CN115575400A - Heaven and earth integrated highway detection system and method - Google Patents
Heaven and earth integrated highway detection system and method Download PDFInfo
- Publication number
- CN115575400A CN115575400A CN202211209926.2A CN202211209926A CN115575400A CN 115575400 A CN115575400 A CN 115575400A CN 202211209926 A CN202211209926 A CN 202211209926A CN 115575400 A CN115575400 A CN 115575400A
- Authority
- CN
- China
- Prior art keywords
- disease
- detection
- unmanned aerial
- aerial vehicle
- vehicle
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
- G01B11/285—Measuring arrangements characterised by the use of optical techniques for measuring areas using photoelectric detection means
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a heaven and earth integrated highway detection system and a method, belonging to the technical field of highway detection. The system comprises a detection vehicle carrying an unmanned aerial vehicle take-off and landing airport, the unmanned aerial vehicle, a mobile detection terminal, an intelligent identification system and a server; the detection vehicle is provided with a camera and is used for collecting disease images of a road surface and a roadside; the unmanned aerial vehicle is provided with a camera and is used for acquiring disease images at high places or in areas where manpower is difficult to reach; the mobile detection terminal is provided with a camera and is used for collecting disease images at positions where a road hidden position, an unmanned aerial vehicle and a detection vehicle cannot reach, and meanwhile, related information such as disease types, disease parameters and the like can be manually input; the collected disease image is transmitted to an intelligent recognition system with an image recognition algorithm, the disease type is recognized by the image recognition algorithm, disease parameter information is extracted, the disease parameter information is compared with a set threshold value to obtain disease scale information, and then the information is transmitted to a server for data processing to generate a detection report.
Description
Technical Field
The invention belongs to the technical field of highway detection, and relates to a highway detection system and method integrating an unmanned aerial vehicle, a detection vehicle and a handheld detection terminal.
Background
With the rapid development of new infrastructure, the intelligent highway based on the human-vehicle-road-environment cooperation becomes the inevitable trend, and the infrastructures such as bridges, side slopes, tunnels, pavements and the like are used as the important components of the intelligent highway, so that the intelligent degree of maintenance management needs to follow the development trend and be adapted in the face of the huge storage and stable increment of the intelligent highway. Therefore, the development of industry transformation upgrading and treatment capacity is carried out by using emerging technologies such as Internet +, cloud computing, beidou, big data, internet of things, artificial intelligence and the like, and the method is an effective means for scientific and high-quality maintenance management.
Although the industry has advanced in the field of intelligence, the working mode of relying on traditional manual visual inspection and simple instrument measurement still dominates in the aspect of detection of road traffic infrastructure at present. The disadvantages of the conventional detection method mainly include the following points: 1) The report documents are manually detected, recorded and sorted, the efficiency is extremely low, and the error and leakage rate is very high; 2) Data scatter and poor utilization rate; 3) The cost is high, and the refinement degree is not enough; 4) The artificial detection has high danger and blind areas. With the continuous development of informatization, a series of detection systems are developed at present to effectively prompt the detection quality and efficiency, but still have many disadvantages, such as: detection software based on a mobile terminal only supports recording of appearance diseases of reachable positions, and is tedious and easy to miss and make mistakes; the unmanned aerial vehicle and the detection vehicle inspection system can only inspect the appearance defects of the bridge and the side slope, and need manual judgment for defects and data processing.
Disclosure of Invention
In view of this, the invention aims to provide a world-integrated highway detection system, which improves the efficiency of field detection and report arrangement and can be generally applied and popularized.
In order to achieve the purpose, the invention provides the following technical scheme:
a heaven and earth integrated highway detection system comprises a detection vehicle carrying an unmanned aerial vehicle take-off and landing airport, an unmanned aerial vehicle, a mobile detection terminal (such as a handheld detection terminal), an intelligent identification system and a server;
the detection vehicle is provided with a high-definition anti-shake camera for collecting disease images of a road surface and a roadside;
the unmanned aerial vehicle is provided with a high-definition anti-shake camera and is used for collecting disease images at high places or in areas where manpower cannot reach easily; the take-off and landing airport of the unmanned aerial vehicle is carried on the detection vehicle;
the mobile detection terminal (such as a handheld detection terminal) is provided with a high-definition anti-shake camera and is used for collecting disease images at positions where a road is hidden and where an unmanned aerial vehicle and a detection vehicle cannot reach; the mobile detection terminal can also manually and directly input related information such as disease types (such as damage, slippage and the like) and disease parameters (such as length, width, area and the like);
the detection vehicle, the unmanned aerial vehicle and the mobile detection terminal (such as a handheld detection terminal) transmit the acquired disease images to an intelligent identification system with an image identification algorithm, the disease types are identified and disease parameter information is extracted by the aid of the image identification algorithm, the disease parameter information is compared with a set threshold value to obtain disease scale information, and then the identified and extracted information is transmitted to a server for data processing to generate a detection report.
Further, disease image information that detection car can gather includes:
(1) pavement: cracks or pits in the road surface;
(2) bridge: damage, cracking and loss of the inner side of the guardrail and blockage of the expansion joint;
(3) tunneling: cracking and water seepage of the lining and damage of an access road;
(4) side slope and roadbed: collapse and loss of road edges and protection facilities and blockage of side ditches.
Further, the disease image information that the unmanned aerial vehicle can acquire includes:
(1) bridge: the main beam of the cable tower and the concrete (the clearance is more than or equal to 3 m), the bridge pier (the height is more than or equal to 3 m), the bridge abutment cracks, damages, exposed ribs, a honeycomb pitted surface, water erosion and scouring, the main beam of the stay cable, the main cable and the steel structure is rusted and deformed, the outer side of the guardrail is damaged and cracked, and the slope protection is cracked and collapsed;
(2) tunneling: cracking, water seepage or collapse of the hole opening and the hole door;
(3) side slope and roadbed: side slope landslide, scouring and collapse, blockage of side slope drainage ditches and road shoulder intercepting ditches and collapse of retaining walls.
Further, the disease image information that the mobile detection terminal (such as a handheld detection terminal) can collect includes:
(1) bridge: shearing and hollowing the support, cracking, damaging, exposing ribs, pitting surfaces of the concrete box girder, the cable tower and the bridge pier (the height is less than 3 m), corroding and scouring by water, and detecting other parts which cannot be detected by a detection vehicle and an unmanned aerial vehicle;
(2) tunneling: blockage of drainage facilities, and other parts which cannot be detected by the detection vehicle and the unmanned aerial vehicle;
(3) side slope and roadbed: other parts which cannot be detected by the detection vehicle and the unmanned aerial vehicle;
(4) road surface: other parts that detection car and unmanned aerial vehicle can't detect.
Further, the parameters for identifying and extracting the disease types by the image identification algorithm comprise the number, the length, the width or the area and the like.
Further, the image recognition algorithm recognizes threshold value ranges (a is less than scale and less than b) of different scale values of different disease types, the recognized parameter information is utilized to judge and recognize scale information of the diseases according to the threshold value ranges, the recognized parameter information is length and width, the width threshold value ranges are used as the judging standard, if a is less than width and less than b is scale 1, c is less than width and less than d is scale 2; the parameter information is identified as area, an area threshold range is used as a judgment standard, e is more than area and less than f is scale 1, g is more than area and less than h is scale 2.
Further, the image recognition algorithm identifies the disease type, and specifically comprises the following steps: carrying out disease identification and disease area positioning by adopting a YOLO target detection algorithm, rapidly detecting the position of a disease and judging the type of the disease; firstly, a Mosaic data enhancement method, SAT self-confrontation training and CmBN are added to an input layer of a YOLOv4 network model to expand a training data set; secondly, CSPDarknet53 is adopted in the main feature extraction network structure, jump connection in a residual error network ResNet is combined, the learning capacity of the convolutional neural network on target features is enhanced, the network is light in weight, and meanwhile, the detection accuracy is guaranteed; and after the batch normalization layer, the Mish activation function provided by Misra is used, so that the characteristic information of the target can be better extracted, and the detection precision of the target is improved.
Further, the image recognition algorithm extracts disease parameter information, and specifically comprises the following steps: firstly, obtaining a disease area positioned by a YOLOV4 model, then performing self-adaptive threshold segmentation on the disease edge extraction, performing coordinate system conversion on the segmented image, and finally obtaining the equivalent size of a pixel point, thereby calculating the parameters of the disease.
The invention has the beneficial effects that: the invention utilizes the rapidity and flexibility equipment such as the existing unmanned aerial vehicle and the existing detection vehicle, integrates an AI intelligent identification technology, can simultaneously carry out rapid disease detection and identification on a target area, and is matched with a handheld detection terminal to carry out manual data acquisition, the three work in cooperation to ensure that the detection is more comprehensive and more time-saving on the target area, the problems of inspection blind areas, insufficient fineness, scattered data and the like existing in a single detection mode are avoided, the efficiency and the accuracy of field detection are greatly improved, meanwhile, the system can complete the processing of the acquired data, and a disease detection report can be generated by manual rechecking, thereby greatly improving the information and intelligence level.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from 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 thereof.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a schematic view of an integrated air-ground detection system;
FIG. 2 is a flow chart of bridge defect type identification;
fig. 3 is a flow chart of bridge defect parameter extraction.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and embodiments may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; for a better explanation of the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
Referring to fig. 1 to 3, the invention provides a world-ground integrated detection system, wherein unmanned aerial vehicle take-off and landing airports, high-definition anti-shake cameras, intelligent identification terminals and other devices are carried on a detection vehicle, an AI image identification technology is integrated, and a handheld detection terminal is matched to complete detection and identification in a world-ground matching manner in a road traffic infrastructure (bridge, tunnel, slope and road surface) detection process. The system comprises a detection vehicle, high-definition anti-shake cameras, an unmanned aerial vehicle, a take-off and landing airport, an intelligent identification terminal, a handheld detection terminal, a server and the like, wherein the high-definition anti-shake cameras are installed in front of the detection vehicle, on the left side, the right side and above the detection vehicle and are used for photographing diseases during pavement and road detection; disease pictures shot by a detection vehicle and an unmanned aerial vehicle are transmitted to an intelligent recognition terminal, disease types (such as damage, slippage and the like) are recognized by an AI intelligent recognition technology, parameters (length, width, area and the like) are extracted, recognized defect information, parameter information and scale information are transmitted to a cloud server for data processing, and finally data confirmation and report generation are completed in server detection software.
The detection system can be applied to the detection of bridges, tunnels, slopes and pavements of highway traffic infrastructures.
1. The content that the detection system can detect and identify includes:
(1) The defect information which can be detected and identified by the detection vehicle comprises the following information:
(1) pavement: cracking of road surface, pits.
(2) Bridge: damage, cracking and loss of the guardrail (inner side) and blockage of the expansion joint.
(3) Tunneling: cracking and water seepage of the lining and damage of the access road.
(4) Side slope and roadbed: collapse and loss of road edges and protection facilities and blockage of side ditches.
(2) The defect information that the unmanned aerial vehicle can detect and identify includes:
(1) bridge: the main beam of the cable tower and the concrete (the clearance is more than or equal to 3 m), the pier (the height is more than or equal to 3 m), the bridge abutment cracks, damages, exposed ribs, a honeycomb pitted surface, water erosion and scouring, the main beam of the stay cable, the main cable and the steel structure is corroded and deformed, the guardrail (the outer side) is damaged and cracked, and the slope protection is cracked and collapsed.
(2) Tunneling: cracking, water seepage and collapse of the opening and the portal.
(3) Side slope and roadbed: side slope landslide, scouring and collapse, blockage of side slope drainage ditches and road shoulder intercepting ditches and collapse of retaining walls.
(3) The defect information which can be detected and identified by the handheld detection terminal comprises:
(1) bridge: the shearing and the emptying of the support, the cracking, the damage, the exposed ribs, the cellular pitted surface, the water erosion and the scouring of a concrete box girder (the inside and the clearance are less than 3 m), a cable tower (the inside), a pier (the height is less than 3 m), and other parts which cannot be detected by a detection vehicle and an unmanned aerial vehicle.
(2) Tunneling: the jam of drainage facility to and other positions that detection car and unmanned aerial vehicle can't detect.
(3) Side slope and roadbed: other parts that detection car and unmanned aerial vehicle can't detect.
(4) Pavement: other parts that detection car and unmanned aerial vehicle can't detect.
2. The parameter information that can be extracted to identify the defect type includes the number, length, width, area, etc. The specific defect type requires parameter information to be extracted, which is shown in table 1.
TABLE 1 Defect type parameter information
3. Presetting threshold value ranges (a is less than scale and less than b) of different scale values of different defect types, judging scale information of the identified diseases according to the threshold value ranges according to the identified parameter information, identifying the parameter information as length and width, taking the width threshold value ranges as judgment standards, and if a is less than width and less than b is scale 1, c is less than width and less than d is scale 2; the parameter information is identified as area, an area threshold range is used as a judgment standard, e < area < f is a scale 1, g < area < h is a scale 2.
4. Recognition algorithm for implanted image of intelligent recognition terminal
(1) Disease recognition algorithm model and method
And disease identification and disease area positioning are carried out by adopting a YOLO-based target detection algorithm, the position of the disease is rapidly detected, and the disease type is judged. Firstly, the YOLOv4 network model adds a Mosaic data enhancement method, SAT self-confrontation training, and CmBN to the input layer to expand the training data set. Secondly, CSPDarknet53 is adopted in the main feature extraction network structure, and jump connection in a residual error network ResNet is combined, so that the learning capacity of the convolutional neural network on target features is enhanced, the network is lightened, and the detection accuracy is ensured; and after the batch normalization layer, the Mish activation function provided by Misra is used, so that the characteristic information of the target can be better extracted, and the detection precision of the target is improved.
(2) Parameter extraction algorithm model and method
And acquiring disease parameter information in a depth information (RGB-D image) based mode. The RGB-D image refers to depth information including both a color image (RGB image) and an image, the image depth information refers to a distance from a midpoint in space to a camera, and the bridge defect parameter extraction flow is shown in fig. 2.
The disease area is positioned by a YOLOV4 model, and the extraction of the disease pixel parameters of honeycombs, peeling (breakage, corner falling and peeling), holes (holes and cavities), steel bar corrosion and the like is completed by using a digital image processing mode. After the edge extraction is carried out on the bridge diseases, the extraction of parameters such as the length, the width, the area and the like of the bridge diseases can be realized. The method for acquiring the bridge defect parameter information through the defect image mainly comprises the step of acquiring the equivalent size of a pixel point according to the image depth information. After the equivalent size of the pixel point is obtained, the parameters of the diseases can be calculated.
Finally, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A heaven-earth integrated highway detection system is characterized by comprising a detection vehicle carrying an unmanned aerial vehicle take-off and landing airport, an unmanned aerial vehicle, a mobile detection terminal, an intelligent identification system and a server;
the detection vehicle is provided with a high-definition anti-shake camera for collecting disease images of the road surface and the road side;
the unmanned aerial vehicle is provided with a high-definition anti-shake camera and is used for collecting disease images at high places or in areas where manpower is difficult to reach;
the mobile detection terminal is provided with a high-definition anti-shake camera and is used for collecting disease images at positions where a hidden road, an unmanned aerial vehicle and a detection vehicle cannot reach; the mobile detection terminal can also manually and directly input the disease type and the disease parameter;
the detection vehicle, the unmanned aerial vehicle and the mobile detection terminal transmit the acquired disease images to an intelligent recognition system with an image recognition algorithm, the disease types are recognized by the image recognition algorithm, disease parameter information is extracted, the disease parameter information is compared with a set threshold value to obtain disease scale information, and then the recognized and extracted information is transmitted to a server for data processing to generate a detection report.
2. The integrated heaven and earth road detection system according to claim 1, wherein the disease image information collected by the detection vehicle comprises:
(1) road surface: cracking or potholes in the pavement;
(2) bridge: damage, cracking and loss of the inner side of the guardrail and blockage of the expansion joint;
(3) tunneling: cracking and water seepage of the lining, and damage of an access road;
(4) side slope and roadbed: collapse and loss of road edges and protective facilities and blockage of side ditches.
3. The integrated heaven and earth road detection system according to claim 1, wherein the disease image information collected by the unmanned aerial vehicle comprises:
(1) bridge: cracking, damage, exposed ribs, cellular pitted surfaces, water erosion and scouring of cable towers, concrete girders, bridge piers and bridge abutments, corrosion and deformation of stay cables, main cables and steel structure girders, damage and cracking of the outer sides of guardrails and cracking and collapse of revetment;
(2) tunneling: cracking, water seepage or collapse of the hole opening and the hole door;
(3) side slope and roadbed: side slope landslide, scouring and collapse, blockage of side slope drainage ditches and road shoulder intercepting ditches and collapse of retaining walls.
4. The integrated heaven and earth road detection system according to claim 1, wherein the disease image information collected by the mobile detection terminal comprises:
(1) bridge: shearing and hollowing the support, cracking, damaging, exposing ribs, cellular pitted surface, water erosion and scouring of the interior of a concrete box girder, the interior of a cable tower and a pier, and other parts which cannot be detected by a detection vehicle and an unmanned aerial vehicle;
(2) tunneling: blockage of drainage facilities, and other parts which cannot be detected by the detection vehicle and the unmanned aerial vehicle;
(3) side slope and roadbed: other parts which cannot be detected by the detection vehicle and the unmanned aerial vehicle;
(4) pavement: other parts that detection car and unmanned aerial vehicle can't detect.
5. The integrated heaven and earth road detection system according to claim 1, wherein the parameters for identifying and extracting the disease type by the image recognition algorithm comprise number, length, width or area.
6. The integrated heaven and earth road detection system according to claim 1 or 5, wherein the image recognition algorithm identifies threshold ranges with different scale values for presetting different disease types, and judges scale information of the identified diseases according to the threshold ranges by using the identified parameter information, wherein the identified parameter information is of length and width, and the width threshold range is used as a judgment standard; the identification parameter information is area, and an area threshold range is used as a judgment standard.
7. The integrated heaven and earth road detection system of claim 1, wherein the image recognition algorithm identifies the disease type, and specifically comprises: carrying out disease identification and disease area positioning by adopting a YOLO-based target detection algorithm, detecting the position of a disease and judging the disease type of the disease; firstly, a Mosaic data enhancement method, SAT self-confrontation training and CmBN are added to an input layer of a YOLOv4 network model to expand a training data set; secondly, CSPDarknet53 is adopted in the main feature extraction network structure, and the learning capacity of the convolutional neural network on target features is enhanced by combining jump connection in a residual error network ResNet; and uses the Mish activation function proposed by Misra after the batch normalization layer.
8. The integrated heaven and earth road detection system according to claim 7, wherein the image recognition algorithm extracts disease parameter information, and specifically comprises: firstly, obtaining a disease area positioned by a YOLOV4 model, then carrying out self-adaptive threshold segmentation on the disease edge, carrying out coordinate system conversion on the segmented image, and finally obtaining the equivalent size of a pixel point, thereby calculating the parameters of the disease.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211209926.2A CN115575400A (en) | 2022-09-30 | 2022-09-30 | Heaven and earth integrated highway detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211209926.2A CN115575400A (en) | 2022-09-30 | 2022-09-30 | Heaven and earth integrated highway detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115575400A true CN115575400A (en) | 2023-01-06 |
Family
ID=84582647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211209926.2A Pending CN115575400A (en) | 2022-09-30 | 2022-09-30 | Heaven and earth integrated highway detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115575400A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953192A (en) * | 2024-01-09 | 2024-04-30 | 北京地铁建筑设施维护有限公司 | Ceiling disease early warning method and image acquisition equipment |
-
2022
- 2022-09-30 CN CN202211209926.2A patent/CN115575400A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953192A (en) * | 2024-01-09 | 2024-04-30 | 北京地铁建筑设施维护有限公司 | Ceiling disease early warning method and image acquisition equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors | |
| US10818003B2 (en) | High-precision intelligent detection method for bridge diseases based on spatial position | |
| Li et al. | Automatic defect detection of metro tunnel surfaces using a vision-based inspection system | |
| Koch et al. | A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure | |
| Gargoum et al. | Automated extraction of road features using LiDAR data: A review of LiDAR applications in transportation | |
| Ribeiro et al. | Remote inspection of RC structures using unmanned aerial vehicles and heuristic image processing | |
| CN103778681B (en) | A kind of vehicle-mounted highway cruising inspection system and data acquisition and disposal route | |
| CN109190481B (en) | Method and system for extracting road material of remote sensing image | |
| CN107944377B (en) | Traffic infrastructure safety monitoring method and system | |
| CN115575400A (en) | Heaven and earth integrated highway detection system and method | |
| Li et al. | RoadID: a dedicated deep convolutional neural network for multipavement distress detection | |
| Dong et al. | Intelligent segmentation and measurement model for asphalt road cracks based on modified mask R-CNN algorithm | |
| Chen et al. | A feasibility study on use of generic mobile laser scanning system for detecting asphalt pavement cracks | |
| CN116484259A (en) | Urban pipe network defect position positioning analysis method and system | |
| CN113312987B (en) | Recognition method based on unmanned aerial vehicle road surface crack image | |
| CN117474870B (en) | Road pavement crack identification decision-making method and system based on big data screening | |
| Shin et al. | Defect-detection model for underground parking lots using image object-detection method | |
| Kulambayev et al. | Real-time road surface damage detection framework based on mask r-cnn model | |
| CN116242774A (en) | Light three-dimensional detection method and device suitable for rural highways | |
| CN113920051A (en) | Standardized batch processing method, system and medium for structure appearance disease detection data | |
| Perry et al. | Unmanned aerial vehicle (UAV)-enabled bridge inspection framework | |
| CN111595859A (en) | Bridge and culvert damage detection method and damage detection and management system | |
| Truong-Hong et al. | Automatic bridge deck damage using low cost UAV-based images | |
| Wei et al. | Deep learning-based automatic detection and evaluation on concrete surface bugholes | |
| Chen et al. | Deep learning based weak inter-layers segmentation and measurement of rock tunnel face |
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 |