函数，E(S i)代表第i种状况信息类型的特征点分类的权重值，
Figure PCTCN2022140686-appb-000006
代表第i *种状况信息类型的特征点分类的权重值，i *＝1,2,…,m，i≠i *，
Figure PCTCN2022140686-appb-000007
代表关于第i *种状况信息类型的分辨特征点的主特征分类函数，
Figure PCTCN2022140686-appb-000008
为判断第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点是否重合的函数；
Figure PCTCN2022140686-appb-000009
代表在第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点的重合情况成立，
Figure PCTCN2022140686-appb-000010
Figure PCTCN2022140686-appb-000011
代表在第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点有重合情况下的主特征分类函数，当第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点不重合时，将第i种状况信息类型的分辨特征点返回
Figure PCTCN2022140686-appb-000012
进行分类计算，将第j种状况信息类型的分辨特征点返回
Figure PCTCN2022140686-appb-000013
进行分类计算；
动作模型子单元：用于将所述分类结果和分辨特征点传输至预设的大数据中心进行分析，构建对应的动作模型；
推断结果子单元：用于基于所述动作模型，对检测机器人的运动姿态进行推断，确定推断结果。
作为本技术方案的一种实施例，所述驱动控制装置内部设有驱动系统和避障系统，所述驱动系统通过控制系统对驱动控制装置进行操控，使驱动控制装置启动产生动力，驱使驱动控制装置进行移动；
所述避障系统接受控制系统的控制信号，对驱动控制装置进避障。
作为本技术方案的一种实施例，所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系 统驱动装置进行常规移动。
本技术方案的有益效果为：
本发明实施例提供了一种CCTV管道在线检测系统，包括控制终端、检测机器人和与所述检测机器人适配的CCTV管道检测系统，CCTV管道检测系统安装在所述检测机器人内部；检测机器人在运行过程中，对管道进行检测和排查，通过外端的控制终端，对检测机器人进行控制，可以对管道的不同区域进行重点或者非重点排查，减少检测成本，同时，通过对检测机器人的控制，也可以尽可能避免检测机器人陷入淤泥等危险，控制终端通过控制系统和检测机器人及适配的CCTV管道检测系统电连接，所述控制系统安装在预设的控制终端内部，用于对机器人进行控制。本技术方案提供一种CCTV管道在线检测机器人的检测方法，通过检测机器人的控制，控制检测机器人对城市管道进行排查，由于检测机器人的成本较高，所以可以通过对管道中进行实时测量，从而减少检测机器人损坏，由于城市管道庞大复杂、结构多变，人工检查不仅耗时耗力，而且浪费时间成本，通过检测机器人的检测，减轻工作人员的时间成本，提高工作效率。
本发明的其它特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本发明而了解。本发明的目的和其他优点可通过在所写的说明书以及附图中所特别指出的结构来实现和获得。
下面通过附图和实施例，对本发明的技术方案做进一步的详细描 述。
附图说明
附图用来提供对本发明的进一步理解，并且构成说明书的一部分，与本发明的实施例一起用于解释本发明，并不构成对本发明的限制。在附图中：
图1为本发明实施例中一种CCTV管道在线检测系统模块图；
图2为本发明实施例中一种CCTV管道在线检测系统模块图；
图3为本发明实施例中一种CCTV管道在线检测系统模块图。
具体实施方式
以下结合附图对本发明的优选实施例进行说明，应当理解，此处所描述的优选实施例仅用于说明和解释本发明，并不用于限定本发明。
实施例1：
根据图1所示，本发明实施例提供了一种CCTV管道在线检测系统，包括控制终端、检测机器人和与所述检测机器人适配的CCTV管道检测系统，所述CCTV管道检测系统安装在所述检测机器人内部；其中，
所述控制终端通过控制系统和检测机器人及适配的CCTV管道检测系统电连接，所述控制系统安装在预设的控制终端内部。
上述技术方案的工作原理为：
本发明实施例提供了一种CCTV管道在线检测系统，包括控制终端、检测机器人和与所述检测机器人适配的CCTV管道检测系统， CCTV管道检测系统安装在所述检测机器人内部；检测机器人在运行过程中，对管道进行检测和排查，通过外端的控制终端，对检测机器人进行控制，可以对管道的不同区域进行重点或者非重点排查，减少检测成本，同时，通过对检测机器人的控制，也可以尽可能避免检测机器人陷入淤泥等危险，控制终端通过控制系统和检测机器人及适配的CCTV管道检测系统电连接，所述控制系统安装在预设的控制终端内部，用于对机器人进行控制。
上述技术方案的有益效果为：
本技术方案提供一种CCTV管道在线检测机器人的检测方法，通过检测机器人的控制，控制检测机器人对城市管道进行排查，由于检测机器人的成本较高，所以可以通过对管道中进行实时测量，从而减少检测机器人损坏，由于城市管道庞大复杂、结构多变，人工检查不仅耗时耗力，而且浪费时间成本，通过检测机器人的检测，减轻工作人员的时间成本，提高工作效率。
实施例2：
在一个实施例中，所述CCTV管道检测系统包括GTR8600监测模块、驱动模块和动力驱动模块；其中，
所述GTR8600监测模块安装在所述检测机器人上；
所述驱动控制模块通过控制终端驱使驱动控制装置进行移动；
所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
上述技术方案的工作原理为：
本技术方案的CCTV管道检测系统包括GTR8600监测模块、驱动模块和动力驱动模块；GTR8600监测模块安装在所述检测机器人上，GTR8600监测模块提供了一种彩色业级、高分辨率的摄像功能，通过对管道的监测，对城市、企业的管道隐患进行及时排查，驱动控制模块通过控制终端驱使驱动控制装置进行移动，通过控制终端，对检测机器人的动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
上述技术方案的有益效果为：
本技术方案通过控制终端的控制，而非常规设置路线，不仅提高了机器人的避障能力，减少机器人的损坏，同时，可以给检测机器人装有简单的功效性，可以对管道进行简单的清理，例如，将管道中的横向阻拦的棍状物通过机器人的驱动轮碾压断，使管道更容易疏通。
实施例3：
在一个实施例中，所述GTR8600监测模块包括业级高分辨彩色摄像单元、运动姿态监测单元、摄像录制处理终端和传输单元；其中，
所述业级高分辨彩色摄像单元用于采集外界影像，通过所述外界影像，获取分辨图像；
所述运动姿态监测单元用于通过所述分辨图像，实时识别和监控管道内部状况，通过所述监控管道内部状况，对检测机器人的运动姿态进行推断，确定推断结果；
所述摄像录制处理终端用于记录并处理采集到的外界影像及对应的管道内部状况，确定记录结果；
所述传输单元用于将所述推断结果和记录结果传输至控制终端。
上述技术方案的工作原理和有益效果为：
本技术方案的GTR8600监测模块包括业级高分辨彩色摄像单元、运动姿态监测单元、摄像录制处理终端和传输单元；其中，所述业级高分辨彩色摄像单元用于采集外界影像，通过所述外界影像，获取分辨图像；所述运动姿态监测单元用于通过所述分辨图像，实时识别和监控管道内部状况，通过所述监控管道内部状况，对检测机器人的运动姿态进行推断，确定推断结果；所述摄像录制处理终端用于收集采集到的外界影像及对应的管道内部状况；所述传输单元用于将推断结果传输至控制终端，通过对机器人的状态分析和外界环境的状态分析，综合分析出管道内部的情况，是否需要维修，从而提供精确的状况信息。
实施例4：
在一个实施例中，所述业级高分辨彩色摄像单元，包括：
影像采集子单元：用于通过预设的摄像设备，实时采集管道内的外界影像；
识别图像子单元：用于基于预设的彩色图像空间转换机制，对所述外界影像进行特征提取和特征识别，获取识别图像；
分辨图像子单元：用于基于预设的高分辨率重建机制，对所述识别图像进行高分辨，获取分辨图像。
上述技术方案的工作原理和有益效果为：
本技术方案的业级高分辨彩色摄像单元，影像采集子单元用于通过预设的摄像设备，实时采集管道内的外界影像；对管道的影响进行实时采集，识别图像子单元用于基于预设的彩色图像空间转换机制，对所述外界影像进行特征提取和特征识别，获取识别图像，通过识别图像，为管道不同类型的问题分类提供原始数据，分辨图像子单元用于基于预设的高分辨率重建机制，对所述识别图像进行高分辨，获取分辨图像，高分辨图像可以对图像中的管道隐患大小、位置进行精细分辨。
实施例5：
在一个实施例中，所述运动姿态监测单元，包括：
偏移角度子单元：用于接收分辨图像，将所述分辨图像传输至预设的平衡检测机制，计算分辨图像的偏移角度；
检测机器人状况子单元：用于通过所述偏移角度，实时识别和监控检测机器人状况；
状况信息子单元：用于按照预设的周期，接收分辨图像，记录管道内部状况，通过所述机器人状况和管道内部状况，生成对应的状况信息；
推断子单元：用于基于所述状况信息，提取所述分辨图像的分辨特征点，将所述分辨特征点传输至预设的大数据中心进行分析，对检测机器人的运动姿态进行推断，确定推断结果。
上述技术方案的工作原理和有益效果为：
在一个实施例中，所述运动姿态监测单元，包括：偏移角度子单 元：用于接收分辨图像，将所述分辨图像传输至预设的平衡检测机制，计算分辨图像的偏移角度；管道内部状况子单元：用于通过所述偏移角度，实时识别和监控管道内部状况；状况信息子单元：用于按照预设的周期，记录所述管道内部状况，生成对应的状况信息；推断子单元：用于基于所述状况信息，提取所述分辨图像的分辨特征点，将所述分辨特征点传输至预设的大数据中心进行分析，对检测机器人的运动姿态进行推断，确定推断结果，本技术方案通过对图像分辨，获取图像信息和机器人信息，综合对管道的损坏类型进行评判，从而避免管道经久不修，导致管道造成城市隐患。
实施例6：
在一个实施例中，所述摄像录制处理终端，包括：
采集结果单元：用于实时采集到的外界影像及对应的管道内部状况，确定采集结果；
判断单元：用于基于所述采集结果，实时判断所述管道内部状况是否有异常，确定判断结果；
无异常单元：用于当所述判断结果无异常，记录对应的外界影像，并将记录后的外界影像进行压缩，上传至预设的云端存储库进行存储，确定正常记录结果；
异常单元：用于当所述判断结果有异常，获取状态管道内部状况，基于预设时间范围内，从预设的云端存储库调取历史正常记录结果，将所述状态管道内部状况和状态管道内部状况传输至大数据中心进行分析和记录，确定异常记录结果；
预警单元：用于将异常记录结果实时传输至控制终端进行预警；
记录结果单元：用于通过所述正常记录结果和异常记录结果，确定记录结果。
上述技术方案的工作原理和有益效果为：
本技术方案的摄像录制处理终端，包括采集结果单元：用于实时采集到的外界影像及对应的管道内部状况，确定采集结果；判断单元：用于基于所述采集结果，实时判断所述管道内部状况是否有异常，确定判断结果；无异常单元：用于当所述判断结果无异常，记录对应的外界影像，并将记录后的外界影像进行压缩，上传至预设的云端存储库进行存储，确定正常记录结果；异常单元：用于当所述判断结果有异常，获取状态管道内部状况，基于预设时间范围内，从预设的云端存储库调取历史正常记录结果，将所述状态管道内部状况和状态管道内部状况传输至大数据中心进行分析和记录，确定异常记录结果；预警单元：用于将异常记录结果实时传输至控制终端进行预警；记录结果单元：用于通过所述正常记录结果和异常记录结果，确定记录结果，通过对管道的初始检测，粗略发现管道中的情况，通过对正常结果进行保存，可以用于维修时候，沿管道的长度进行检查，对管道什么原因导致损坏进行挖掘，从而不仅减轻工作人员的工作负担，同时，减少了检测排查的人力成本和时间成本。
实施例7：
在一个实施例中，所述状况信息子单元，包括：
处理图像子单元：用于按照预设的周期，接收分辨图像，将所述 分辨图像的图像像素进行灰度处理和归一化处理，确定处理图像；
局部图像子单元：用于对所述处理图像进行拉伸和分割，确定局部图像；
识别结果子单元：用于通过所述局部图像，对管道损坏类型进行识别，确定识别结果；
统计子单元：用于通过所述识别结果，统计预设的检测区域内的管道损坏位置和对应的管道损坏类型；
管道内部状况子单元：用于基于所述管道损坏位置和对应的管道损坏类型，确定管道内部状况；
状况信息子单元：用于获取所述管道内部状况对应的接收时间，通过所述接收时间，追溯对应的机器人状况，并生成对应的状况信息。
上述技术方案的工作原理和有益效果为：
本技术方案的状况信息子单元，包括：处理图像子单元用于按照预设的周期，接收分辨图像，将所述分辨图像的图像像素进行灰度处理和归一化处理，确定处理图像，由于管道中光线较暗，噪声比较大，所以刚拿到图像需要进行噪声处理，避免图像不清晰，局部图像子单元用于对处理图像进行拉伸和分割，确定局部图像，对于图像识别而言，图像的背景区域容易识别，但是图像需要重点识别的地方，需要重点分辨，识别结果子单元用于通过局部图像，对管道损坏类型进行识别，确定识别结果，管道有淤泥堵塞、泄露、管道变形等不同损坏风险，不同风险有不同隐患；统计子单元用于通过识别结果，统计预设的检测区域内的管道损坏位置和对应的管道损坏类型，可以通过控 制终端预设的定位系统对管道损坏的位置进行定位，管道内部状况子单元用于基于管道损坏位置和对应的管道损坏类型，确定管道内部状况，状况信息子单元用于获取管道内部状况对应的接收时间，通过接收时间，追溯对应的机器人状况，并生成对应的状况信息。
实施例8：
在一个实施例中，所述推断子单元，包括：
状况信息类型子单元：用于将所述状况信息传输至预设的类型筛选器中进行分类，确定状况信息类型；
Figure PCTCN2022140686-appb-000014
其中，S i代表第i种状况信息类型，i＝1,2,…,m，m代表接收到状况信息的总批数，f i代表第i批状况信息，j＝1,2,…,n，n代表类型筛选器的总个数，a j代表第j种类型筛选器，p(f i,a j)代表第i批状况信息在第j种类型筛选器的筛选概率，w i,j代表第i批状况信息进入第j种类型筛选器产生的权值，L代表筛选器的影响系数，Δt代表状况信息的接收时刻，
Figure PCTCN2022140686-appb-000015
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的分离函数，
Figure PCTCN2022140686-appb-000016
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的最大化分离函数，
Figure PCTCN2022140686-appb-000017
代表接收时刻Δt下关于第i批状况信息在第j种类型筛选器的筛选概率的最小化分离函数；
分类子单元：用于通过所述状况信息类型，提取所述分辨图像的分辨特征点，同时，对分辨特征点进行分类，确定分类结果；
Figure PCTCN2022140686-appb-000018
其中，D(S)代表对状况信息类型分类后的分类结果，g i代表第i种状况信息类型的分辨特征点，R(g i)代表关于第i种状况信息类型的分辨特征点的主特征分类函数，E(S i)代表第i种状况信息类型的特征点分类的权重值，
Figure PCTCN2022140686-appb-000019
代表第i *种状况信息类型的特征点分类的权重值，i *＝1,2,…,m，i≠i *，
Figure PCTCN2022140686-appb-000020
代表关于第i *种状况信息类型的分辨特征点的主特征分类函数，
Figure PCTCN2022140686-appb-000021
为判断第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点是否重合的函数；
Figure PCTCN2022140686-appb-000022
代表在第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点的重合情况成立，
Figure PCTCN2022140686-appb-000023
Figure PCTCN2022140686-appb-000024
代表在第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点有重合情况下的主特征分类函数，当第i种状况信息类型的分辨特征点和第j种状况信息类型的分辨特征点不重合时，将第i种状况信息类型的分辨特征点返回
Figure PCTCN2022140686-appb-000025
进行分类计算，将第j种状况信息类型的分辨特征点返回
Figure PCTCN2022140686-appb-000026
进行分类计算；
动作模型子单元：用于将所述分类结果和分辨特征点传输至预设的大数据中心进行分析，构建对应的动作模型；
推断结果子单元：用于基于所述动作模型，对检测机器人的运动姿态进行推断，确定推断结果。
上述技术方案的工作原理和有益效果为：
本技术方案的推断子单元，包括：状况信息类型子单元：用于将所述状况信息传输至预设的类型筛选器中进行分类，确定状况信息类 型S i，分类子单元用于通过所述状况信息类型，提取所述分辨图像的分辨特征点，同时，对分辨特征点进行分类，确定分类结果；动作模型子单元用于将所述分类结果和分辨特征点传输至预设的大数据中心进行分析，构建对应的动作模型；推断结果子单元用于基于所述动作模型，对检测机器人的运动姿态进行推断，确定推断结果。
实施例9：
在一个实施例中，所述驱动控制装置内部设有驱动系统和避障系统，所述驱动系统通过控制系统对驱动控制装置进行操控，使驱动控制装置启动产生动力，驱使驱动控制装置进行移动；
所述避障系统接受控制系统的控制信号，对驱动控制装置进避障。
实施例10：
在一个实施例中，所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
上述技术方案的工作原理和有益效果为:
本技术方案的动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动，动力驱动装置用于生成动力控制驱动控制装置进行移动，通过动力驱动可以控制方向和速度，从而对检测机器人进行控制。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不 脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (10)

  1. 一种CCTV管道在线检测系统，包括控制终端、检测机器人和与所述检测机器人适配的CCTV管道检测系统，所述CCTV管道检测系统安装在所述检测机器人内部；其中，
    所述控制终端通过控制系统和检测机器人及适配的CCTV管道检测系统电连接，所述控制系统安装在预设的控制终端内部。
  2. 如权利要求1所述的一种CCTV管道在线检测系统，其特征在于，所述CCTV管道检测系统包括GTR8600监测模块、驱动模块和动力驱动模块；其中，
    所述GTR8600监测模块安装在所述检测机器人上；
    所述驱动控制模块通过控制终端驱使驱动控制装置进行移动；
    所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
  3. 如权利要求2所述的一种CCTV管道在线检测系统，其特征在于，所述GTR8600监测模块包括业级高分辨彩色摄像单元、运动姿态监测单元、摄像录制处理终端和传输单元；其中，
    所述业级高分辨彩色摄像单元用于采集外界影像，通过所述外界影像，获取分辨图像；
    所述运动姿态监测单元用于通过所述分辨图像，实时识别和监控管道内部状况，通过所述监控管道内部状况，对检测机器人的运动姿态进行推断，确定推断结果；
    所述摄像录制处理终端用于记录并处理采集到的外界影像及对应的管道内部状况，确定记录结果；
    所述传输单元用于将所述推断结果和记录结果传输至控制终端。
  4. 如权利要求3所述的一种CCTV管道在线检测系统，其特征在于，所述业级高分辨彩色摄像单元，包括：
    影像采集子单元：用于通过预设的摄像设备，实时采集管道内的外界影像；
    识别图像子单元：用于基于预设的彩色图像空间转换机制，对所述外界影像进行特征提取和特征识别，获取识别图像；
    分辨图像子单元：用于基于预设的高分辨率重建机制，对所述识别图像进行高分辨，获取分辨图像。
  5. 如权利要求3所述的一种CCTV管道在线检测系统，其特征在于，所述运动姿态监测单元，包括：
    偏移角度子单元：用于接收分辨图像，将所述分辨图像传输至预设的平衡检测机制，计算分辨图像的偏移角度；
    检测机器人状况子单元：用于通过所述偏移角度，实时识别和监控检测机器人状况；
    状况信息子单元：用于按照预设的周期，接收分辨图像，记录管道内部状况，通过所述机器人状况和管道内部状况，生成对应的状况信息；
    推断子单元：用于基于所述状况信息，提取所述分辨图像的分辨特征点，将所述分辨特征点传输至预设的大数据中心进行分析，对检 测机器人的运动姿态进行推断，确定推断结果。
  6. 如权利要求3所述的一种CCTV管道在线检测系统，其特征在于，所述摄像录制处理终端，包括：
    采集结果单元：用于实时采集到的外界影像及对应的管道内部状况，确定采集结果；
    判断单元：用于基于所述采集结果，实时判断所述管道内部状况是否有异常，确定判断结果；
    无异常单元：用于当所述判断结果无异常，记录对应的外界影像，并将记录后的外界影像进行压缩，上传至预设的云端存储库进行存储，确定正常记录结果；
    异常单元：用于当所述判断结果有异常，获取状态管道内部状况，基于预设时间范围内，从预设的云端存储库调取历史正常记录结果，将所述状态管道内部状况和状态管道内部状况传输至大数据中心进行分析和记录，确定异常记录结果；
    预警单元：用于将异常记录结果实时传输至控制终端进行预警；
    记录结果单元：用于通过所述正常记录结果和异常记录结果，确定记录结果。
  7. 如权利要求5所述的一种CCTV管道在线检测系统，其特征在于，所述状况信息子单元，包括：
    处理图像子单元：用于按照预设的周期，接收分辨图像，将所述分辨图像的图像像素进行灰度处理和归一化处理，确定处理图像；
    局部图像子单元：用于对所述处理图像进行拉伸和分割，确定局 部图像；
    识别结果子单元：用于通过所述局部图像，对管道损坏类型进行识别，确定识别结果；
    统计子单元：用于通过所述识别结果，统计预设的检测区域内的管道损坏位置和对应的管道损坏类型；
    管道内部状况子单元：用于基于所述管道损坏位置和对应的管道损坏类型，确定管道内部状况；
    状况信息子单元：用于获取所述管道内部状况对应的接收时间，通过所述接收时间，追溯对应的机器人状况，并生成对应的状况信息。
  8. 如权利要求5所述的一种CCTV管道在线检测系统，其特征在于，所述推断子单元，包括：
    状况信息类型子单元：用于将所述状况信息传输至预设的类型筛选器中进行分类，确定状况信息类型；
    分类子单元：用于通过所述状况信息类型，提取所述分辨图像的分辨特征点，同时，对分辨特征点进行分类，确定分类结果；
    动作模型子单元：用于将所述分类结果和分辨特征点传输至预设的大数据中心进行分析，构建对应的动作模型；
    推断结果子单元：用于基于所述动作模型，对检测机器人的运动姿态进行推断，确定推断结果。
  9. 如权利要求2所述的一种CCTV管道在线检测系统，其特征在于，所述驱动控制装置内部设有驱动系统和避障系统；其中，
    所述驱动系统通过控制系统对驱动控制装置进行操控，使驱动控制装置启动产生动力，驱使驱动控制装置进行移动；
    所述避障系统接受控制系统的控制信号，对驱动控制装置进避障。
  10. 如权利要求2所述的一种CCTV管道在线检测系统，其特征在于，所述动力驱动装置内部设有动力驱动系统，通过控制系统对动力驱动系统进行操控，控制动力驱动系统驱动装置进行常规移动。
PCT/CN2022/140686 2022-02-22 2022-12-21 一种cctv管道在线检测系统 WO2023160188A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/197,132 US20230281782A1 (en) 2022-02-22 2023-05-15 Closed-circuit television (cctv) online pipeline detection system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210159647.3A CN114544668B (zh) 2022-02-22 2022-02-22 一种cctv管道在线检测系统
CN202210159647.3 2022-02-22

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/197,132 Continuation US20230281782A1 (en) 2022-02-22 2023-05-15 Closed-circuit television (cctv) online pipeline detection system

Publications (1)

Publication Number Publication Date
WO2023160188A1 true WO2023160188A1 (zh) 2023-08-31

Family

ID=81678301

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/140686 WO2023160188A1 (zh) 2022-02-22 2022-12-21 一种cctv管道在线检测系统

Country Status (3)

Country Link
US (1) US20230281782A1 (zh)
CN (1) CN114544668B (zh)
WO (1) WO2023160188A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114544668B (zh) * 2022-02-22 2023-04-07 盐城笃诚建设有限公司 一种cctv管道在线检测系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060128593A (ko) * 2005-06-09 2006-12-14 정선구 관로 내부 비파괴 검사 장치
CN207316352U (zh) * 2017-09-22 2018-05-04 贵州省交通规划勘察设计研究院股份有限公司 一种用于探测清淤的管道爬行机器人
CN207867340U (zh) * 2018-02-08 2018-09-14 安徽机电职业技术学院 一种地下管道巡检机器人控制系统
CN110145692A (zh) * 2019-05-23 2019-08-20 昆山华新建设工程有限公司 污水管道cctv检测系统及方法
CN111396754A (zh) * 2020-02-27 2020-07-10 吴盛 一种排水管cctv检测车及其检测系统
CN212251706U (zh) * 2019-12-10 2020-12-29 上海城建城市运营(集团)有限公司 一种管道机器人检测系统
CN112763499A (zh) * 2020-12-26 2021-05-07 上海浦东路桥绿化工程有限公司 一种管道cctv检测信息管理系统
CN114544668A (zh) * 2022-02-22 2022-05-27 盐城笃诚建设有限公司 一种cctv管道在线检测系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109268621B (zh) * 2018-11-16 2020-06-16 合肥工业大学 基于电致动材料驱动的管道检测机器人、管道检测系统
CN109611641B (zh) * 2019-01-11 2021-01-08 广州市天驰测绘技术有限公司 一种管道检测无线机器人
CN211649493U (zh) * 2019-11-19 2020-10-09 武汉海涵立科技有限公司 Cctv管道检测机器人机体结构

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060128593A (ko) * 2005-06-09 2006-12-14 정선구 관로 내부 비파괴 검사 장치
CN207316352U (zh) * 2017-09-22 2018-05-04 贵州省交通规划勘察设计研究院股份有限公司 一种用于探测清淤的管道爬行机器人
CN207867340U (zh) * 2018-02-08 2018-09-14 安徽机电职业技术学院 一种地下管道巡检机器人控制系统
CN110145692A (zh) * 2019-05-23 2019-08-20 昆山华新建设工程有限公司 污水管道cctv检测系统及方法
CN212251706U (zh) * 2019-12-10 2020-12-29 上海城建城市运营(集团)有限公司 一种管道机器人检测系统
CN111396754A (zh) * 2020-02-27 2020-07-10 吴盛 一种排水管cctv检测车及其检测系统
CN112763499A (zh) * 2020-12-26 2021-05-07 上海浦东路桥绿化工程有限公司 一种管道cctv检测信息管理系统
CN114544668A (zh) * 2022-02-22 2022-05-27 盐城笃诚建设有限公司 一种cctv管道在线检测系统

Also Published As

Publication number Publication date
US20230281782A1 (en) 2023-09-07
CN114544668A (zh) 2022-05-27
CN114544668B (zh) 2023-04-07

Similar Documents

Publication Publication Date Title
CN111016932B (zh) 节能型空轨系统的轨道巡检车和检测方法
CN110059631A (zh) 接触网非接触式监测缺陷识别方法
CN107424380A (zh) 城市地下综合管廊监测预警系统及其方法
WO2023160188A1 (zh) 一种cctv管道在线检测系统
CN106647819A (zh) 移动式图像采集装置及高速列车一级检修智能辅助系统
CN111300453A (zh) 一种综合管廊智能巡检机器人
CN210899299U (zh) 一种隧道监控系统
CN206074832U (zh) 一种地铁车辆车顶受电弓异物检测系统
CN104792796A (zh) 基于机器视觉的矿用胶带运行工况在线监测系统
CN116448773B (zh) 一种图像-振动特征融合的路面病害检测方法及系统
CN111061264A (zh) 智能巡检机器人
CN108527382A (zh) 一种巡检机器人
CN101833117A (zh) 智能车辆安全视觉检测装置及运动目标跟踪方法
CN113988518A (zh) 用于多源信息融合分析的配网设备健康诊断方法
CN115165362A (zh) 一种基于巡检及振动信号的轴承故障智能检测系统和方法
CN113128709A (zh) 一种供水管网漏损管理系统
CN113483815A (zh) 一种基于工业大数据的机械故障监控系统
CN111565024A (zh) 一种太阳能电池板故障检测与运行效率预测装置和方法
CN103422417A (zh) 一种公路表面破损的动态识别系统与方法
CN111767913A (zh) 一种基于深度学习的动车组车辆故障动态图像检测方法
CN115527364A (zh) 一种基于雷视数据融合的交通事故溯源方法及系统
CN117686650A (zh) 一种适用于运营期隧道的病害智能检测系统及方法
CN212312040U (zh) 一种综合管廊智能巡检机器人
CN108764762A (zh) 一种移动式城市排水管网健康管理系统
CN116743069A (zh) 光伏组件的清洗控制方法、清洗机器人、光伏清洗系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22928433

Country of ref document: EP

Kind code of ref document: A1