CN119935017B - A sensor position calibration system for limit recognition - Google Patents
A sensor position calibration system for limit recognitionInfo
- Publication number
- CN119935017B CN119935017B CN202510430345.9A CN202510430345A CN119935017B CN 119935017 B CN119935017 B CN 119935017B CN 202510430345 A CN202510430345 A CN 202510430345A CN 119935017 B CN119935017 B CN 119935017B
- Authority
- CN
- China
- Prior art keywords
- sensor
- verification
- score
- data
- credibility
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
本发明涉及限界识别技术领域，公开了一种用于限界识别的传感器位置校准系统，包括数据采集模块，获取各个传感器采集的位置信息数据；数据处理模块，获取位置信息数据并分别识别位置关联特征；数据比对模块，根据位置关联特征进行一致性验证、稳定性验证以及冗余信息验证，并将验证结果数据发送至可信度评价模块；可信度评价模块，根据预设的可信度评分策略计算各个传感器的可信度评分，其中可信度评分越低表示对应传感器可能出现异常；校准预警模块，基于可信度评分的分布进行判断，若其中一个传感器的可信度评分与其他传感器可信度评分均值的偏差程度大于预设的评分偏差阈值，则将该传感器作为待验证传感器并生成验证指令。
The present invention relates to the technical field of limit recognition, and discloses a sensor position calibration system for limit recognition, comprising a data acquisition module, for acquiring position information data acquired by each sensor; a data processing module, for acquiring the position information data and respectively identifying position-related features; a data comparison module, for performing consistency verification, stability verification and redundant information verification according to the position-related features, and sending the verification result data to a credibility evaluation module; a credibility evaluation module, for calculating the credibility score of each sensor according to a preset credibility scoring strategy, wherein the lower the credibility score, the more likely the corresponding sensor is to be abnormal; and a calibration warning module, for making a judgment based on the distribution of the credibility score, and if the degree of deviation between the credibility score of one sensor and the mean of the credibility scores of other sensors is greater than a preset score deviation threshold, the sensor is used as a sensor to be verified and a verification instruction is generated.
Description
Technical Field
The invention relates to the technical field of limit identification, in particular to a sensor position calibration system for limit identification.
Background
In the fields of railway transportation and the like, limit identification is important, and the safety operation of vehicles such as trains and the like can be ensured. The laser limit detection is used for detecting the limit of the vehicle, and can judge whether the appearance of the vehicle exceeds a specified safety range, so that accidents such as collision and scraping of the vehicle in the running process are avoided, the vehicle can safely pass through limited structures such as tunnels and bridges, and the laser limit detection is a necessary procedure for detecting and checking the contour line of the vehicle when the subway vehicle and the engineering vehicle are newly built (or overhauled). The laser limit detection device adopts a non-contact detection method, can rapidly acquire data when a vehicle passes through, automatically completes comparison with a standard limit, does not need manual intervention, and greatly improves detection efficiency.
However, due to environmental factors, equipment aging, etc., the position of the sensor may shift, resulting in inaccurate collected data, which in turn affects the accuracy of the boundary identification. At present, the existing sensor calibration system often lacks a comprehensive and accurate calibration mechanism, and can not timely discover and process abnormal conditions of the sensor, so that potential threats are brought to the safety of industries such as railway transportation and the like. Therefore, there is a need for an efficient, reliable sensor position calibration system for boundary identification.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a sensor position calibration system for limit identification, which is used for accurately evaluating the reliability of a sensor by comprehensively processing and verifying data acquired by the sensor and timely finding and processing the sensor which is possibly abnormal, thereby improving the accuracy and reliability of limit identification.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a sensor position calibration system for boundary identification, comprising:
the data acquisition module acquires position information data acquired by each sensor;
The data processing module acquires the position information data and respectively identifies position association features, and the position association features reflect the features which accord with the corresponding relation in the position information data acquired by different sensors;
the data comparison module performs consistency verification, stability verification and redundant information verification according to the position association characteristics and sends verification result data to the credibility evaluation module,
A credibility evaluation module for calculating credibility scores of the sensors according to a preset credibility scoring strategy, wherein the lower the credibility score is, the higher the probability of abnormality of the corresponding sensor is,
And the calibration early warning module is used for judging based on the distribution of the credibility scores, and if the credibility score of one sensor is larger than a preset score deviation threshold value with the deviation degree of the credibility score average value of other sensors, the sensor is used as the sensor to be verified and a verification instruction is generated.
Further, the sensor comprises a plurality of laser profilers and a plurality of area array cameras, the laser profilers acquire three-dimensional point cloud data of a train, the area array cameras acquire train image information of the train, the data processing module identifies point cloud key features and point cloud feature parameters in the three-dimensional point cloud data, the data processing module identifies image key features and image feature parameters in the train image information, the similarity between the point cloud feature parameters and the image feature parameters is judged, and if the similarity meets a preset feature similarity threshold, the corresponding point cloud key features and the image key features/the plurality of point cloud key features/the plurality of image key features are used as position association features, and the position association features comprise edge corner points and contour points of the train.
Further, the calculation formula of the credibility scoring strategy specifically comprises:
,
Where S represents a confidence score, A represents a consistency score, Weight parameters representing the consistency score, B represents the stability score,A weight parameter representing a stability score, C representing a redundant information verification score,Weight parameters representing redundant information validation scores.
Further, the consistency verification step includes:
defining the current sensor as a target sensor, acquiring at least one target verification point based on the location correlation feature,
Values of the target verification point in the world coordinate system are obtained to define as target verification values,
Defining a sensor having a position key feature with a target sensor as a reference sensor, acquiring a corresponding reference verification point based on the target verification point,
Values of the reference verification point in the world coordinate system are acquired to be defined as reference verification values.
Further, the consistency score calculation formula specifically includes:
,
,
,
d represents the sum of the consistency deviations of the target sensors, m represents the number of reference sensors, where the jth position-related feature has in the ith measurement A verification point, E is the kth target verification value of the jth position key feature of the target sensor in the ith measurement, F is the comparison with the target sensorReference verification values of the reference sensors under the same measurement conditions, W represents verification number weights,Representing the total number of verifications of all reference sensor devices in the respective measurements.
Further, the stability verification step includes:
acquiring positional information data and extracting critical dimensions, including width, length, surface curvature,
And acquiring the historical size and comparing the historical size with the key size.
Further, the calculation formula of the stability score is specifically:
,
,
Where V represents the variance of the critical dimension from the historical dimension, q-1 represents the number of historical dimensions, The parameter values representing the dimensions of the history,Parameter values representing the corresponding critical dimensions.
Further, the redundant information verification step includes:
acquiring depth data based on three-dimensional point cloud data, and performing data preprocessing on the depth data;
Acquiring texture images based on train image information, and performing image preprocessing;
converting the coordinates of the depth data into the coordinate system identical to the texture image so as to have a corresponding relation;
And calculating the correlation between the depth data and the texture data, wherein if the correlation is larger, the matching degree is higher, and the redundant information verification score is higher.
Further, the credibility evaluation module is configured with a weight dynamic adjustment strategy, and the formula of the weight dynamic adjustment strategy is specifically as follows:
,
,
Wherein the method comprises the steps of The v is 1,2 and 3, which respectively represent the weight parameter of the consistency score, the weight parameter of the stability score and the weight parameter of the redundant information verification score,The vector of the environmental parameter is represented,The basis weight is represented as a function of the basis weight,Representing the coefficient of influence of the environmental parameter on the weight,A quantization function representing the influence of the environmental parameter on the weight.
Further, the reliability evaluation module is configured with a stability weight parameter adjustment sub-strategy, which comprises obtaining historical overrun data, wherein the historical overrun data comprises a train overrun position, a detection range of the train overrun position and a sensor is judged, if the number of times of train overrun abnormality which occurs in the detection range corresponding to a target sensor is larger, the basic weight of a stability score weight parameter is smaller, if the number of times of verification corresponding to the target sensor is larger, the weight parameter of a consistency score is larger, and if the number of sensors with position correlation characteristics of the target sensor is smaller, the basic weight of a redundant information verification score weight parameter is larger.
The invention has the beneficial effects that:
The system provided by the invention is used for mutually verifying through the sensors arranged in the vehicle limit recognition system, judging the association between the data features acquired by each sensor device through the recognition position association features, mutually verifying through the sensors, respectively calculating the reliability scores, setting a plurality of evaluation items of the reliability scores, including consistency scores, stability scores and redundant information verification scores, and if the deviation degree of the reliability score average value of one of the sensor devices is larger than a preset score deviation threshold value, indicating that the deviation degree of the sensor device and other devices is high, errors are more likely to occur, so that whether the device needs to be verified or not is judged to be calibrated so as to ensure the detection precision of each sensor.
Drawings
FIG. 1 is a schematic diagram of a system architecture of the present invention;
FIG. 2 is a flow chart of a consistency verification step of the present invention;
FIG. 3 is a flow chart of a stability verification step in the present invention;
FIG. 4 is a flow chart of the redundant information verification step in the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When a component is considered to be "connected" to another component, it can be directly connected to the other component or intervening components may also be present. When an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
As shown in fig. 1 to 4, a sensor position calibration system for limit recognition of the present embodiment includes:
the data acquisition module acquires position information data acquired by each sensor;
The data processing module acquires the position information data and respectively identifies position association features, and the position association features reflect the features which accord with the corresponding relation in the position information data acquired by different sensors;
the data comparison module performs consistency verification, stability verification and redundant information verification according to the position association characteristics and sends verification result data to the credibility evaluation module,
The credibility evaluation module calculates the credibility score of each sensor according to a preset credibility scoring strategy, wherein the lower the credibility score is, the abnormity of the corresponding sensor is possible,
And the calibration early warning module is used for judging based on the distribution of the credibility scores, and if the credibility score of one sensor is larger than a preset score deviation threshold value with the deviation degree of the credibility score average value of other sensors, the sensor is used as the sensor to be verified and a verification instruction is generated.
The confidence score may set multiple evaluation items, such as consistency, stability, and redundancy verification items in the present application. And (3) consistency, namely comparing the same geometric characteristic parameters extracted by the two devices, and calculating the deviation degree of the geometric characteristic parameters. The smaller the deviation is, the higher the consistency of the measurement results of the two devices is, the higher the reliability is, and the stability index is that the fluctuation condition of the measurement data of each device is analyzed in the process of multiple measurement. The smaller the data fluctuation, the better the stability of the equipment measurement is, the higher the reliability is, and the redundant information verification index is that the mutual verification is performed by utilizing the complementarity of the two equipment measurement information, such as the texture information of an area array camera and the depth information of a three-dimensional laser profilometer. The more the verification result is in line with the expectation, the higher the credibility of the measurement of the device is.
The following describes the respective modules of the sensor position calibration system for limit detection:
1. Data acquisition module
The data acquisition module is used for acquiring position information data acquired by each sensor. For example, in a railroad clearance identification scenario, the sensor may include a number of laser profilers and a number of area array cameras. The laser profiler can acquire three-dimensional point cloud data of the train, and the area array camera can acquire train image information of the train. Assuming that a plurality of laser profilers and cameras are installed at a railway tunnel portal, the laser profilers scan the train in real time to generate three-dimensional point cloud data on the surface of the train, the area array camera shoots images of the train, and the data acquisition module collects the data.
2. Data processing module
The module obtains location information data and identifies location-related features, respectively. The position association features reflect the features which accord with the corresponding relation in the position information data acquired by different sensors. Specifically, the data processing module identifies point cloud key features and point cloud feature parameters in the three-dimensional point cloud data, and identifies image key features and image feature parameters in the train image information. For example, in three-dimensional point cloud data of a train, point cloud key features such as train side corner points and contour points are identified, and point cloud feature parameters such as coordinates and angles are calculated, and in train image information, image key features such as train side corner points and contour points are also identified, and image feature parameters are calculated. And judging the similarity between the point cloud characteristic parameters and the image characteristic parameters, and taking the corresponding point cloud key characteristics and the image key characteristics/a plurality of point cloud key characteristics/a plurality of image key characteristics as position association characteristics if the similarity accords with a preset characteristic similarity threshold value. For example, when the similarity between the coordinates of the corner points of the train head in the point cloud data and the coordinates of the corresponding corner points in the image is more than 90%, the two corner points are used as the position correlation features.
3. Data comparison module
The module performs consistency verification, stability verification and redundant information verification according to the position association characteristics, and sends verification result data to the credibility evaluation module.
Consistency verification, namely comparing the same geometric characteristic parameters extracted by the two devices, and calculating the deviation degree of the geometric characteristic parameters. The smaller the deviation, the higher the consistency of the measurement results of the two devices, the higher the reliability.
The consistency verification step comprises the following steps:
defining the current sensor as a target sensor, acquiring at least one target verification point based on the location correlation feature,
Values of the target verification point in the world coordinate system are obtained to define as target verification values,
Defining a sensor having a position key feature with a target sensor as a reference sensor, acquiring a corresponding reference verification point based on the target verification point,
Values of the reference verification point in the world coordinate system are acquired to be defined as reference verification values.
The consistency score calculation formula specifically comprises:
,
,
,
d represents the sum of the consistency deviations of the target sensors, m represents the number of reference sensors, where the jth position-related feature has in the ith measurement A verification point, E is a k-th target verification value of a j-th position key feature of the target sensor in the i-th measurement, F is a reference verification value of a first reference sensor compared with the target sensor under the same measurement condition, W represents verification times weight,Representing the total number of verifications of all reference sensor devices in the respective measurements. The smaller the deviation is, the more times are verified, the higher the consistency score is, and meanwhile the reliability of the device serving as a reference of other devices is also reflected.
Stability verification in the course of multiple measurements, the fluctuation of each device measurement data is analyzed. The smaller the data fluctuation, the better the stability of the device measurement, and the higher the reliability.
The stability verification step includes:
acquiring positional information data and extracting critical dimensions, including width, length, surface curvature,
And acquiring the historical size and comparing the historical size with the key size.
The calculation formula of the stability score is specifically as follows:
,
,
Where V represents the variance of the critical dimension from the historical dimension, q-1 represents the number of historical dimensions, The parameter values representing the dimensions of the history,Parameter values representing the corresponding critical dimensions.
And (3) verifying redundant information, namely performing mutual verification by using complementarity of measurement information of two devices, such as texture information of an area array camera and depth information of a three-dimensional laser profiler. The more the verification result is in line with the expectation, the higher the credibility of the measurement of the device is.
The redundant information verification step includes:
acquiring depth data based on three-dimensional point cloud data, and performing data preprocessing on the depth data;
Acquiring texture images based on train image information, and performing image preprocessing;
converting the coordinates of the depth data into the coordinate system identical to the texture image so as to have a corresponding relation;
And calculating the correlation between the depth data and the texture data, wherein if the correlation is larger, the matching degree is higher, and the redundant information verification score is higher.
A local surface normal vector of depth data is calculated that reflects the orientation information of the surface. The depth change rate, i.e. the difference in depth values of adjacent points, can also be extracted for characterizing the curvature of the surface. For example, in the case of a train surface shape, the surface normal vector may indicate the direction of inclination of the vehicle body surface, and the depth change rate may represent the degree of undulation of the surface.
For texture images, scale Invariant Feature Transform (SIFT) features, speeded Up Robust Features (SURF) features, etc. are extracted. These features are invariant to rotation, scaling, illumination changes of the image, and can effectively describe the uniqueness of the texture.
And matching by using the extracted features. If the KD tree and other data structures are adopted, the characteristic points of the depth data and the characteristic points of the texture data are quickly matched. For example, matching the surface normal vector feature points in the depth data with the SIFT feature points in the texture data, and finding the corresponding relation between the surface normal vector feature points and the SIFT feature points on the feature level.
And calculating the correlation between the depth value of the matching point pair and the strength of the texture feature. For example, it is counted whether the intensity of the texture feature corresponding to the point with the larger depth value also shows a certain regular change in a certain number of matching point pairs. The consistency of the variation trend of the depth data and the texture data in the same area can be calculated, for example, the consistency of the gradient directions of the depth data and the texture data in a certain local area is calculated, and the degree of the fit of the depth data and the texture data is estimated through the quantization index.
4. Credibility evaluation module
And calculating the reliability score of each sensor according to a preset reliability score strategy, wherein the lower the reliability score is, the abnormal condition of the corresponding sensor is likely to occur. The calculation formula of the credibility scoring strategy is specifically as follows:
,
Where S represents a confidence score, A represents a consistency score, Weight parameters representing the consistency score, B represents the stability score,A weight parameter representing a stability score, C representing a redundant information verification score,Weight parameters representing redundant information validation scores.
The credibility evaluation module is configured with a weight dynamic adjustment strategy, and the formula of the weight dynamic adjustment strategy is specifically as follows:
,
,
Wherein the method comprises the steps of The v is 1,2 and 3, which respectively represent the weight parameter of the consistency score, the weight parameter of the stability score and the weight parameter of the redundant information verification score,The vector of the environmental parameter is represented,The basis weight is represented as a function of the basis weight,Representing the influence coefficient of the preset environmental parameter on the weight,A quantization function representing the influence of the environmental parameter on the weight. For example, if the environmental shock is greater, it may be more important to score stability, the weight of stability should be increased, or in the case of insufficient illumination, the correlation of redundant information, such as depth data and texture, may be more critical, and the weight of redundant information needs to be increased.
For example, this time introduces three environmental parameters altogether, including illumination intensity, vibrations and humidity, corresponds and needs to set up photosensitive sensor, accelerometer and humidity transducer, and wherein illumination intensity can influence texture data quality, and vibrations can influence point cloud stability, and humidity can influence laser reflectance.The quantization function representing the influence of the environmental parameter on the weight is a preset function, and specific examples are given below:
is set as a quantization function of the illumination intensity, ;
Is set as a quantization function of the vibration intensity,;
Is set as a quantization function of the humidity,;
Wherein the method comprises the steps ofA weight parameter representing the intensity of the illumination,The intensity of the light is indicated and,() In particular to a trigonometric function formula,A weight parameter representing the intensity of the vibration,The intensity of the vibration is indicated,A weight parameter indicative of the humidity is provided,Indicating humidity.
The reliability evaluation module is configured with a stability weight parameter adjustment sub-strategy, and comprises the steps of acquiring historical overrun data, wherein the historical overrun data comprises a train overrun position, judging a detection range of a sensor and the train overrun position, and if the number of times of train overrun abnormality in the detection range corresponding to a target sensor is more, obtaining basic weight of a stability score weight parameterThe smaller the target sensor is, the larger the weight parameter of the consistency score is, the more the number of times the target sensor is verified is, and the smaller the number of sensors having position-related features with the target sensor is, the basic weight of the weight parameter of the redundant information verification score isThe larger.
5. Calibration early warning module
Judging based on the distribution of the credibility scores, and if the credibility score of one sensor and the credibility score mean value of the other sensors are larger than a preset score deviation threshold, taking the sensor as a sensor to be verified and generating a verification instruction. For example, when the preset score deviation threshold is 20%, and the deviation between the credibility score of a certain laser profiler and the credibility score mean value of other laser profilers and cameras exceeds 20%, the laser profiler is used as a sensor to be verified, and the system generates a verification instruction to prompt a worker to further check and calibrate the sensor.
Working principle:
The operation principle of the system is introduced according to the working flow:
data acquisition phase
The application uses different kinds of sensors to collect data, and the area array camera and the laser profiler are used for measurement. The data acquisition module is used for collecting three-dimensional point cloud data of the train acquired by the laser profiler and train image information acquired by the area array camera in real time. For example, the laser profiler scans the passing train once every 1 second to generate three-dimensional point cloud data on the surface of the train, and the area array camera simultaneously shoots the image information of the train.
(II) data processing stage
The data processing module processes the acquired data. And unifying the data acquired by the area array camera and the three-dimensional laser profiler to the same global coordinate system. Through an accurate calibration process, the conversion relation among a camera coordinate system, a laser profiler coordinate system and a global coordinate system is determined, and the consistency of measurement data of different devices in space positions is ensured. Representative characteristic points, such as edge points, key contour points and the like of the vehicle, are respectively extracted from the area array camera image and the three-dimensional laser profiler point cloud data. And (3) adopting a characteristic point matching algorithm to find out corresponding characteristic point pairs in the two data, and taking the corresponding point cloud key characteristics and the image key characteristics as position association characteristics when the similarity accords with a preset characteristic similarity threshold (such as 85%). And establishing a position mapping relation between the area array camera image and the three-dimensional laser profiler point cloud data according to the matched characteristic point pairs. Through the mapping relation, the position information measured by the two devices can be correlated, and subsequent anomaly analysis is facilitated.
(III) data alignment stage
1. Consistency verification
And selecting one corner point of the train head as a target verification point according to the position correlation characteristic by taking a certain laser profiler as a target sensor, and obtaining a target verification value of the train head under a world coordinate system. And taking the other laser profiler with the position key characteristics of the laser profiler as a reference sensor to acquire the reference verification value of the same edge and corner point of the train head acquired by the laser profiler. And calculating the consistency score according to a consistency score calculation formula.
2. Stability verification
And extracting key dimensions such as width, length, surface curvature and the like of a train carriage from the three-dimensional point cloud data of the train, which are acquired by the laser profiler, and comparing the key dimensions with the historical dimensions. The stability score is calculated according to a stability score calculation formula.
3. Redundant information verification
And processing the train image information to obtain a texture image and preprocessing the texture image. And converting the coordinates of the depth data into the same coordinate system as the texture image, and calculating the correlation between the depth data and the texture data to obtain a redundant information verification score.
(IV) credibility evaluation stage
The credibility evaluation module calculates credibility scores of the sensors according to a preset credibility scoring strategy. And simultaneously, regulating sub-strategies according to the weight parameters, and regulating the weight parameters of each verification index by combining the historical overrun data. For example, if the number of times of train overrun anomalies recently occurs in the detection range corresponding to a certain laser profiler is large, the weight parameter of the stability score is properly reduced.
(V) calibration early warning stage
The calibration early warning module judges based on the distribution of the credibility scores. If the degree of deviation of the credibility score of a certain sensor from the credibility score mean value of other sensors is larger than a preset score deviation threshold (such as 20%), the sensor is used as a sensor to be verified, a verification instruction is generated, and staff is informed to check and calibrate the sensor.
The laser profiler can be used for acquiring three-dimensional point cloud data, the area array camera can acquire image information of a train, the three-dimensional point cloud data and the image information can be associated according to position characteristics, such as profile characteristics of edges, angles and the like, and then reliability scores are calculated.
Through the steps, the system provided by the invention can calibrate and monitor the position of the sensor in real time, and ensure the accuracy and reliability of limit identification.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510430345.9A CN119935017B (en) | 2025-04-08 | 2025-04-08 | A sensor position calibration system for limit recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510430345.9A CN119935017B (en) | 2025-04-08 | 2025-04-08 | A sensor position calibration system for limit recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119935017A CN119935017A (en) | 2025-05-06 |
| CN119935017B true CN119935017B (en) | 2025-07-22 |
Family
ID=95549049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510430345.9A Active CN119935017B (en) | 2025-04-08 | 2025-04-08 | A sensor position calibration system for limit recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119935017B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120558291B (en) * | 2025-06-20 | 2026-01-30 | 深圳瑞惯科技有限公司 | Landslide monitoring sensor signal calibration method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020162937A1 (en) * | 2019-02-07 | 2020-08-13 | General Electric Company | Automated model validation system for electrical grid |
| CN119151387A (en) * | 2024-11-19 | 2024-12-17 | 水利部交通运输部国家能源局南京水利科学研究院 | River hydrologic sampling inspection method and system based on unmanned aerial vehicle |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4836086B2 (en) * | 2007-09-10 | 2011-12-14 | 三菱電機株式会社 | 3D shape detector |
| US8193481B2 (en) * | 2009-01-26 | 2012-06-05 | Centre De Recherche Industrielle De Quebec | Method and apparatus for assembling sensor output data with data representing a sensed location on a moving article |
| CN104657987B (en) * | 2015-02-03 | 2017-08-08 | 深圳大学 | Evaluation method and system based on the objective algorithm of PET/CT picture qualities |
| CN113728220B (en) * | 2018-08-25 | 2023-12-22 | 山东诺方电子科技有限公司 | A method for calibration and collaborative work of air pollution monitoring sensors |
| CN112306808B (en) * | 2020-11-03 | 2022-08-16 | 平安科技（深圳）有限公司 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
| DE102021101336A1 (en) * | 2021-01-22 | 2022-07-28 | Audi Aktiengesellschaft | Method for evaluating sensor data from a distance sensor, determination device, computer program and electronically readable data carrier |
| US12318951B2 (en) * | 2021-08-09 | 2025-06-03 | Mujin, Inc. | Systems and methods for object detection |
| CN117011828A (en) * | 2023-07-21 | 2023-11-07 | 中数智科(杭州)科技有限公司 | Train obstacle detecting system |
| CN116938960B (en) * | 2023-08-07 | 2024-07-26 | 北京斯年智驾科技有限公司 | Sensor data processing method, device, equipment and computer readable storage medium |
| CN118722761A (en) * | 2024-06-28 | 2024-10-01 | 东莞市诺丽科技股份有限公司 | A linear motor air gap comprehensive warning system and warning method |
| CN118764612B (en) * | 2024-09-05 | 2025-01-24 | 中数智科(杭州)科技有限公司 | A synchronous calibration system for multi-angle train image acquisition |
| CN118885941B (en) * | 2024-09-26 | 2025-01-21 | 中数智科(杭州)科技有限公司 | A fault prediction method based on 360° dynamic image detection system |
| CN118884883B (en) * | 2024-09-29 | 2025-01-03 | 成都秦川物联网科技股份有限公司 | Intelligent numerical control processing monitoring method and system based on industrial Internet of things |
| CN119249359B (en) * | 2024-12-04 | 2025-03-25 | 中煤西安设计工程有限责任公司 | A multi-terminal data fusion system for trackless rubber-tyred vehicles |
| CN119270282B (en) * | 2024-12-10 | 2025-04-22 | 水利部交通运输部国家能源局南京水利科学研究院 | Underwater defect positioning device and method for ultra-long water conveyance tunnel |
| CN119760355A (en) * | 2024-12-16 | 2025-04-04 | 深圳市东深智能技术有限公司 | A multidimensional analysis method and system based on water conservancy data |
| CN119722713B (en) * | 2025-02-26 | 2025-06-27 | 北京东宇宏达科技有限公司 | Partition data processing method for infrared image in specific area |
-
2025
- 2025-04-08 CN CN202510430345.9A patent/CN119935017B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020162937A1 (en) * | 2019-02-07 | 2020-08-13 | General Electric Company | Automated model validation system for electrical grid |
| CN119151387A (en) * | 2024-11-19 | 2024-12-17 | 水利部交通运输部国家能源局南京水利科学研究院 | River hydrologic sampling inspection method and system based on unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119935017A (en) | 2025-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210302157A1 (en) | Method, device and system for analyzing tunnel clearance based on laser point cloud | |
| US8103376B2 (en) | System and method for the on-machine 2-D contour measurement | |
| CN119935017B (en) | A sensor position calibration system for limit recognition | |
| CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
| CN118961708A (en) | A method and system for evaluating mechanical properties of ancient building wooden structures | |
| CN116879866B (en) | Road surface flatness evaluation method based on laser radar three-dimensional data | |
| CN118149727B (en) | Method and system for detecting railway turnout track structure based on 3D point cloud | |
| CN119693434A (en) | A multi-type bridge substructure crack depth detection system | |
| CN119321728A (en) | Roadway deformation real-time detection method and system based on binocular vision | |
| CN118111345A (en) | Tunnel foundation pit surrounding rock displacement, cracks and water accumulation monitoring system | |
| CN117761664A (en) | A lidar data security verification method, equipment and storage medium | |
| CN116681912A (en) | Gauge detection method and device for railway turnout | |
| CN118747741B (en) | Method and equipment for detecting cooperative state of track multi-index ad hoc network | |
| CN117911412B (en) | Dimension detection method and system for caterpillar track section for engineering machinery | |
| CN119492331A (en) | A method and device for measuring displacement distance based on machine vision | |
| CN118999665A (en) | High-speed rail contact net suspension system detection and state evaluation method based on inertial navigation | |
| CN117746288A (en) | Vehicle weight prediction, sample data construction and model training method and device | |
| CN120253128B (en) | A bridge pier rigidity detection method and system | |
| CN114509224A (en) | Bridge deflection testing method and system, readable storage medium and device | |
| CN115330751A (en) | A bolt detection and positioning method based on YOLOv5 and Realsense | |
| CN118408607B (en) | Automobile part detection method and device | |
| US12517061B2 (en) | Multi-angle vehicle defect measurement using surface-adaptive optical corrections | |
| CN120726051B (en) | Method and system for detecting defects of monorail track finger-shaped plate | |
| CN120701524B (en) | Unmanned aerial vehicle-based fan tower deformation detection method and system | |
| CN119417830B (en) | A method for judging bolt looseness based on detecting the minimum bounding box |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |