CN118857308B - An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines - Google Patents
An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines Download PDFInfo
- Publication number
- CN118857308B CN118857308B CN202411346052.4A CN202411346052A CN118857308B CN 118857308 B CN118857308 B CN 118857308B CN 202411346052 A CN202411346052 A CN 202411346052A CN 118857308 B CN118857308 B CN 118857308B
- Authority
- CN
- China
- Prior art keywords
- data
- vibration
- visual
- robot
- module
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 146
- 230000005540 biological transmission Effects 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000003379 elimination reaction Methods 0.000 title claims description 10
- 230000008030 elimination Effects 0.000 title claims description 9
- 238000005286 illumination Methods 0.000 claims abstract description 78
- 230000004927 fusion Effects 0.000 claims abstract description 32
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 32
- 230000007613 environmental effect Effects 0.000 claims description 26
- 230000033001 locomotion Effects 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 24
- 238000012544 monitoring process Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 13
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 10
- 230000008447 perception Effects 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010183 spectrum analysis Methods 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000010191 image analysis Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims 2
- 230000001960 triggered effect Effects 0.000 claims 2
- 230000006978 adaptation Effects 0.000 claims 1
- 230000007423 decrease Effects 0.000 claims 1
- 230000003631 expected effect Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 22
- 238000007689 inspection Methods 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
- G01C21/1656—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with passive imaging devices, e.g. cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/183—Compensation of inertial measurements, e.g. for temperature effects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/682—Vibration or motion blur correction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/76—Circuitry for compensating brightness variation in the scene by influencing the image signals
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manipulator (AREA)
Abstract
The invention discloses an outdoor visual positioning system of an intelligent defect eliminating robot of a power transmission line and a method thereof, wherein the system comprises an environment sensing module, an illumination compensation module, a visual inertia fusion module, a vibration compensation module, a self-adaptive visual algorithm module, a multi-sensor fusion module and a path planning and navigation module, wherein the environment sensing module is used for collecting surrounding environment data, the illumination compensation module is used for dynamically adjusting camera parameters, the visual inertia fusion module is used for compensating instability of visual data of the robot in a moving or vibrating process, the vibration compensation module is used for correcting visual positioning deviation caused by line vibration, the self-adaptive visual algorithm module can dynamically adjust parameter setting of the visual system, the multi-sensor fusion module fuses sensor data, and the path planning and navigation module are used for accurately planning paths. The invention can dynamically adjust the parameters of the camera, reduce positioning errors and ensure the positioning accuracy and stability of the robot in a complex environment.
Description
Technical Field
The invention relates to the technical field of defect eliminating robots, in particular to an intelligent defect eliminating robot outdoor visual positioning system for a power transmission line and a method thereof.
Background
In the power industry, the safety and stability of a transmission line, which is an important channel for power transmission, are directly related to the reliable operation of the whole power grid. However, the power transmission line often spans a wide region and is exposed to a complex outdoor environment, and is influenced by wind and rain erosion, temperature change, illumination difference and vibration caused by natural and human factors for a long time, and the factors can damage or defect the power transmission line, so that the safety of a power grid is threatened.
The traditional power transmission line inspection and maintenance work mainly depends on manual inspection, so that the labor intensity is high, the efficiency is low, the power transmission line inspection and maintenance work is difficult to be performed under severe environmental conditions, and great potential safety hazards exist. With the progress of technology, particularly the development of robot technology and computer vision technology, intelligent inspection robots for power transmission lines gradually become a research hotspot. However, when the existing intelligent inspection robot performs visual positioning in an outdoor complex environment, challenges such as illumination change, unstable visual data, line vibration and the like are often faced, and the positioning accuracy and the working efficiency of the robot are seriously affected by the problems.
Specifically, the quality of an image acquired by a camera is reduced due to the change of illumination conditions, the accuracy of visual positioning is affected, and the data acquired by a visual sensor can be unstable and error when the robot moves or is subjected to line vibration, so that the positioning accuracy is further reduced.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
In order to solve the technical problems, the invention provides the following technical scheme that the outdoor visual positioning system of the intelligent defect eliminating robot for the power transmission line mainly comprises the following components:
the environment sensing module is used for collecting surrounding environment data through the sensor;
the illumination compensation module dynamically adjusts the parameters of the camera according to the illumination data provided by the environment sensing module;
The visual inertial fusion module is used for fusing the data of the visual sensor and the inertial sensor and compensating the instability of the visual data of the robot in the moving or vibrating process by adopting a visual inertial odometer technology;
The vibration compensation module is used for analyzing the vibration frequency and amplitude of the power transmission line monitored by the environment sensing module and correcting visual positioning deviation caused by line vibration;
the self-adaptive visual algorithm module can dynamically adjust the parameter setting of the visual system according to the environmental change;
The multi-sensor fusion module adopts a multi-sensor fusion algorithm to fuse sensor data;
And the path planning and navigation module is used for carrying out accurate path planning by analyzing the position information and the surrounding environment information of the current robot on the power transmission line according to the data of the multiple sensors.
The intelligent defect eliminating robot outdoor visual positioning system for the power transmission line is characterized in that the sensor comprises an illumination sensor, a wind speed sensor, a temperature and humidity sensor and a vibration sensor, wherein the illumination sensor is used for monitoring illumination intensity and change in real time, the wind speed sensor is used for collecting wind speed information of the environment where the power transmission line is located, the temperature and humidity sensor is used for collecting temperature and humidity information of the environment where the power transmission line is located, and the vibration sensor is used for detecting vibration frequency and amplitude of the power transmission line and judging line change caused by wind power or mechanical movement.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the parameters of the camera comprise exposure, gain and contrast.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line further comprises a feedback control module, a remote monitoring module and a fault detection module;
the feedback control module adjusts the motion parameters of the robot in real time according to the feedback data of each module;
the remote monitoring module can check the running state and positioning information of the robot on the power transmission line in real time through a remote monitoring system, and is matched with an AR technology to help ground operators to remotely adjust the robot;
the fault detection module is used for detecting faults and timely reporting sensor abnormality or data failure.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the invention comprises the following steps of:
S11, setting a threshold value of illumination change by the system, and triggering a dynamic adjustment flow when the illumination intensity change exceeds the set threshold value;
s12, classifying current illumination conditions according to the monitored illumination data, evaluating the type and the amplitude of illumination change through a preset algorithm, and judging whether parameter adjustment is needed;
s13, calculating a required compensation amount according to the deviation between the current illumination data and the normal working illumination range, and then converting the compensation amount into adjustment values of exposure time, gain and contrast according to a mapping formula;
S14, calling a control interface of the camera, and adjusting exposure time, gain and contrast according to the calculated compensation value;
S15, the camera feeds back the adjusted image data to the system, and the vision system checks the brightness, definition and noise level of the picture through an image analysis algorithm to judge whether the adjustment effect reaches the expected value;
s16, when the illumination condition is stable, the system locks the current parameter setting, unnecessary adjustment is avoided, and the vision system is ensured to continuously provide high-quality images in the illumination stable stage.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the formula for calculating the required compensation quantity is as follows:
,
wherein:
is shown at the moment Is used for the illumination compensation amount of the lens;
Representing an initial time;
Representing time;
setting the ideal image brightness expected by the camera as the standard brightness required by the system;
indicating the current time The brightness of the actual image captured by the lower camera;
Indicating the moment of time The ambient illumination intensity of (2) is acquired in real time through an illumination sensor;
indicating the current time Is measured by an ambient noise detector;
indicating the current time Gain of the camera, parameters that the system can dynamically adjust;
indicating the current time The exposure time of the camera, the parameter that the system can adjust dynamically;
indicating the current time The contrast of the camera image is a measure of the difference of the brightness of the image;
Is an exponential decay function, is used for controlling the influence of gain and contrast adjustment at the past moment on the current compensation quantity, The degree of influence of the past adjustment on the current is determined for the attenuation coefficient to be positive, the larger the value is, the smaller the influence of the past adjustment is,A small scale for representing a summation term for discrete adjustment calculations in the time dimension;
The square of the difference between ideal brightness and actual brightness is represented, the square is amplified, and the system can also react to small deviation of brightness;
representing the superposition effect of the ambient illumination intensity and noise, the illumination intensity And noiseTwo key factors influencing the image quality, the larger the two sums, the stronger the environmental influence is, and the less compensation is required for brightness difference;
Representing an exponential function And gainAnd contrast ratioReflecting their common effect in the time dimension, the exponential decay controls the effect of the past time on the current compensation,AndThe adjustment strength of the gain and the contrast to the image is determined;
Indicating exposure time And the intensity of ambient lightEnsuring a balance between exposure time and illumination conditions in the compensation calculation, avoiding excessive adjustment;
Representing cumulative adjustment in the time dimension by an exponential decay function To ensure that the past gain and contrast have progressively less impact on the current, the summation expressing the time accumulation effect in camera parameter adjustment, ensuring that the system is able to respond dynamically to the environment over time;
From the initial time To the current timeThe accumulated compensation quantity of the brightness difference along with time is calculated through integration, so that the system can track illumination change and perform dynamic adjustment;
Value range meaning:
Value range of formula At the position ofAn inner part;
when (when) When the image quality is close to 0, the illumination condition is ideal, the image quality is close to the expected value, and great adjustment is not needed;
when (when) When the value increases, indicating that the light conditions deviate from expected, the system needs to increase the exposure or gain, or make contrast adjustments.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the invention comprises the following steps of:
step 21, initializing a visual sensor and an inertial sensor, ensuring the data time stamps of the visual sensor and the inertial sensor to be synchronous, then acquiring visual frame sequence data through the visual sensor, and acquiring acceleration and angular velocity through the inertial sensor;
Step 22, detecting and extracting characteristic points in the current image frame, tracking the matching relation of the characteristic points between adjacent frames, and recording the displacement information of the characteristic points;
Step 23, integrating the acquired acceleration and angular velocity data, and calculating the position and posture change quantity of the robot at each moment;
step 24, fusing the inertial data and the visual data through a Kalman filter or an extended Kalman filter, filtering noise and errors, and updating the current position information of the robot according to the fused result;
Step 25, performing visual inertial odometer calculation on each continuous frame, calculating pose changes of the robot at continuous moments according to image data provided by a visual sensor and motion data of the inertial sensor, and accumulating pose results of each frame with results of previous frames to obtain a complete moving track of the robot;
Step 26, analyzing high-frequency vibration information in the inertial sensor, identifying the motion characteristic of the robot at the vibration moment, dynamically correcting the visual positioning data according to the vibration characteristic, and smoothing noise caused by high-frequency vibration;
step 27, updating the position information of the robot on the power transmission line in real time according to the corrected vision and inertia data, and feeding back the current position information to a path planning and navigation module so as to carry out the next movement decision;
and 28, monitoring the positioning accuracy in real time, feeding back to the control system, and adjusting the compensation algorithm and the sensor parameters according to the environmental change.
As a preferable scheme of the intelligent defect eliminating robot outdoor visual positioning system for the power transmission line, the invention comprises the following steps of:
Step 31, monitoring vibration frequency and vibration amplitude of the power transmission line in real time by a sensor, and analyzing the vibration frequency and the vibration amplitude in each time period to determine the vibration characteristics of the line;
step 32, acquiring inertial data of the robot, ensuring time synchronization with vibration data, synchronizing the inertial data with vibration sensor data, and facilitating subsequent fusion calculation;
Step 33, performing spectrum analysis on the vibration data, determining high-frequency vibration components, and identifying main vibration components affecting visual positioning accuracy according to analysis results;
step 34, extracting and tracking characteristic points in the image, detecting the offset of the characteristic points between adjacent frames, comparing the data of the visual sensor and the inertial sensor, and calculating a visual positioning error;
Step 35, establishing a vibration compensation model based on frequency and amplitude, calculating compensation quantity, correcting sensor data and filtering high-frequency interference;
And 36, adjusting the positions of the visual characteristic points in real time according to the vibration compensation model, correcting visual data deviation, updating corrected position information and ensuring the visual positioning stability of the robot.
The invention relates to an optimal scheme of an intelligent defect eliminating robot outdoor visual positioning system for a power transmission line, wherein the method for establishing a vibration compensation model based on frequency and amplitude and calculating compensation quantity comprises the following steps:
step 351, preprocessing data acquired by a vibration sensor arranged on a power transmission line by using a filtering algorithm, and extracting key information of frequency and amplitude from the filtered data;
Step 352, performing Fourier transform on the acquired vibration data to obtain a spectrogram of vibration frequency, classifying high-frequency and low-frequency vibration components according to the spectrogram, and analyzing the change of amplitude;
step 353 defining a vibration compensation function Constructing a compensation model;
Vibration compensation function:
wherein:
And Representing the amplitudes of the high-frequency and low-frequency vibrations, respectively;
And The frequencies of the high-frequency and low-frequency vibrations, respectively;
And Is an influence coefficient for adjusting the influence of high-frequency and low-frequency vibration on the compensation amount;
And Is an adjustment parameter, controlling the response of the compensation function to frequency;
step 354, the acquired frequency and amplitude data is brought into a compensation function Calculating real-time compensation quantity, and adjusting characteristic points acquired by the visual sensor by using the compensation quantity to reduce positioning errors;
and 355, applying the calculated compensation quantity to the vision positioning system in real time, correcting the position of the characteristic point, and automatically adjusting the compensation model parameters by the feedback system according to the correction result to ensure that the vision positioning system is suitable for different vibration conditions.
The positioning method using the intelligent defect eliminating robot outdoor visual positioning system of the power transmission line comprises the following steps:
Collecting environmental data around the power transmission line by various sensors in the environmental perception module, wherein the environmental data comprise illumination intensity, wind speed, temperature and humidity and line vibration data;
Starting a visual sensor, acquiring a visual image sequence, and synchronously starting an inertial sensor to ensure that the time stamps of visual data and inertial data are synchronous;
Triggering an illumination compensation module according to illumination data acquired by the environment sensing module, and dynamically adjusting camera parameters to adapt to current illumination conditions so as to ensure stable image quality;
extracting visual characteristic points from a current image frame, tracking the displacement of the characteristic points in adjacent frames, and recording the displacement information of the characteristic points to perform preliminary visual positioning;
integrating acceleration and angular velocity data of the inertial sensor, calculating pose variation of the robot at each moment, and estimating displacement and angle variation of the robot;
The visual inertial fusion module is used for fusing visual data with inertial sensor data, and a Kalman filter or an extended Kalman filter is used for carrying out data filtering, so that noise and errors are eliminated, and the position information of the robot is updated in real time;
Monitoring the vibration frequency and amplitude of the power transmission line through a vibration sensor, performing spectrum analysis on vibration data, and extracting high-frequency vibration components affecting visual positioning;
Calculating vibration compensation quantity according to a frequency and amplitude-based compensation model constructed by the vibration compensation module, correcting visual positioning deviation caused by line vibration, and correcting the position of a characteristic point in visual data;
the multi-sensor fusion module is used for fusing the environment data, the visual data, the inertia data and the vibration compensation data to acquire more accurate robot position information;
According to the fused positioning data, combining with the geographical position information of the power transmission line, planning a moving path of the robot on the power transmission line through a path planning and navigation module, so as to ensure that the robot can stably and accurately travel;
the positioning accuracy of the robot is monitored in real time through a feedback control module, the motion parameters of the robot are adjusted if necessary, and the compensation algorithm and the sensor parameters are dynamically adjusted according to the environmental change;
The ground operator can check the positioning information and the running state of the robot in real time through the remote monitoring module to carry out remote adjustment, and meanwhile, the fault detection module is used for monitoring system abnormality and alarming in time.
The invention has the beneficial effects that:
1. According to the invention, through comprehensive use of the environment sensing module, the illumination compensation module, the visual inertia fusion module and the vibration compensation module, the system can effectively process the illumination change, the instability of visual data and the interference caused by line vibration, in addition, the camera parameters are dynamically adjusted through the illumination compensation module so as to adapt to different illumination conditions, and the visual inertia fusion module and the vibration compensation module can reduce positioning errors caused by vibration and movement, so that the positioning accuracy and stability of the robot in a complex environment are ensured by the measures, and the accuracy and efficiency of the defect elimination task are improved.
2. The self-adaptive vision algorithm module in the system can automatically adjust the parameter settings of the vision system, such as exposure time, contrast and the like, according to the change of the external environment so as to adapt to different vision environments and ensure the validity and accuracy of vision information. The self-adaptive capacity greatly enhances the adaptability of the robot to complex and changeable outdoor environments. Meanwhile, the multi-sensor fusion module integrates data from different sensors, so that the reliability and redundancy of the data are improved, the system can sense and understand the surrounding environment more comprehensively, and more accurate and rich information support is provided for subsequent path planning and navigation. The path planning and navigation module is based on the multi-source fusion data and combines an intelligent algorithm to realize accurate path planning and navigation, so that the operation of the robot on the power transmission line is more efficient and safer. The characteristics improve the intelligent level of the system together, and provide powerful technical support for intelligent inspection and maintenance of the power transmission line.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a block diagram of an outdoor visual positioning system of an intelligent defect eliminating robot for a power transmission line.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Further, in describing the embodiments of the present invention in detail, the cross-sectional view of the device structure is not partially enlarged to a general scale for convenience of description, and the schematic is only an example, which should not limit the scope of protection of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Referring to fig. 1, for one embodiment of the present invention, an outdoor visual positioning system of an intelligent defect eliminating robot for a power transmission line is provided, which mainly includes:
the environment sensing module is used for collecting surrounding environment data including illumination intensity, wind speed, temperature, humidity, vibration frequency of the power transmission line and the like through the sensor. The module provides environmental information input for parameter adjustment of the vision system and optimization of the overall positioning system.
The sensor comprises:
The illumination sensor is used for monitoring illumination intensity and change in real time;
the wind speed sensor is used for collecting wind speed information of the environment where the power transmission line is located;
The temperature and humidity sensor is used for collecting temperature and humidity information of the environment where the power transmission line is located;
And the vibration sensor is used for detecting the vibration frequency and amplitude of the power transmission line and judging line variation caused by wind power or mechanical motion.
And the illumination compensation module dynamically adjusts camera parameters according to illumination data provided by the environment sensing module, wherein the parameters comprise exposure, gain, contrast and the like, so that the definition and stability of the vision system can be maintained under the condition that illumination is severely changed (such as strong light, shadow and night). The module cooperates with the environment sensing module to adjust the image acquisition quality in real time.
The visual inertial fusion module is used for fusing the data of the visual sensor and the inertial sensor, adopting a visual inertial odometer technology to compensate the instability of the visual data of the robot in the moving or vibrating process, and particularly carrying out position correction through the inertial data under the condition of larger vibration.
And the vibration compensation module is used for analyzing the vibration frequency and amplitude of the power transmission line monitored by the environment sensing module and correcting the visual positioning deviation caused by line vibration. The module can effectively improve the positioning accuracy of the robot in the windy weather or under the condition of mechanical movement of the line.
The adaptive vision algorithm module can dynamically adjust the parameter setting of the vision system according to environmental changes (such as wind speed, temperature, humidity and the like). The module acquires real-time environmental data through the environmental perception module, and adjusts algorithm parameters to enhance the anti-interference capability of the system, so that higher visual positioning accuracy can be maintained in severe weather.
The multi-sensor fusion module adopts a multi-sensor fusion algorithm to fuse sensor data, so that the overall positioning accuracy of the robot is improved, and other sensors can provide effective compensation especially when a single sensor fails or the data is unreliable.
And the path planning and navigation module performs accurate path planning by analyzing the position information and the surrounding environment information of the current robot on the power transmission line according to the data of the multiple sensors. The module ensures that the robot can avoid obstacles and travel according to a planned path on the basis of high-precision positioning.
The system also comprises a feedback control module, a remote monitoring module and a fault detection module;
The feedback control module adjusts the motion parameters of the robot in real time according to the feedback data of each module, including speed, gesture and position control, so as to ensure that the robot can stably and accurately travel and operate in a complex environment;
The remote monitoring module can check the running state and positioning information of the robot on the power transmission line in real time through a remote monitoring system, and the remote monitoring module is matched with an AR technology to help ground operators to remotely adjust the robot;
the fault detection module is used for detecting faults and timely reporting sensor abnormality or data failure.
The modules cooperate with each other, and the outdoor visual positioning precision and stability of the intelligent defect eliminating robot of the power transmission line can be enhanced.
Specifically, dynamically adjusting the camera parameters includes the following steps:
S11, setting a threshold value of illumination change by the system, and triggering a dynamic adjustment flow when the illumination intensity change exceeds the set threshold value;
s12, classifying current illumination conditions, such as strong light, weak light, backlight or shadow environments, according to the monitored illumination data, evaluating the type and the amplitude of illumination change through a preset algorithm, and judging whether parameter adjustment is needed;
s13, calculating a required compensation amount according to the deviation between the current illumination data and the normal working illumination range, and then converting the compensation amount into adjustment values of exposure time, gain and contrast according to a mapping formula;
The mapping formula is as follows:
wherein:
wherein:
For the amount of adjustment of the exposure time, For the weight coefficient of exposure time adjustment, the sensitivity of exposure to illumination compensation is controlled,For a nonlinear mapping function, the illumination compensation quantityMapped to an appropriate exposure time adjustment value,The sensitivity coefficient is adjusted to control the influence of the compensation quantity on exposure adjustment;
For the amount of adjustment of the gain, For the weight coefficient of the gain adjustment,Converting the illumination compensation amount into an adjustment value of the gain as a nonlinear mapping function,The amplitude of gain change is controlled, so that the gain is increased when the light is insufficient, and the gain is reduced when the light is too strong;
as the amount of adjustment of the contrast ratio, For the weight coefficient of the contrast adjustment,As a function, the illumination compensation amount is converted into a contrast adjustment value,Controlling the frequency and amplitude of contrast adjustment to ensure that the contrast fluctuates within a proper range;
Combining all adjustments, the final exposure time, gain and contrast values can be expressed as:
,,
wherein, 、、The initial exposure time, gain and contrast set values of the camera are respectively calculated to obtain adjustment amounts of three parameters through calculation of illumination compensation amounts, so that the adaptability of the camera in different illumination environments is ensured;
Weighting of 、、The setting may be made according to the priority of the actual scene. In general, exposure time is preferentially adjusted in a low-light environment, and adjustment of gain and contrast should be fine-tuned based on exposure adjustment. The adjustment of the weight can be changed in real time according to the environmental conditions, so that the accuracy of the overall compensation is ensured.
S14, calling a control interface of the camera, and adjusting exposure time, gain and contrast according to the calculated compensation value;
S15, the camera feeds back the adjusted image data to the system, and the vision system checks the brightness, definition and noise level of the picture through an image analysis algorithm to judge whether the adjustment effect reaches the expected value;
s16, when the illumination condition is stable, the system locks the current parameter setting, unnecessary adjustment is avoided, and the vision system is ensured to continuously provide high-quality images in the illumination stable stage.
Further, the formula for calculating the required compensation amount is as follows:
wherein:
is shown at the moment Is used for the illumination compensation amount of the lens;
Representing an initial time;
Representing time;
setting the ideal image brightness expected by the camera as the standard brightness required by the system;
indicating the current time The brightness of the actual image captured by the lower camera;
Indicating the moment of time The ambient illumination intensity of (2) is acquired in real time through an illumination sensor;
indicating the current time Is measured by an ambient noise detector;
indicating the current time Gain of the camera, parameters that the system can dynamically adjust;
indicating the current time The exposure time of the camera, the parameter that the system can adjust dynamically;
indicating the current time The contrast of the camera image is a measure of the difference of the brightness of the image;
Is an exponential decay function, is used for controlling the influence of gain and contrast adjustment at the past moment on the current compensation quantity, The degree of influence of the past adjustment on the current is determined for the attenuation coefficient, which is usually a positive value, and the larger the value is, the smaller the influence of the past adjustment is,The subscript used to represent the summation term, typically used for discrete adjustment calculations in the time dimension;
The square of the difference between ideal brightness and actual brightness is represented, the square is amplified, and the system can also react to small deviation of brightness;
representing the superposition effect of the ambient illumination intensity and noise, the illumination intensity And noiseTwo key factors influencing the image quality, the larger the two sums, the stronger the environmental influence is, and the less compensation is required for brightness difference;
Representing an exponential function And gainAnd contrast ratioReflecting their common effect in the time dimension, the exponential decay controls the effect of the past time on the current compensation,AndThe adjustment strength of the gain and the contrast to the image is determined;
Indicating exposure time And the intensity of ambient lightEnsuring a balance between exposure time and illumination conditions in the compensation calculation, avoiding excessive adjustment;
Representing cumulative adjustment in the time dimension by an exponential decay function To ensure that the past gain and contrast have progressively less impact on the current, the summation expressing the time accumulation effect in camera parameter adjustment, ensuring that the system is able to respond dynamically to the environment over time;
From the initial time To the current timeThe accumulated compensation quantity of the brightness difference along with time is calculated through integration, so that the system can track illumination change and perform dynamic adjustment;
Value range meaning:
Value range of formula At the position ofAn inner part;
when (when) When the image quality is close to 0, the illumination condition is ideal, the image quality is close to the expected value, and great adjustment is not needed;
when (when) When the value increases, indicating that the light conditions deviate from expected, the system needs to increase the exposure or gain, or make contrast adjustments.
Specifically, the method for compensating the instability of visual data of the robot in the moving or vibrating process comprises the following steps:
step 21, initializing a visual sensor and an inertial sensor, ensuring the data time stamps of the visual sensor and the inertial sensor to be synchronous, then acquiring visual frame sequence data through the visual sensor, and acquiring acceleration and angular velocity through the inertial sensor;
Step 22, detecting and extracting characteristic points in the current image frame by using image data in a visual sensor and adopting a characteristic extraction algorithm (such as SIFT, ORB and the like), tracking the characteristic point matching relation between adjacent frames, and recording the displacement information of the characteristic points;
step 23, acquiring acceleration and angular velocity data by using an inertial sensor, integrating the acquired acceleration and angular velocity data, and calculating the position and posture change of the robot at each moment;
step 24, fusing the inertial data and the visual data through a Kalman filter or an extended Kalman filter, filtering noise and errors, and updating the current position information of the robot according to the fused result;
Step 25, performing visual inertial odometer calculation on each continuous frame, calculating pose changes of the robot at continuous moments according to image data provided by a visual sensor and motion data of the inertial sensor, and accumulating pose results of each frame with results of previous frames to obtain a complete moving track of the robot;
Step 26, analyzing high-frequency vibration information in the inertial sensor, identifying the motion characteristic of the robot at the vibration moment, dynamically correcting the visual positioning data according to the vibration characteristic, and smoothing noise caused by high-frequency vibration;
step 27, updating the position information of the robot on the power transmission line in real time according to the corrected vision and inertia data, and feeding back the current position information to a path planning and navigation module so as to carry out the next movement decision;
and 28, monitoring the positioning accuracy in real time, feeding back to the control system, and adjusting the compensation algorithm and the sensor parameters according to the environmental change.
Through the steps, the system can effectively fuse vision and inertial data, and the position information of the robot on the power transmission line is accurately calculated by utilizing a Vision Inertial Odometer (VIO) technology, particularly when the robot is subjected to external vibration or movement, the error of the vision data can be compensated in real time, so that the positioning accuracy is maintained.
Specifically, correcting the visual positioning deviation due to line vibration includes the steps of:
Step 31, installing vibration sensors (such as an accelerometer and a gyroscope) on a power transmission line, monitoring the vibration frequency and the vibration amplitude of the power transmission line in real time through the vibration sensors, acquiring real-time data of the line vibration through an environment sensing module, and analyzing the vibration frequency and the vibration amplitude in each time period to determine the characteristics of the line vibration;
step 32, acquiring inertial data of the robot through an inertial measurement unit of the robot, ensuring time synchronization with vibration data, synchronizing the inertial data with vibration sensor data, and facilitating subsequent fusion calculation;
Step 33, carrying out frequency spectrum analysis on the vibration frequency and amplitude of the circuit, determining high-frequency vibration components, and identifying main vibration components affecting the visual positioning accuracy according to analysis results;
Step 34, acquiring real-time visual data from a robot camera, including image frames of environmental feature points, extracting and tracking feature points in the images, detecting the offset of the feature points between adjacent frames, comparing the data of a visual sensor and an inertial sensor, and calculating a visual positioning error;
step 35, establishing a vibration compensation model according to the vibration frequency, amplitude and visual positioning error, calculating compensation quantity, correcting sensor data by using the technology such as Kalman filtering, and filtering high-frequency interference;
And 36, adjusting the positions of the vision characteristic points in real time according to the correction amount output by the vibration compensation model, correcting vision data deviation, updating corrected position information and ensuring the vision positioning stability of the robot.
Through the steps, the system can effectively analyze the vibration characteristics of the power transmission line and correct the visual positioning deviation caused by the vibration characteristics. The vibration compensation module combines the data of multiple sensors, realizes the dynamic correction of instability of visual data through a compensation model and a filtering algorithm, and ensures the accurate positioning of the robot in a complex environment.
Further, a vibration compensation model based on frequency and amplitude is established, and the compensation amount is calculated by the following steps:
step 351, preprocessing data acquired by a vibration sensor arranged on a power transmission line by using a filtering algorithm, and extracting key information of frequency and amplitude from the filtered data;
Step 352, performing Fourier transform on the acquired vibration data to obtain a spectrogram of vibration frequency, classifying high-frequency and low-frequency vibration components according to the spectrogram, and analyzing the change of amplitude;
step 353 defining a vibration compensation function Constructing a compensation model;
Vibration compensation function:
wherein:
And Representing the amplitudes of the high-frequency and low-frequency vibrations, respectively;
And The frequencies of the high-frequency and low-frequency vibrations, respectively;
And Is an influence coefficient for adjusting the influence of high-frequency and low-frequency vibration on the compensation amount;
And Is an adjustment parameter, controlling the response of the compensation function to frequency;
step 354, the acquired frequency and amplitude data is brought into a compensation function Calculating real-time compensation quantity, and adjusting characteristic points acquired by the visual sensor by using the compensation quantity to reduce positioning errors;
and 355, applying the calculated compensation quantity to the vision positioning system in real time, correcting the position of the characteristic point, and automatically adjusting the compensation model parameters by the feedback system according to the correction result to ensure that the vision positioning system is suitable for different vibration conditions.
Through the steps, the vibration compensation model can dynamically calculate and apply the compensation amount according to the frequency and amplitude information. Therefore, visual positioning deviation caused by vibration of the power transmission line can be effectively reduced, and stable positioning and operation of the robot are ensured.
In summary, the system can effectively process the disturbance caused by illumination change, instability of visual data and line vibration through the comprehensive use of the environment sensing module, the illumination compensation module, the visual inertia fusion module and the vibration compensation module, and the camera parameters are dynamically adjusted through the illumination compensation module so as to adapt to different illumination conditions, and the visual inertia fusion module and the vibration compensation module can reduce the positioning error caused by vibration and movement, so that the measures ensure the positioning precision and stability of the robot in a complex environment, and the accuracy and efficiency of the defect elimination task are improved. The self-adaptive vision algorithm module in the system can automatically adjust the parameter settings of the vision system, such as exposure time, contrast and the like, according to the change of the external environment so as to adapt to different vision environments and ensure the validity and accuracy of vision information. The self-adaptive capacity greatly enhances the adaptability of the robot to complex and changeable outdoor environments. Meanwhile, the multi-sensor fusion module integrates data from different sensors, so that the reliability and redundancy of the data are improved, the system can sense and understand the surrounding environment more comprehensively, and more accurate and rich information support is provided for subsequent path planning and navigation. The path planning and navigation module is based on the multi-source fusion data and combines an intelligent algorithm to realize accurate path planning and navigation, so that the operation of the robot on the power transmission line is more efficient and safer. The characteristics improve the intelligent level of the system together, and provide powerful technical support for intelligent inspection and maintenance of the power transmission line.
The positioning method using the intelligent defect eliminating robot outdoor visual positioning system of the power transmission line comprises the following steps:
Collecting environmental data around the power transmission line by various sensors in the environmental perception module, wherein the environmental data comprise illumination intensity, wind speed, temperature and humidity and line vibration data;
Starting a visual sensor, acquiring a visual image sequence, and synchronously starting an inertial sensor to ensure that the time stamps of visual data and inertial data are synchronous;
Triggering an illumination compensation module according to illumination data acquired by the environment sensing module, and dynamically adjusting camera parameters to adapt to current illumination conditions so as to ensure stable image quality;
extracting visual characteristic points from a current image frame, tracking the displacement of the characteristic points in adjacent frames, and recording the displacement information of the characteristic points to perform preliminary visual positioning;
integrating acceleration and angular velocity data of the inertial sensor, calculating pose variation of the robot at each moment, and estimating displacement and angle variation of the robot;
The visual inertial fusion module is used for fusing visual data with inertial sensor data, and a Kalman filter or an extended Kalman filter is used for carrying out data filtering, so that noise and errors are eliminated, and the position information of the robot is updated in real time;
Monitoring the vibration frequency and amplitude of the power transmission line through a vibration sensor, performing spectrum analysis on vibration data, and extracting high-frequency vibration components affecting visual positioning;
Calculating vibration compensation quantity according to a frequency and amplitude-based compensation model constructed by the vibration compensation module, correcting visual positioning deviation caused by line vibration, and correcting the position of a characteristic point in visual data;
the multi-sensor fusion module is used for fusing the environment data, the visual data, the inertia data and the vibration compensation data to acquire more accurate robot position information;
According to the fused positioning data, combining with the geographical position information of the power transmission line, planning a moving path of the robot on the power transmission line through a path planning and navigation module, so as to ensure that the robot can stably and accurately travel;
the positioning accuracy of the robot is monitored in real time through a feedback control module, the motion parameters of the robot are adjusted if necessary, and the compensation algorithm and the sensor parameters are dynamically adjusted according to the environmental change;
The ground operator can check the positioning information and the running state of the robot in real time through the remote monitoring module to carry out remote adjustment, and meanwhile, the fault detection module is used for monitoring system abnormality and alarming in time.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411346052.4A CN118857308B (en) | 2024-09-26 | 2024-09-26 | An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411346052.4A CN118857308B (en) | 2024-09-26 | 2024-09-26 | An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118857308A CN118857308A (en) | 2024-10-29 |
| CN118857308B true CN118857308B (en) | 2025-03-25 |
Family
ID=93177673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411346052.4A Active CN118857308B (en) | 2024-09-26 | 2024-09-26 | An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118857308B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119282412B (en) * | 2024-12-12 | 2025-03-04 | 北京金橙子科技股份有限公司 | Equipment processing method and system based on multi-speed production line |
| CN119478032A (en) * | 2025-01-10 | 2025-02-18 | 融梦跃视(上海)体育科技有限公司 | Table tennis ball landing point analysis and calculation system, method and device based on computer vision |
| CN119964283A (en) * | 2025-01-23 | 2025-05-09 | 泰智达(北京)网络科技有限公司 | An intelligent verification and access control system and method based on face recognition |
| CN119897873A (en) * | 2025-03-31 | 2025-04-29 | 浙江强脑科技有限公司 | Dynamic adaptive calibration method and device for robot dual-arm hand-eye |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118376237A (en) * | 2024-04-26 | 2024-07-23 | 重庆邮电大学 | Three-dimensional scene positioning method and device based on visual inertial odometry based on self-attention |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100568926C (en) * | 2006-04-30 | 2009-12-09 | 华为技术有限公司 | Obtaining method and control method of automatic exposure control parameters and imaging device |
| EP2942941B1 (en) * | 2014-05-08 | 2016-04-27 | Axis AB | Method and apparatus for determining a need for a change in a pixel density requirement due to changing light conditions |
| CN112204946A (en) * | 2019-10-28 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Data processing method, device, movable platform and computer readable storage medium |
| CN114723811A (en) * | 2022-02-25 | 2022-07-08 | 江苏云幕智造科技有限公司 | Stereo vision positioning and mapping method for quadruped robot in unstructured environment |
| CN117972457A (en) * | 2024-02-01 | 2024-05-03 | 光子(深圳)精密科技有限公司 | Adaptive compensation photoelectric sensor optimization method, system and storage medium |
| CN118192638A (en) * | 2024-04-18 | 2024-06-14 | 天津现代职业技术学院 | A UAV control platform capable of three-dimensional holographic inspection |
-
2024
- 2024-09-26 CN CN202411346052.4A patent/CN118857308B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118376237A (en) * | 2024-04-26 | 2024-07-23 | 重庆邮电大学 | Three-dimensional scene positioning method and device based on visual inertial odometry based on self-attention |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118857308A (en) | 2024-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118857308B (en) | An outdoor visual positioning system and method for an intelligent fault elimination robot for power transmission lines | |
| CN104470139B (en) | A Closed-loop Feedback Control Method for Tunnel Lighting | |
| CN117423225B (en) | A disaster remote sensing early warning system based on high-speed railway operation | |
| CN112693985A (en) | Non-invasive elevator state monitoring method fusing sensor data | |
| CN114577325B (en) | An online monitoring and early warning system and method for contact suspension operating status in strong wind areas | |
| CN112326039A (en) | Photovoltaic power plant patrols and examines auxiliary system | |
| CN110395398A (en) | A kind of ground connection assembly system and its earthing method based on multi-rotor unmanned aerial vehicle | |
| CN119760489B (en) | Multi-sensor altitude prediction system integrating LSTM and Kalman filtering | |
| CN114527294A (en) | Target speed measuring method based on single camera | |
| CN119803822A (en) | A structural health monitoring system for long-span bridge beams based on deformation analysis | |
| CN119723421B (en) | A method for low-altitude target recognition and real-time tracking in AI video based on deep learning | |
| JP2011223580A (en) | Correction of camera attitude | |
| CN115272892A (en) | A UAV positioning deviation monitoring and control system based on data analysis | |
| KR101886510B1 (en) | System and method for measuring tension of cable bridge | |
| CN119472804A (en) | A method and system for intelligently adjusting adaptive blinds based on light intensity | |
| CN119107510A (en) | A structural intelligent monitoring device based on deep learning | |
| CN114543680A (en) | On-site monitoring and ranging method for construction vehicles of overhead transmission line passages | |
| CN119967395A (en) | A high-precision positioning and navigation remote emergency takeover system | |
| CN118921443B (en) | An industrial monitoring system based on image data | |
| CN119719807B (en) | Elevator digital twin virtual and physical sensor data calibration method | |
| CN119460918B (en) | An intelligent control system for a tethered drone's retractable wire device | |
| KR102737459B1 (en) | System having Drone Equip Structure for Measuring Altitude as way of Revision | |
| CN120298449A (en) | Water conservancy construction safety supervision system and method based on artificial intelligence | |
| CN120125947A (en) | A UAV power inspection multimodal data fusion system and UAV | |
| CN118816866A (en) | A high-precision inertial measurement device and a measurement method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20250305 Address after: 214000 No.12 Liangxi Road, Wuxi City, Jiangsu Province Applicant after: STATE GRID JIANGSU ELECTRIC POWER CO., LTD. WUXI POWER SUPPLY Co. Country or region after: China Applicant after: Wuxi Guangying Group Co.,Ltd. Address before: No. 333 Xishan Avenue, Anzhen Street, Xishan District, Wuxi City, Jiangsu Province, China 214105 Applicant before: Wuxi University Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |