CN113240675A - Lining scanning detection method and system combining front camera and rear camera - Google Patents
Lining scanning detection method and system combining front camera and rear camera Download PDFInfo
- Publication number
- CN113240675A CN113240675A CN202110782104.2A CN202110782104A CN113240675A CN 113240675 A CN113240675 A CN 113240675A CN 202110782104 A CN202110782104 A CN 202110782104A CN 113240675 A CN113240675 A CN 113240675A
- Authority
- CN
- China
- Prior art keywords
- scanning
- camera
- defect
- rear camera
- lining
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- G01N2021/8854—Grading and classifying of flaws
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
Abstract
The invention provides a lining scanning detection method combining front and rear cameras, which comprises the following steps: continuously scanning all tunnel surfaces through a front camera arranged at the front part of the detection vehicle; analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect score, and judging whether the defect is a suspected disease defect according to the defect score; when the suspected disease defect is judged, triggering a rear camera to start scanning the suspected disease defect; and analyzing the defects of the post-scanning image data obtained by scanning the post-camera, and scoring and marking the defects of the diseases. The invention adopts the technologies of pre-camera scanning rough processing and post-camera high-performance complementary shooting fine processing, can meet the continuous detection requirement when the detection vehicle travels at high speed, can position the fault parameters such as lining diseases and the like at high precision, reduces the requirement of data storage space, reduces the requirement of image post-processing, and can realize the real-time processing and display of result data.
Description
Technical Field
The invention relates to the technical field of computer network security, in particular to an automatic penetration testing system and method based on a state machine.
Background
The tunnel lining disease detection method comprises a manual detection method and an automatic detection method, wherein the manual detection method is low in efficiency and high in labor intensity, is mainly used before the tunnel is built, and is inconvenient to use due to the limitation of skylight time when the tunnel is operated.
The high-definition linear array camera is a lining defect automatic detection method mainly used at present, and has the characteristics of high test efficiency and high precision. The principle is that a scanning light source is used for illuminating the surface of the tunnel lining, a high-definition linear array camera is used for scanning images, and the acquired images are analyzed, analyzed and evaluated by computer processing analysis and evaluation software and the like to analyze, process and extract the defect parameters of the tunnel lining and evaluate the danger level.
The general case of tunnel lining detection has the following requirements: 1, the running speed of a detection vehicle can reach more than 120 km/h; 2, the defect resolution of the detection system is required to be more than 0.2 mm; 3 can be continuously detected.
The current lining detection method using a high-definition linear array camera is difficult to meet the requirements of high-speed traveling, high detection resolution and sustainability of a detection vehicle.
Disclosure of Invention
Aiming at the problems that the lining image detected by the existing measuring method cannot meet the requirements of high-speed testing, high precision and sustainability at the same time, the test result is difficult to analyze in real time by testing data, and the workload of image data post-processing is also large due to large image data amount, the invention adopts the technology of pre-camera scanning rough processing combined with post-high performance camera compensation fine processing, can meet the requirements of high-speed testing, high precision and sustainability at the same time, can process and analyze the measured data in real time, and can output the test result on site, thereby reducing the requirements of data storage and post-processing.
The embodiment of the invention provides a lining scanning detection method combining front and rear cameras, which comprises the following steps:
continuously scanning all tunnel surfaces through a front camera arranged at the front part of the detection vehicle;
analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect score, and judging whether the defect is a suspected disease defect according to the defect score;
triggering a rear camera to start scanning when the suspected disease defect is judged;
and analyzing the defects of the post-scanning image data obtained by scanning the post-camera, and scoring and marking the defects of the diseases.
The lining scanning detection method combining the front camera and the rear camera further comprises the following steps:
and storing the post-scanning image data in a computer or storing the post-scanning image data in a hard disk after compression.
The lining scanning detection method combining the front camera and the rear camera further comprises the following steps: and storing the disease defect picture generated after analysis and treatment for subsequent extraction and query.
In the lining scanning detection method combining the front camera and the rear camera, the rear camera is arranged behind the front camera, the time when the part suspected of being damaged reaches the rear camera is calculated according to the distance length between the rear camera and the front camera and the advancing speed of a detection vehicle, and the rear camera is triggered to scan before the time; and after the rear camera starts scanning, the position encoder signal is used as a continuous scanning trigger signal, and the scanning of the rear camera is finished after the scanning continuous interval length reaches the preset time.
The lining scanning detection method combining the front camera and the rear camera further comprises the following steps: and if the number of suspected disease defects continuously detected by the front camera exceeds a threshold value, recalculating the preset time scanned by the rear camera.
According to another aspect of the invention, a lining scanning detection system with a front camera and a rear camera combined is also provided, and comprises a front camera, a rear camera and a control module, wherein the front camera is arranged at the front part of a detection vehicle and is used for continuously scanning all tunnel surfaces; the control module is used for analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect fraction, judging whether the defect is a suspected disease defect according to the defect fraction, and triggering the post-camera to start scanning when the defect is judged to be the suspected disease defect; and the system is also used for carrying out defect analysis on post-scanning image data obtained by scanning the post-camera and scoring and marking the defect of the disease.
In the lining scanning detection system with the front camera and the rear camera combined, the control module is also used for storing the rear scanning image data in a computer or storing the compressed rear scanning image data in a hard disk.
In the lining scanning detection system with the combination of the front camera and the rear camera, the control module is also used for storing the disease defect picture generated after the analysis and the processing for subsequent extraction and query.
In the lining scanning detection system with the combined front camera and the rear camera, which is provided by the invention, the rear camera is arranged behind the front camera, the control module calculates the time when the part suspected of being damaged reaches the rear camera according to the distance length between the rear camera and the front camera and the advancing speed of a detection vehicle, and triggers the rear camera to scan before the time; and after the rear camera starts scanning, the position encoder signal is used as a continuous scanning trigger signal, and the scanning of the rear camera is finished after the scanning continuous interval length reaches the preset time.
In the lining scanning detection system with the front camera and the rear camera combined, the control module is further configured to recalculate the preset time for scanning by the rear camera when the number of suspected disease defects continuously detected by the front camera exceeds a threshold.
The embodiment of the invention has the following beneficial effects: the invention provides a lining disease image detection method combining lower-resolution full-coverage image scanning with key suspected area partial-coverage high-resolution scanning. The mechanism can centralize the scanning interval of the rear high-definition high-speed camera to the position of suspected disease defect, avoids high-definition scanning on the common non-suspected defect position, ensures that the rear high-definition camera does not need to continuously scan, and only needs to scan a small part of suspected disease area for a short time. Because continuous scanning is not needed, the rear camera can continuously transmit the collected data to clear the data cache by utilizing the scanning interval, and the system can process and analyze the scanning data in the scanning interval, so that the test can be continuously carried out, the test result can be timely obtained, and the subsequent image data needing to be processed is greatly reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating lining scanning detection by a front camera and a rear camera according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problems that the existing measuring method for detecting the lining image cannot meet the requirements of high-speed testing, high precision and sustainability at the same time, the testing result is difficult to analyze in real time the testing data, and the image data amount is large, so that the post-processing workload of the image data is also large, the invention aims to provide a lining scanning detection method combining front and rear cameras, and the core idea is as follows: the scheme that a front camera and a rear camera of a detection vehicle are arranged in a double mode is adopted, the front camera adopts a camera with lower resolution and lower scanning speed to continuously scan and shoot, continuous real-time analysis is easy to realize due to lower data volume, the degree of suspected lining diseases is scored, and the score is used for deciding whether the rear high-resolution high-speed camera triggers scanning or not; the scanning result of the rear camera is more precise, a high-definition image can be obtained, and the lining disease condition can be accurately positioned and measured, but the data volume scanned by the rear camera is large, the performance requirement can be met only in a short time, and the scanning cannot be continued for a long time. The front camera is arranged at the front part of the test vehicle, continuous acquisition is carried out during traveling, all tunnel surfaces are covered, test data are processed in real time, whether suspected diseases exist or not is judged, and the rear high-definition camera is triggered to take a picture if the suspected diseases exist.
Fig. 1 is a flowchart illustrating a lining scanning detection method by combining front and rear cameras according to an embodiment of the present invention, where it should be noted that step logics in the flowchart have a sequential relationship, and that the execution of the steps is performed in parallel, and multiple steps may be executed simultaneously. As shown in fig. 1, the lining scanning detection method with front and back cameras combined provided by the invention comprises the following steps:
step S1, continuously scanning all tunnel surfaces through a front camera arranged at the front part of the detection vehicle;
specifically, in the invention, the resolution and sampling rate required by the front camera are low, continuous scanning is required, and the detected surface of the whole tunnel is covered, and a linear array camera with low rate and resolution can be selected, and a small number of cameras are used for full coverage. Because the resolution and sampling rate of the selected front-facing camera are general, the data volume of the step is general, the occupied system processing resource is less, the step can be ensured to be continuously carried out under high priority, and the scanned image is timely stored in a hard disk to prevent loss. Since the camera performance is not large in general data traffic, the data processing and transmission bottleneck does not occur in the step.
Step S2, analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect score, and judging whether the defect is a suspected disease defect according to the defect score;
specifically, in the invention, the defect score needs to be analyzed and evaluated in real time, can be ensured to be continuously carried out under high priority, and is used as a trigger basis for subsequent high-definition high-speed camera image scanning. The defect score criteria cannot be too high, which easily misses a minor failure; nor too low, which would add a large amount of defect-free collected data, resulting in a data collection bottleneck. The performance of the image analysis algorithm determines the processing resources required, and a high-performance simplified algorithm is required to evaluate the possibility of defects in order to guarantee real-time performance.
Step S3, when the suspected disease defect is judged, triggering a rear camera to start scanning;
specifically, in the invention, the rear camera is arranged at a certain distance behind the front camera, the distance length and the traveling speed of the detection vehicle are known in advance, the time when the suspected disease defect reaches the camera can be calculated, the time is advanced by a certain margin and is taken as the trigger time for starting scanning of the camera, the position encoder signal is taken as the continuous scanning trigger signal after the camera starts scanning, the interval length of continuous scanning can be set as a fixed value, and the camera scanning is finished after the fixed value is reached. If the front camera continuously detects that the suspected defects exceed the standard in the camera scanning process, the position of the camera for finishing scanning is recalculated, and the scanning interval is prolonged according to the updated position. If the continuous scanning interval is too long and the cache is insufficient, the scanning data with high suspected defect degree is preferentially reserved, and the scanning steps or data with low suspected defect degree are discarded. The camera scanning triggering step has low requirements on system performance, can adopt high priority to ensure real-time performance and ensure that the camera can reliably trigger scanning action according to the position on time.
And step S4, storing the post-scanning image data in a computer or compressing and storing the post-scanning image data in a hard disk.
Specifically, in the invention, post-scan image data is transferred from the camera to the computer memory in time for subsequent image processing, and data loss caused by overflow of the camera buffer space is prevented. The step occupies large system resources, adopts middle-high priority, generally has no too long duration, can cause partial data overflow and loss when the duration is too long, and can avoid the problem of data overflow caused by too long continuous scanning time by reasonably setting parameters of the scanning triggering step of the front camera.
Furthermore, the method can also comprise an image compression step, which can greatly reduce the occupied space of data and reduce the requirement of data storage on the bandwidth of a storage device, but greatly consumes the real-time processing performance of the system, and the compressed image is transferred from the system cache to the hard disk for long-term storage. In order to guarantee the real-time performance of the compression step, a system needs to use a high-performance multi-core processor to process image compression in parallel.
And step S5, carrying out defect analysis on post-scanning image data obtained by scanning the post-camera, and scoring and marking the defect of the disease.
Specifically, in the invention, image data is extracted from a memory or a hard disk, defect analysis is carried out, suspected disease defects are scored and labeled, and pictures generated after analysis processing are additionally stored for subsequent extraction and query. This step requires a large amount of system computing resources, but the real-time requirement is low, so the setting is run at a low priority and is executed when the system is rich in processing resources.
And step S6, displaying the detection image scanning analysis results of the front camera and the rear camera.
The invention provides a lining disease image detection method combining lower-resolution full-coverage image scanning with key suspected area partial-coverage high-resolution scanning. The mechanism can centralize the scanning interval of the rear high-definition high-speed camera to the position of suspected disease defect, avoids high-definition scanning on the common non-suspected defect position, ensures that the rear high-definition camera does not need to continuously scan, and only needs to scan a small part of suspected disease area for a short time. Because continuous scanning is not needed, the rear camera can continuously transmit the collected data to clear the data cache by utilizing the scanning interval, and the system can process and analyze the scanning data in the scanning interval, so that the test can be continuously carried out, the test result can be timely obtained, and the subsequent image data needing to be processed is greatly reduced.
Based on the same invention concept, the invention also discloses a lining scanning detection system with the front camera and the rear camera combined, which comprises a front camera, a rear camera and a control module, wherein the front camera, the rear camera and the control module are arranged at the front part of the detection vehicle. The front-end camera needs low resolution and sampling rate, needs continuous scanning and covers the detected surface of the whole tunnel, and can select a linear array camera with low rate and resolution and use a small number of cameras for full coverage. The rear camera needs to be fully covered by a high-definition high-speed linear array camera, and the number of the cameras is large.
Specifically, the control module is used for analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect fraction, judging whether the defect is a suspected disease defect according to the defect fraction, and triggering the post-camera to start scanning the suspected disease defect when the defect is judged to be the suspected disease defect; storing the post-scanning image data into a computer or storing the post-scanning image data into a hard disk after compression; the system is also used for carrying out defect analysis on post-scanning image data obtained by scanning of the post-camera, and scoring and marking the defect of the disease; and storing the disease defect picture generated after analysis and treatment for subsequent extraction and query.
Further, the rear camera is arranged behind the front camera, the control module calculates the time when the part suspected of being damaged reaches the rear camera according to the distance length between the rear camera and the front camera and the advancing speed of the detection vehicle, and the rear camera is triggered to scan before the time; after the rear camera starts scanning, taking a position encoder signal as a continuous scanning trigger signal, and finishing the scanning of the rear camera after the scanning duration interval length reaches the preset time; and when the number of suspected disease defects continuously detected by the front camera exceeds a threshold value, recalculating the preset time scanned by the rear camera.
It should be noted that the above description of the various modules is divided into these modules for clarity of illustration. However, in actual implementation, the boundaries of the various modules may be fuzzy. For example, any or all of the functional modules herein may share various hardware and/or software elements. Also for example, any and/or all of the functional modules herein may be implemented in whole or in part by a common processor executing software instructions. Additionally, various software sub-modules executed by one or more processors may be shared among the various software modules. Accordingly, the scope of the present invention is not limited by the mandatory boundaries between the various hardware and/or software elements, unless explicitly claimed otherwise.
Embodiments of the present invention also provide a non-transitory computer storage medium storing computer-executable instructions that can execute the method for automated penetration testing based on a state machine as described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM) > Random Access Memory (RAM) > Flash Memory > Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid-State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a Random Access Memory (RAM), or the like.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A lining scanning detection method combining front and rear cameras is characterized by comprising the following steps:
continuously scanning all tunnel surfaces through a front camera arranged at the front part of the detection vehicle;
analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect score, and judging whether the defect is a suspected disease defect according to the defect score;
when the suspected disease defect is judged, triggering a rear camera to start scanning the suspected disease defect;
and analyzing the defects of the post-scanning image data obtained by scanning the post-camera, and scoring and marking the defects of the diseases.
2. The lining scanning detection method combining the front camera and the rear camera according to claim 1, further comprising:
and storing the post-scanning image data in a computer or storing the post-scanning image data in a hard disk after compression.
3. The lining scanning detection method combining the front camera and the rear camera according to claim 1, further comprising: and storing the disease defect picture generated after analysis and treatment for subsequent extraction and query.
4. The lining scanning detection method combining the front camera and the rear camera according to claim 1, wherein the rear camera is arranged behind the front camera, the time when the part suspected of being damaged reaches the rear camera is calculated according to the distance length between the rear camera and the front camera and the advancing speed of the detection vehicle, and the scanning of the rear camera is triggered before the time; and after the rear camera starts scanning, the position encoder signal is used as a continuous scanning trigger signal, and the scanning of the rear camera is finished after the scanning continuous interval length reaches the preset time.
5. The lining scanning detection method combining the front camera and the rear camera according to claim 4, further comprising: and if the number of suspected disease defects continuously detected by the front camera exceeds a threshold value, recalculating the preset time scanned by the rear camera.
6. A lining scanning detection system combining a front camera and a rear camera is characterized by comprising a front camera, a rear camera and a control module, wherein the front camera, the rear camera and the control module are arranged at the front part of a detection vehicle, and the front camera is used for continuously scanning all tunnel surfaces; the control module is used for analyzing the pre-scanning image data obtained by scanning the pre-camera in real time, evaluating a defect fraction, judging whether the defect is a suspected disease defect according to the defect fraction, and triggering the post-camera to start scanning the part of the suspected disease defect when the defect is judged to be the suspected disease defect; and the system is also used for carrying out defect analysis on post-scanning image data obtained by scanning the post-camera and scoring and marking the defect of the disease.
7. The lining scanning detection system with the combination of the front camera and the rear camera as recited in claim 6, wherein the control module is further configured to save the post-scan image data to a computer or to save the post-scan image data to a hard disk after compression.
8. The lining scanning detection system with the combination of the front camera and the rear camera as recited in claim 6, wherein the control module is further configured to store the disease defect picture generated after the analysis processing for subsequent extraction and query.
9. The lining scanning detection system combining the front camera and the rear camera according to claim 6, wherein the rear camera is arranged behind the front camera, the control module calculates the time when the part suspected of being damaged reaches the rear camera according to the distance length between the rear camera and the front camera and the advancing speed of the detection vehicle, and triggers the rear camera to scan before the time; and after the rear camera starts scanning, the position encoder signal is used as a continuous scanning trigger signal, and the scanning of the rear camera is finished after the scanning continuous interval length reaches the preset time.
10. The system of claim 9, wherein the control module is further configured to recalculate the preset time for scanning by the rear camera when the number of suspected defects detected by the front camera continuously exceeds a threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110782104.2A CN113240675B (en) | 2021-07-12 | 2021-07-12 | Lining scanning detection method and system combining front camera and rear camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110782104.2A CN113240675B (en) | 2021-07-12 | 2021-07-12 | Lining scanning detection method and system combining front camera and rear camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113240675A true CN113240675A (en) | 2021-08-10 |
| CN113240675B CN113240675B (en) | 2021-11-30 |
Family
ID=77135248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110782104.2A Active CN113240675B (en) | 2021-07-12 | 2021-07-12 | Lining scanning detection method and system combining front camera and rear camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240675B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1508535A (en) * | 2002-12-20 | 2004-06-30 | 宝山钢铁股份有限公司 | Scanning land steel surface detercting method and apparatus |
| CN102941864A (en) * | 2012-11-09 | 2013-02-27 | 武汉翔翼科技有限公司 | Train loading state high-definition monitoring and overloading detection method |
| CN104048969A (en) * | 2014-06-19 | 2014-09-17 | 樊晓东 | Tunnel defect recognition method |
| CN205382956U (en) * | 2016-01-19 | 2016-07-13 | 湖南华宏铁路高新科技开发有限公司 | Railway tunnel wall detection device based on image |
| CN111562220A (en) * | 2020-06-02 | 2020-08-21 | 吉林大学 | Rapid and intelligent detection method for bridge diseases |
| CN111674412A (en) * | 2020-06-30 | 2020-09-18 | 爱德森（厦门）电子有限公司 | Steel rail flaw detection vehicle with data networking sharing function and connection method thereof |
| EP3816857A1 (en) * | 2019-11-04 | 2021-05-05 | TOMRA Sorting GmbH | Neural network for bulk sorting |
-
2021
- 2021-07-12 CN CN202110782104.2A patent/CN113240675B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1508535A (en) * | 2002-12-20 | 2004-06-30 | 宝山钢铁股份有限公司 | Scanning land steel surface detercting method and apparatus |
| CN102941864A (en) * | 2012-11-09 | 2013-02-27 | 武汉翔翼科技有限公司 | Train loading state high-definition monitoring and overloading detection method |
| CN104048969A (en) * | 2014-06-19 | 2014-09-17 | 樊晓东 | Tunnel defect recognition method |
| CN205382956U (en) * | 2016-01-19 | 2016-07-13 | 湖南华宏铁路高新科技开发有限公司 | Railway tunnel wall detection device based on image |
| EP3816857A1 (en) * | 2019-11-04 | 2021-05-05 | TOMRA Sorting GmbH | Neural network for bulk sorting |
| CN111562220A (en) * | 2020-06-02 | 2020-08-21 | 吉林大学 | Rapid and intelligent detection method for bridge diseases |
| CN111674412A (en) * | 2020-06-30 | 2020-09-18 | 爱德森（厦门）电子有限公司 | Steel rail flaw detection vehicle with data networking sharing function and connection method thereof |
Non-Patent Citations (4)
| Title |
|---|
| 李庆桐 等: "隧道衬砌图像清晰度影响因素的模型试验研究", 《岩石力学与工程学报》 * |
| 杨俊: "公路隧道结构快速检测车综述", 《华东交通大学学报》 * |
| 王华夏: "高速铁路隧道衬砌裂缝自动化检测硬件系统研究", 《铁道标准设计 隧道/地下工程》 * |
| 王耀东: "基于局部图像纹理计算的隧道裂缝视觉检测技术", 《铁道学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113240675B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569699B (en) | Method and device for carrying out target sampling on picture | |
| CN110910655A (en) | Parking management method, device and equipment | |
| CN102590330A (en) | Image processing-based magnetic particle inspection defect intelligent identification detection system | |
| CN109446967B (en) | Face detection method and system based on compressed information | |
| CN111695493B (en) | Method and system for detecting hidden danger of power transmission line | |
| CN113240675B (en) | Lining scanning detection method and system combining front camera and rear camera | |
| CN107564018A (en) | It is a kind of to utilize the method for improving iterative algorithm extraction target image | |
| CN108961316A (en) | Image processing method, device and server | |
| CN105554414A (en) | Strong light inhibition method and device | |
| CN112673801A (en) | On-line detection method and system for broken impurities of grain combine harvester | |
| CN112289032B (en) | Automatic inspection method for unmanned aerial vehicle expressway | |
| CN106683113B (en) | Feature point tracking method and device | |
| CN113218957B (en) | Tunnel lining crack scanning detection method and system combining geological radar with high-speed linear array camera | |
| CN109934126B (en) | Vehicle tail smoke detection method and system | |
| US20210374383A1 (en) | Method and apparatus for determining temporal behaviour of an object | |
| WO2023060885A1 (en) | Rope defect detection method, terminal device, computer storage medium and computer program product | |
| CN111626104A (en) | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery | |
| CN112017441A (en) | Vehicle traffic behavior detection method, device, equipment and storage medium | |
| CN111860289B (en) | Time sequence action detection method and device and computer equipment | |
| CN115291243A (en) | Laser radar three-dimensional reconstruction method and device, electronic equipment and storage medium | |
| US20110141304A1 (en) | Electronic camera | |
| CN104504732A (en) | Video content retrieval method based on key frame extraction | |
| CN112288675A (en) | Vehicle-mounted contact net component imaging processing method | |
| CN108931526B (en) | Band steel surface defect detection method based on multi-task scheduling mechanism | |
| CN117197131B (en) | Method and apparatus for conveyor belt tear identification and computing device |
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 |