CN114943693A - Jetson Nano bridge crack detection method and system - Google Patents
Jetson Nano bridge crack detection method and system Download PDFInfo
- Publication number
- CN114943693A CN114943693A CN202210497871.3A CN202210497871A CN114943693A CN 114943693 A CN114943693 A CN 114943693A CN 202210497871 A CN202210497871 A CN 202210497871A CN 114943693 A CN114943693 A CN 114943693A
- Authority
- CN
- China
- Prior art keywords
- bridge
- picture
- detected
- shooting
- acquiring
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for detecting cracks based on a Jetson Nano bridge, wherein the method comprises the following steps: configuring a neural network model for Jetsonnano arranged at a bridge detection workstation; receiving analysis data generated by a Jetson Nano based on a neural network model and a surface picture of a bridge to be detected; and determining a bridge crack detection result based on the analysis data. The method for detecting the bridge cracks based on the Jetson Nano bridge realizes intelligent monitoring of the bridge cracks and improves reliability and certainty of data acquisition.
Description
Technical Field
The invention relates to the technical field of bridge detection, in particular to a method and a system for detecting bridge cracks based on Jetson Nano.
Background
The bridge plays a very important role in national economic development. After the bridge is built, the bridge is influenced by factors such as environmental factors, natural conditions, load action and the like for a long time, cracks can appear on the surface of the bridge, the cracks not only can cause the protection failure of a concrete layer on internal reinforcing steel bars, but also can cause the falling of concrete, and serious cracks are more precursors of the collapse of the bridge, so the cracks are one of main evaluation indexes of the health condition of the bridge.
The existing detection method still adopts an artificial detection mode, and has many defects:
(1) the cost is high: the manual detection mode needs a large amount of manpower and equipment such as bridge inspection vehicles, and is long in time consumption and high in cost;
(2) the real-time property is poor: the manual detection mode is carried out regularly, and the problems cannot be found in time;
(3) the informatization degree is low: the bridge crack file cannot be established, the management and maintenance of the bridge are inconvenient, and decision support information cannot be provided for management departments.
Disclosure of Invention
One of the purposes of the invention is to provide a method for detecting bridge cracks based on Jetson Nano, which realizes intelligent monitoring of bridge cracks and improves reliability and certainty of acquired data.
The method for detecting the bridge crack based on Jetson Nano provided by the embodiment of the invention comprises the following steps:
configuring a neural network model for Jetsonnano arranged at a bridge detection workstation;
receiving analysis data generated by a Jetson Nano based on a neural network model and a surface picture of a bridge to be detected;
and determining a bridge crack detection result based on the analysis data.
Preferably, the analysis data generated by jetsonno based on the neural network model and the surface picture of the bridge to be measured performs the following operations:
acquiring a surface picture of at least one bridge to be detected and a position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the position;
inputting each surface picture into a neural network model, and acquiring output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form analysis data.
Preferably, the determination of the bridge crack detection result based on the analysis data comprises:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring bridge crack detection results correspondingly associated with the standard feature set in a detection library;
analyzing the analysis data and constructing an analysis feature set, wherein the analysis feature set comprises the following steps:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging output data in each group of sampling data according to the sequence of numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of sampled data to form an analysis feature set; wherein the sample data closest to the current time is located in the first row.
Preferably, the acquiring of the surface picture of the bridge to be measured includes:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected for the vehicle to run through the bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through unmanned aerial vehicle shooting equipment;
acquiring the position of the surface picture corresponding to the bridge to be detected, comprising the following steps:
acquiring a preset three-dimensional space containing a bridge to be detected;
acquiring a setting parameter and a first shooting parameter of a camera;
mapping the camera to a three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle when shooting a second picture;
mapping the bridge inspection vehicle to a three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle shooting equipment to a three-dimensional space based on the second positioning information;
and determining the position of the bridge to be detected corresponding to the third picture based on the third shooting parameter.
Preferably, the obtaining of the surface picture of at least one bridge to be measured and the position of the surface picture corresponding to the bridge to be measured includes:
extracting a preset region of the surface picture;
acquiring a first area picture;
acquiring a preset position determination library;
matching the first area picture with each standard picture in a position determination library to acquire position information corresponding to the standard picture matched with the first area picture;
and analyzing the position information, and determining the position of the bridge to be detected corresponding to the surface picture.
Preferably, the numbering of the surface pictures based on position comprises:
acquiring a preset three-dimensional space containing a bridge to be detected;
determining a coordinate value in a three-dimensional space corresponding to the surface picture based on the position of the bridge to be detected corresponding to the surface picture;
and arranging the coordinate values in sequence to form the serial number of the surface picture.
The invention provides a bridge crack detection system based on Jetson Nano, comprising:
the configuration module is used for configuring a neural network model for Jetsonnano arranged at the bridge detection workstation;
the analysis data receiving module is used for receiving analysis data generated by the Jetson Nano based on the neural network model and the surface picture of the bridge to be detected;
and the detection module is used for determining the bridge crack detection result based on the analysis data.
Preferably, the analysis data generated by jetsonno based on the neural network model and the surface picture of the bridge to be measured performs the following operations:
acquiring a surface picture of at least one bridge to be detected and a position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the position;
inputting each surface picture into a neural network model, and acquiring output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form analysis data.
Preferably, the detection module determines the bridge crack detection result based on the analysis data, and performs the following operations:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring bridge crack detection results which are correspondingly associated with the standard feature set in a detection library;
analyzing the analysis data and constructing an analysis feature set, wherein the analysis feature set comprises the following steps:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging output data in each group of sampling data according to the sequence of numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of sampled data to form an analysis feature set; wherein the sample data closest to the current time is located in the first row.
Preferably, the obtaining of the surface picture of the bridge to be measured by jetsonno includes:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected for the vehicle to run through the bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through an unmanned aerial vehicle or a handheld camera;
jetson Nano obtains the position that the surface picture corresponds the bridge that awaits measuring, includes:
acquiring a preset three-dimensional space containing a bridge to be detected;
acquiring a setting parameter and a first shooting parameter of a camera;
mapping the camera to a three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle in shooting a second picture;
mapping the bridge inspection vehicle to a three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle shooting equipment to a three-dimensional space based on the second positioning information;
and determining the position of the bridge to be measured corresponding to the third picture based on the third shooting parameter.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a Jetson Nano bridge crack detection method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a model construction according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a model configuration according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a jetsonno bridge crack detection method in the embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides a method for detecting a bridge crack based on Jetson Nano, which comprises the following steps of:
step S1: configuring a neural network model for Jetsonnano arranged at a bridge detection workstation;
step S2: receiving analysis data generated by the Jetson Nano based on the neural network model and the surface picture of the bridge to be detected;
step S3: and determining a bridge crack detection result based on the analysis data.
The working principle and the beneficial effects of the technical scheme are as follows:
jetsonnano is an edge computing terminal, field data analysis is realized by arranging the Jetsonnno near a bridge to be detected, and a final detection result can be obtained by analyzing the analysis data only by the platform side; yolov5 target detection algorithm was carried out using JetsonNano artificial intelligence edge computing device of engida. And carrying out visual measurement and quantitative evaluation on the damage of the surface of the bridge according to a detection result after carrying out bridge crack detection by adopting a yolov5 algorithm. As shown in fig. 2, TensorRT is an SDK developed by england for high performance deep learning reasoning, which can compress, optimize, and deploy the network at runtime after training the neural network, and without the overhead of a framework. TensorRT optimizes and selects through combinations layers, kernel, and performs normalization and conversion to the optimal matrix method according to the specified precision, thereby improving the delay, throughput and efficiency of the network. The model is lightened as much as possible, and the terminal is accelerated as much as possible. The py file trained with the Pyroch was converted to a TensorRT file and then deployed on Jetson Nano, Invitro. A speed of 20 frames per second can be achieved. Jetson Nano is an artificial intelligence computing module derived from NVIDIA, is small in appearance, can process a plurality of sensors in parallel, can run a plurality of modern neural networks on each sensor, supports a plurality of common artificial intelligence frameworks, and is suitable for edge computing deployment. The operation steps of the method can be simply summarized as training a self YOLOv5 model on a host computer, converting the model into a TensorRT model, deploying the TensorRT model on a Jetson Nano and running the Jepson Nano by using DeepStream. Hardware environment: RTX 2080TI host Jetson Nano 4G B01; software environment: jetson Nano, Ubuntu 18.04, Jetpack 4.5.1, deep stream 5.1; a host computer: ubuntu 18.04, CUDA 10.2, yolov 55.0; the specific flow chart is shown in FIG. 3; training model (on-platform): the model used in the present invention was yolov 5. The method has the advantages that the single-stage yolov5 detection algorithm is adopted, the complicated process of manually extracting the surface defect characteristics of the bridge is omitted, and the deep semantic characteristics of the bridge surface defects are automatically extracted by utilizing a deep convolutional neural network, so that the detection algorithm has higher adaptability and robustness. Meanwhile, the detection problem is solved as a regression problem, the bridge gap detection and positioning can be completed only by one-time network passing of the image sequence, and the detection speed is considered on the basis of ensuring high detection precision; preparing an environment: preparing an environment above python3.8, creating a virtual environment by using conda, and installing dependencies in yolov5/requirements.txt under the yolov5 project; preparing a data set: and (4) providing a corresponding marking paradigm according to the existing bridge surface damage standard, and manually marking according to the marking paradigm. And obtaining a labeling file at the rectangular position of each category of each picture after labeling through labellmg. And for images which have low contrast and are not easy to mark by naked eyes and appear in the data set. By using the image enhancement technology, the image contrast is improved, and the bridge crack details are enhanced. And finally, obtaining the number of the images, the number of the labeling frames and the number of the small targets of each category. Converting the voc format into a yolo format data set by using a voc format data set with a label printed by using a labelImg (the voc format data set can be printed by other modes by self or the yolo format data set can be directly printed by using the labelImg), and generating images folders (storing all pictures), labels folders (storing printed labels), test.txt (test set), train.txt (training set) and val.txt (verification set); creating a configuration file: create dataset configuration file dataset.yaml; yaml, and copy a model to be trained in yolov5/models under yolov5 to modify. Training: modifying a parameter path data set configuration file path, a model configuration file path, a pre-training weight file path, CUDA equipment or a CPU, a picture folder path or a camera to be identified, a weight path and displaying an identification result according to actual conditions. Turning to TensorRT: tensorrtx/yolov5/gen _ wts. py is copied to the root directory of the yolov5 project to execute command generation wts file. Environment to Jetson Nano: a tensorrtx project was also cloned on the nano, and the resulting. wts was put under tensorrtx/yolov 5/with modifications tensorrtx/yolov5/yololayer. Deployed with DeepStream (on Nano): and (5) cloning the project. And (3) a bridge crack target detection algorithm based on YOLOv 5. The method is a single-stage general target detection algorithm based on deep learning and a neural network. And converting the target detection problem into a regression problem. The method has the advantages of light model weight, high reasoning speed, end-to-end optimization and the like. The algorithm skills of a backbone network, a loss function, multi-scale fusion, a detection head, data enhancement, an Anchor and the like through a v1-v4 algorithm are gradually optimized in an iterative manner, and the accuracy and the speed are continuously improved. Jetson has the advantage of TensorRT addition. TensorRT can improve the network reasoning performance by several times. When the neural network is used for reasoning, back propagation is not needed, and the use of a large amount of temporary storage is reduced. The reasoning framework can also fuse partial layers to improve the IO performance. In addition, the network input size is generally fixed, the network can be frozen, and the video memory can be more reasonably distributed. Besides layer fusion, TensorRT also performs tensor fusion, kernel automatic adjustment and other methods for automatic optimization, and FP32 and FP16 can be used in a Jetson platform in a mixed mode. Yoov 5 which is in real time in the current detection algorithm is selected, and Jetson Nano artificial intelligence edge computing equipment is used. Compared with the existing edge computing device built-in SOC system level chip.
In addition, the edge computing is arranged at one side close to an object or a data source, and a nearest-end service is provided nearby by adopting an open platform with the integration of network, computing, storage and application core capabilities. The application program is initiated at the edge side, so that a faster network service response is generated, and the basic requirements on real-time business and application intelligence are met. And the cloud computing still can access the historical data of the edge computing.
In one embodiment, the analysis data generated by jetsonno based on the neural network model and the surface picture of the bridge to be measured performs the following operations:
acquiring a surface picture of at least one bridge to be detected and a position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the positions;
inputting each surface picture into a neural network model, and acquiring output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form analysis data.
The working principle and the beneficial effects of the technical scheme are as follows:
the surface pictures of the bridge to be detected are mainly the road surface pictures, the side surfaces, the bottom surfaces and other positions of the travelling crane; the picture can adopt the extraction key position; the key position is determined according to the structure of the bridge and historical crack detection data and experience; the surface picture corresponds to the position of the bridge to be measured, namely the surface picture is the position of the surface of the bridge to be measured on the bridge to be measured; inputting a surface picture shot by the camera equipment into a neural network model configured by the platform by Jetson Nano to obtain output data; the output data includes: the number of cracks in a unit area, the maximum crack depth, the maximum crack area, the area ratio of the cracks in the unit area and the like; numbering the surface pictures according to the positions corresponding to the surface pictures to realize the difference between the surface pictures, and associating the numbers with output data to construct analysis data; the method is convenient for determining the position of the bridge corresponding to the analysis data, and is convenient for a user to trace.
In one embodiment, determining a bridge crack detection result based on the analysis data includes:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring bridge crack detection results which are correspondingly associated with the standard feature set in a detection library;
analyzing the analysis data and constructing an analysis feature set, wherein the analysis feature set comprises the following steps:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging output data in each group of sampling data according to the sequence of numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of sampling data to form an analysis feature set; wherein the sample data closest to the current time is located in the first row.
The working principle and the beneficial effects of the technical scheme are as follows:
the platform carries out detection and analysis of the system through a detection library; the detection analysis mainly determines the influence of the cracks on the service life of the bridge, and a user can conveniently deal with the cracks according to the detection result. Before matching the analysis feature set and the standard feature set, normalizing the numerical values in the analysis feature set; when the analysis feature set is matched with the standard feature set, a similarity calculation mode can be adopted, and a similarity calculation formula is as follows:
x ij analyzing data of ith row and jth column in the feature set; y is ij Data of ith row and jth column in standard feature set; n is the line number of the analysis characteristic set or the standard characteristic set; m is the column number of the analysis feature set or the standard feature set; x is similarity; when the similarity is the maximum in the detection library, determining that the two are matched; the detection library is constructed in advance based on a large amount of data analysis summary.
In one embodiment, acquiring a surface picture of a bridge to be measured includes:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected for the vehicle to run through the bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through unmanned aerial vehicle shooting equipment;
the working principle and the beneficial effects of the technical scheme are as follows:
the method comprises the following steps of acquiring a surface picture of bridge detection, wherein the first way is to shoot a bridge through a camera arranged at a fixed point, and the first way can be arranged at any position of the bridge through a support; the second type is a bridge inspection vehicle; the bridge inspection vehicle is a tool capable of running on the running surface of the bridge and is provided with a camera capable of shooting; thirdly, shooting by an unmanned aerial vehicle; of course, before shooting, the edge computing terminal needs to be connected; the cameras arranged at fixed points can be connected to the edge computing terminal through cables; bridge inspect the car and unmanned aerial vehicle passes through the bluetooth and is connected to marginal calculation terminal.
In order to determine the position of the surface picture, in an embodiment, acquiring the position of the surface picture corresponding to the bridge to be measured includes:
acquiring a preset three-dimensional space containing a bridge to be detected;
acquiring a setting parameter and a first shooting parameter of a camera; the setting of the parameters includes: the relative position relation with the bridge, camera setting angle, first shooting parameters: including the shooting direction, focal length, etc.;
mapping the camera to a three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle in shooting a second picture;
mapping the bridge inspection vehicle to a three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle shooting equipment to a three-dimensional space based on the second positioning information;
and determining the position of the bridge to be detected corresponding to the third picture based on the third shooting parameter.
In one embodiment, the obtaining of the surface picture of at least one bridge to be measured and the position of the surface picture corresponding to the bridge to be measured includes:
extracting a preset region of the surface picture;
acquiring a first area picture;
acquiring a preset position determination library;
matching the first area picture with each standard picture in a position determination library to acquire position information corresponding to the standard picture matched with the first area picture;
and analyzing the position information, and determining the position of the bridge to be detected corresponding to the surface picture.
The working principle and the beneficial effects of the technical scheme are as follows:
the first region is the middle part or other positions of the surface picture, and the preset region of the surface picture is subjected to region extraction, namely the preset region is extracted and is extracted from the surface picture; the position is determined through the position determining library, so that when the surface picture is independently extracted, the position can be determined from the picture; binding the position with the picture to ensure the accuracy of position determination; one specific application is that the position calibration is realized by attaching a two-dimensional code or a mark pattern to the bridge position corresponding to the surface picture; certainly, when shooting, shooting parameters of the camera can be corrected through the calibrated marks, so that accurate picture acquisition is realized; in the position determination library, associating the position information with the standard picture; the location determination library is also constructed in advance.
In one embodiment, numbering the surface pictures based on location includes:
acquiring a preset three-dimensional space containing a bridge to be detected;
determining a coordinate value in a three-dimensional space corresponding to the surface picture based on the position of the bridge to be detected corresponding to the surface picture;
and arranging the coordinate values in sequence to form the serial number of the surface picture.
The working principle and the beneficial effects of the technical scheme are as follows:
by associating the coordinate values with the serial numbers of the surface pictures, a user can conveniently position the abnormal position of the bridge on site according to the abnormal pictures.
The invention provides a bridge crack detection system based on Jetson Nano, as shown in figure 4, comprising:
the system comprises a configuration module 1, a detection module and a control module, wherein the configuration module 1 is used for configuring a neural network model for Jetson Nano arranged in a bridge detection workstation;
the analysis data receiving module 2 is used for receiving analysis data generated by the Jetson Nano based on the neural network model and the surface picture of the bridge to be detected;
and the detection module 3 is used for determining a bridge crack detection result based on the analysis data.
In one embodiment, the analysis data generated by jetsonno based on the neural network model and the surface picture of the bridge to be measured performs the following operations:
acquiring a surface picture of at least one bridge to be detected and a position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the position;
inputting each surface picture into a neural network model, and acquiring output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form analysis data.
In one embodiment, the detection module determines a bridge crack detection result based on the analysis data, and performs the following operations:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring bridge crack detection results correspondingly associated with the standard feature set in a detection library;
analyzing the analysis data and constructing an analysis feature set, wherein the analysis feature set comprises the following steps:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging output data in each group of sampling data according to the sequence of numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of sampling data to form an analysis feature set; wherein the sample data closest to the current time is located in the first row.
In one embodiment, the jetsonno obtains a picture of the surface of the bridge to be measured, and includes:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected for the vehicle to run through the bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through unmanned aerial vehicle shooting equipment;
jetson Nano obtains the position that the surface picture corresponds the bridge that awaits measuring, includes:
acquiring a preset three-dimensional space containing a bridge to be detected;
acquiring a setting parameter and a first shooting parameter of a camera;
mapping the camera to a three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle in shooting a second picture;
mapping the bridge inspection vehicle to a three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle shooting equipment to a three-dimensional space based on the second positioning information;
and determining the position of the bridge to be detected corresponding to the third picture based on the third shooting parameter.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for detecting cracks based on a Jetson Nano bridge is characterized by comprising the following steps:
configuring a neural network model for Jetson Nano arranged at a bridge detection workstation;
receiving analysis data of the Jetson Nano generated based on the neural network model and the surface picture of the bridge to be detected;
and determining a bridge crack detection result based on the analysis data.
2. The method for detecting the bridge crack based on the jetsonno bridge of claim 1, wherein the following operations are performed on the analysis data generated by the jetsonno bridge based on the neural network model and the surface picture of the bridge to be detected:
acquiring the surface picture of at least one bridge to be detected and the position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the position;
inputting each surface picture into the neural network model, and acquiring the output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form the analysis data.
3. The jetsonon nano-based bridge crack detection method of claim 1, wherein determining a bridge crack detection result based on the analysis data comprises:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring the bridge crack detection result which is correspondingly associated with the standard feature set in the detection library;
analyzing the analysis data to construct the analysis feature set, wherein the analyzing the analysis data comprises:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging the output data in the sampling data of each group according to the sequence of the serial numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of the sampling data to form the analysis feature set; wherein the sample data closest to the current time is located on a first row.
4. The jetsonon nano bridge crack detection method of claim 2, wherein the obtaining the surface picture of the bridge to be detected comprises:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected, wherein the bridge deck is used for vehicles to run, through the bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through unmanned aerial vehicle shooting equipment;
the acquiring the position of the surface picture corresponding to the bridge to be detected comprises the following steps:
acquiring a preset three-dimensional space containing the bridge to be detected;
acquiring a setting parameter and a first shooting parameter of the camera;
mapping the camera to the three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle in shooting the second picture;
mapping the bridge inspection vehicle to the three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle photographing device to the three-dimensional space based on the second positioning information;
and determining the position of the bridge to be detected corresponding to the third picture based on the third shooting parameter.
5. The jetsonno-based bridge crack detection method of claim 2, wherein the obtaining at least one surface picture of the bridge to be detected and a position of the surface picture corresponding to the bridge to be detected includes:
performing region extraction on a preset region of the surface picture;
acquiring a first area picture;
acquiring a preset position determination library;
matching the first area picture with each standard picture in the position determination library to acquire the position information corresponding to the standard picture matched with the first area picture;
and analyzing the position information, and determining the position of the bridge to be detected corresponding to the surface picture.
6. The jetsonon nano bridge crack detection method of claim 2, wherein numbering the surface pictures based on the positions comprises:
acquiring a preset three-dimensional space containing the bridge to be detected;
determining a coordinate value of the surface picture corresponding to the three-dimensional space based on the position of the bridge to be detected corresponding to the surface picture;
and arranging the coordinate values in sequence to form the serial number of the surface picture.
7. A bridge crack detection system based on Jetson Nano is characterized by comprising:
the configuration module is used for configuring a neural network model for Jetsonnano arranged at the bridge detection workstation;
the analysis data receiving module is used for receiving analysis data of the Jetson Nano, wherein the analysis data are generated based on the neural network model and the surface picture of the bridge to be detected;
and the detection module is used for determining the bridge crack detection result based on the analysis data.
8. The jetsonno bridge crack detection system of claim 7, wherein the analysis data generated by the jetsonno bridge based on the neural network model and the surface image of the bridge under test is performed as follows:
acquiring the surface picture of at least one bridge to be detected and the position of the surface picture corresponding to the bridge to be detected;
numbering the surface pictures based on the position;
inputting each surface picture into the neural network model, and acquiring the output data corresponding to each surface picture;
and associating the number of each surface picture with the output data to form the analysis data.
9. The jetsonno-based bridge crack detection system of claim 7, wherein the detection module determines a bridge crack detection result based on the analysis data, and performs the following operations:
analyzing the analysis data to construct an analysis feature set;
acquiring a preset detection library;
matching the analysis feature set with each standard feature set in the detection library one by one;
when the analysis feature set is matched with the standard feature set, acquiring the bridge crack detection result which is correspondingly associated with the standard feature set in the detection library;
analyzing the analysis data to construct the analysis feature set, wherein the analyzing the analysis data comprises:
sampling the analysis data according to a preset analysis data sampling rule to obtain N groups of sampling data; the value of N is greater than or equal to 1;
arranging the output data in the sampling data of each group according to the sequence of the serial numbers to form a line of data;
arranging the data of each row from top to bottom according to the time sequence of each group of the sampling data to form the analysis feature set; wherein the sample data closest to the current time is located in a first row.
10. The jetsonno-based bridge crack detection method of claim 8, wherein the jetsonno obtains the surface picture of the bridge to be detected, and the jetsonno comprises:
shooting a first picture of the bridge to be detected through a plurality of cameras respectively shooting a plurality of preset first positions of the bridge to be detected;
shooting a second picture of a bridge deck of the bridge to be detected for the vehicle to run by a bridge detection vehicle;
shooting a third picture of the outer side of the bridge to be detected through unmanned aerial vehicle shooting equipment;
the jetsonno acquiring the position of the surface picture corresponding to the bridge to be detected comprises the following steps:
acquiring a preset three-dimensional space containing the bridge to be detected;
acquiring a setting parameter and a first shooting parameter of the camera;
mapping the camera to the three-dimensional space based on the setting parameters;
determining the position of the bridge to be detected corresponding to the first picture corresponding to the camera based on the first shooting parameter;
acquiring first positioning information and second shooting parameters of the bridge inspection vehicle in shooting the second picture;
mapping the bridge inspection vehicle to the three-dimensional space based on the first positioning information;
determining the position of the bridge to be detected corresponding to the second picture based on the second shooting parameter;
acquiring second positioning information of the unmanned aerial vehicle shooting equipment when the unmanned aerial vehicle shooting equipment shoots the third picture;
mapping the unmanned aerial vehicle photographing device to the three-dimensional space based on the second positioning information;
and determining the position of the bridge to be detected corresponding to the third picture based on the third shooting parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497871.3A CN114943693B (en) | 2022-05-09 | 2022-05-09 | Jetson Nano bridge crack detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497871.3A CN114943693B (en) | 2022-05-09 | 2022-05-09 | Jetson Nano bridge crack detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114943693A true CN114943693A (en) | 2022-08-26 |
| CN114943693B CN114943693B (en) | 2023-07-25 |
Family
ID=82907732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210497871.3A Active CN114943693B (en) | 2022-05-09 | 2022-05-09 | Jetson Nano bridge crack detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943693B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| KR20190086141A (en) * | 2018-01-12 | 2019-07-22 | 인하대학교 산학협력단 | Simulation Data Preprocessing Technique for Development of Damage Detecting Method for Bridges Based on Convolutional Neural Network |
| US20200098103A1 (en) * | 2018-09-21 | 2020-03-26 | Chongqing Construction Engineering Group Corporation Limited | High-precision Intelligent Detection Method For Bridge Diseases Based On Spatial Position |
| CN111402227A (en) * | 2020-03-13 | 2020-07-10 | 河海大学常州校区 | Bridge crack detection method |
| CN114049560A (en) * | 2021-11-25 | 2022-02-15 | 江苏科技大学 | Road surface multi-feature disease detection method and device based on combination of multiple neural networks |
| CN114419565A (en) * | 2021-12-24 | 2022-04-29 | 天津市水木兄弟科技有限公司 | Special vehicle operation collision early warning method and system based on YOLOv4 |
-
2022
- 2022-05-09 CN CN202210497871.3A patent/CN114943693B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| KR20190086141A (en) * | 2018-01-12 | 2019-07-22 | 인하대학교 산학협력단 | Simulation Data Preprocessing Technique for Development of Damage Detecting Method for Bridges Based on Convolutional Neural Network |
| US20200098103A1 (en) * | 2018-09-21 | 2020-03-26 | Chongqing Construction Engineering Group Corporation Limited | High-precision Intelligent Detection Method For Bridge Diseases Based On Spatial Position |
| CN111402227A (en) * | 2020-03-13 | 2020-07-10 | 河海大学常州校区 | Bridge crack detection method |
| CN114049560A (en) * | 2021-11-25 | 2022-02-15 | 江苏科技大学 | Road surface multi-feature disease detection method and device based on combination of multiple neural networks |
| CN114419565A (en) * | 2021-12-24 | 2022-04-29 | 天津市水木兄弟科技有限公司 | Special vehicle operation collision early warning method and system based on YOLOv4 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114943693B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ukhwah et al. | Asphalt pavement pothole detection using deep learning method based on YOLO neural network | |
| US20210319561A1 (en) | Image segmentation method and system for pavement disease based on deep learning | |
| Wang et al. | Autonomous damage segmentation and measurement of glazed tiles in historic buildings via deep learning | |
| CN113252700B (en) | Structural crack detection method, equipment and system | |
| KR102346676B1 (en) | Method for creating damage figure using the deep learning-based damage image classification of facility | |
| CN110910341B (en) | Method and device for detecting defects of rusted areas of power transmission line | |
| Li et al. | Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing | |
| CN110009614A (en) | Method and apparatus for output information | |
| CN109858414A (en) | A kind of invoice piecemeal detection method | |
| CN110837839B (en) | High-precision unmanned aerial vehicle orthographic image manufacturing and data acquisition method | |
| KR102308456B1 (en) | Tree species detection system based on LiDAR and RGB camera and Detection method of the same | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN115409069A (en) | Village and town building identification method, classification method, device, electronic equipment and medium | |
| TW202009681A (en) | Sample labeling method and device, and damage category identification method and device | |
| CN116363125B (en) | Deep learning-based battery module appearance defect detection method and system | |
| CN110688955A (en) | Building construction target detection method based on YOLO neural network | |
| CN116258980A (en) | Unmanned aerial vehicle distributed photovoltaic power station inspection method based on vision | |
| CN113674216A (en) | Subway tunnel disease detection method based on deep learning | |
| CN115171045A (en) | YOLO-based power grid operation field violation identification method and terminal | |
| CN117422699A (en) | Highway detection method, highway detection device, computer equipment and storage medium | |
| CN112184903A (en) | Method, device, equipment and medium for detecting high-voltage line tree obstacle risk points | |
| CN114943693B (en) | Jetson Nano bridge crack detection method and system | |
| CN116681962A (en) | Power equipment thermal image detection method and system based on improved YOLOv5 | |
| CN116229001A (en) | Urban three-dimensional digital map generation method and system based on spatial entropy | |
| CN114140703A (en) | Intelligent recognition method and system for forest pine wood nematode diseases |
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 |