CN109688388B - All-dimensional real-time monitoring method using tunnel inspection robot - Google Patents
All-dimensional real-time monitoring method using tunnel inspection robot Download PDFInfo
- Publication number
- CN109688388B CN109688388B CN201910099459.4A CN201910099459A CN109688388B CN 109688388 B CN109688388 B CN 109688388B CN 201910099459 A CN201910099459 A CN 201910099459A CN 109688388 B CN109688388 B CN 109688388B
- Authority
- CN
- China
- Prior art keywords
- module
- tunnel
- instruction
- monitoring
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
- G08G1/054—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed photographing overspeeding vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Abstract
The invention discloses a method for omnibearing real-time monitoring by using a tunnel inspection robot, which comprises the steps of 1, sending an instruction; step 2, the tunnel inspection robot receives the instruction and then carries out real-time all-around monitoring on the interior of the tunnel, and the tunnel inspection robot realizes all-around real-time monitoring of the tunnel through each carried module, including illegal driving, traffic accidents, vehicle congestion, road foreign matters and the like, so that tunnel abnormity and illegal conditions can be timely found and timely processed, the supervision cost of the tunnel is reduced, the supervision efficiency is improved, the passing efficiency rate of the tunnel is guaranteed, and the safety of the tunnel is improved.
Description
Technical Field
The invention relates to the technical field of tunnel detection, in particular to an all-dimensional real-time monitoring method using a tunnel inspection robot.
Background
The tunnel is an important section of road traffic, which carries most vehicles on the road, and the safety of tunnel traffic is always one of the focuses of attention of traffic control departments. Along with the development of city construction, the city scale is enlarged and the traffic pressure is increased in recent years! In urban municipal engineering projects, the quantity and scale of urban traffic tunnels and high-speed traffic tunnels are continuously increased, and the tunnel operation safety is increasingly aroused by people to attach importance! Illegal lane change in the tunnel, the hypervelocity, low-speed, phenomenon such as rubbish is shed at will frequently takes place, sets up wall infiltration scheduling problem in the tunnel and also can arouse the traffic accident, consequently, the control in the tunnel needs great manpower and material resources, and the maintenance cost is higher, and manpower control also can't in time discover the illegal and abnormal conditions in the tunnel sometimes simultaneously, leads to many problems and the illegal condition can't in time be handled for there is very high potential safety hazard in the tunnel.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the method for comprehensively monitoring the tunnel inspection robot in real time, which can effectively detect abnormal conditions including violation of regulations, water seepage and the like in the tunnel, and simultaneously remind vehicles coming and going, thereby ensuring the safety of the tunnel and reducing the labor cost.
In order to solve the technical problems, the invention solves the technical problems by the following technical scheme: a method for omnibearing real-time monitoring by using a tunnel inspection robot comprises the following steps: step 1, sending an instruction; and 2, the tunnel inspection robot receives the instruction and then carries out real-time all-around monitoring on the interior of the tunnel.
In the above scheme, the inspection module comprises a main control module, a voice module, a communication module, a power module, a motion module, a monitoring module and a holder.
In the above scheme, the monitoring module comprises a 3D laser radar, a thermal external imaging device, a camera set and a snapshot machine.
In the scheme, in the step 1, the sending instruction comprises a main control module in the inspection module sending a motion instruction to the motion module, and sending a foreign matter detection instruction, an illegal snapshot instruction, a water seepage detection instruction and a high-definition image acquisition instruction to the monitoring module.
In the scheme, in the step 2, the motion module receives the motion instruction and then drives the tunnel inspection robot to run along the track laid in the tunnel, and each module starts to act to complete all-dimensional real-time monitoring in the tunnel.
In the above solution, the executing the foreign object detection instruction includes the following steps: collecting monitoring data: monitoring the passing lower road surface by the 3D laser radar, and acquiring original point cloud data in a road surface environment; analyzing the monitoring condition; processing the original point cloud data obtained in the second step, obtaining a data model, judging whether abnormal information exists or not, and confirming the abnormal information condition; and the polling result responds: and responding according to the abnormal information.
In the scheme, the execution of the illegal snapshot instruction is completed through the snapshot machine.
In the above scheme, the executing of the water seepage detection instruction comprises the following steps: continuously taking pictures: when a thermal imager in the thermal imaging device moves along with the inspection robot, continuously taking pictures of the passing wall surface; and (3) image conversion treatment: converting and binarizing the obtained infrared image, and establishing a gray threshold block; image analysis: detecting whether a water seepage area exists or not through a threshold block value; water seepage alarm: if the water seepage is detected, a signal is sent to the main control module, and the main control module sends an alarm by sending an instruction to the operation end and the voice module.
In the above scheme, the executing of the high-definition image acquisition instruction comprises the following steps: primary calibration of the inspection device; a main control module in the inspection device sends an image acquisition instruction to a high-definition imaging component; initializing a high-definition imaging component; drawing by a high-definition imaging assembly; processing after the high-definition imaging assembly acquires the image; and outputting the panoramic image.
Compared with the prior art, the invention has the following beneficial effects: the tunnel inspection robot realizes the all-round real time monitoring in tunnel through each module that carries on, including the condition such as illegal travel, traffic accident, vehicle are crowded, road surface foreign matter to reach the tunnel unusual with the timely discovery and the timely processing of illegal condition, reduced the supervision cost in tunnel, improved supervision efficiency, guaranteed the current efficiency rate in tunnel, improved the security in tunnel.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is described in further detail below with reference to fig. 1 and the specific embodiments.
A method for omnibearing real-time monitoring by using a tunnel inspection robot comprises the following steps: step 1, sending an instruction; the tunnel inspection robot starts self-checking after being started, a main control module in an inspection module sends a motion instruction to a motion module and sends a foreign matter detection instruction, an illegal snapshot instruction, a water seepage detection instruction and a high-definition image acquisition instruction to a monitoring module, the inspection module comprises a main control module, a voice module, a communication module, a power supply module, a motion module, a monitoring module and a holder, and the monitoring module comprises a 3D laser radar, a thermal external imaging device, a camera set and a snapshot machine; and 2, analyzing the received instruction by the built-in inspection module of the tunnel inspection robot and carrying out real-time all-dimensional monitoring on the inside of the tunnel.
When a foreign matter detection monitoring instruction is received, the 3D laser radar monitors the passing lower road surface and acquires original point cloud data in the road surface environment; carrying out pose transformation and clustering segmentation on the collected original point cloud data, and filtering out point cloud data outside the road surface edge to obtain point cloud data only with road surface information; secondly, the point cloud data after processing is analyzed by an information processing device arranged in the 3D laser radar, when a data model is identified, the 3D laser radar transmits the identified specific model characteristics to model data which are trained in a deep learning module in advance for comparison, and in a tunnel, bicycles and pedestrians are not allowed to appear in the tunnel, so that the bicycles and the pedestrians are classified as foreign body models during deep learning, and therefore, when the identified data model is the bicycles and the pedestrians, the foreign bodies can be directly judged after the model data comparison; when the detected foreign matter is a bicycle or a pedestrian, an alarm switch in the monitoring module is triggered, meanwhile, the monitoring module sends an alarm signal to the main control module, the main control module controls the communication module to send the alarm signal to the background control end, sends a play signal to the voice module, plays early warning voice, or remotely calls through the voice module to remind people or a cyclist to leave, and turns off the alarm after leaving, if the calling people or the bicycle do not leave, a processor is dispatched to the site to process, and the alarm is turned off after the processing is finished; if the data model at the identification position is an automobile, the 3D laser radar transmits the identified automobile model to model data which are trained in a deep learning module in advance, the 3D laser radar continuously tracks the running speed of the automobile, and when the speed of all the automobiles in the detection area is lower than 3-6 km/h, the abnormal condition is judged to be traffic jam; triggering an alarm switch in the monitoring module, simultaneously sending an alarm signal to the main control module by the monitoring module, controlling the communication module to send the alarm signal to the background control end by the main control module, sending a play signal to the voice module, playing early warning voice, simultaneously shooting a foreign object point by a holder, and waiting for related personnel to carry out traffic guidance or field processing; if the data model at the identification position is an undefined object, the 3D laser radar transmits the undefined object model to model data which are trained in a deep learning module in advance, the 3D laser radar continuously tracks the speed of the undefined object, when the speed is lower than a set threshold value, the foreign object is judged, and the threshold value period is 0-5 km/h; when the detected foreign matters are undefined objects, the pan-tilt camera is automatically rotated according to the undefined object positions to shoot the foreign matter points, the remote control end checks details of the foreign matters according to shooting conditions, when the foreign matters are small objects and cannot cause great influence on traffic, the alarm is remotely turned off, and the inspection device continues to inspect along the guide rail; if the foreign matter is a large object, the potential safety hazard is judged to exist, the traffic is seriously affected, the alarm is continuously given out, treating personnel are dispatched to the site to be treated, and the alarm is closed after the treatment is finished.
When an illegal snapshot monitoring instruction is received, the snapshot machine judges whether a scanning vehicle accords with overspeed, illegal lane change and overtaking through built-in defined parameters, illegal parking parameters are met, if yes, information is fed back to a processing module in the main snapshot machine, the processing module processes the information and then sends the processed information to a main control module, the master control module controls the snapshot machine and a cloud platform to work, the snapshot machine takes a snapshot of illegal photos, and the cloud platform starts to record illegal video evidences.
When a water seepage detection instruction is received: when a thermal imager in the thermal imaging device moves along with the inspection robot, continuously taking pictures of the passing wall surface; firstly, converting an acquired infrared image into a gray level image, carrying out binarization processing, then establishing a gray level threshold block, setting the size of the threshold block according to acquired data, sliding line by line, when the threshold block slides to a certain position to detect abnormality, carrying out multi-neighborhood sliding to judge whether the threshold block is false detection, if the neighborhood abnormality value of the abnormal area reaches a preset parameter value, judging that the position has a water leakage phenomenon, sending a signal to a main control module, and sending an instruction to an operation end and a voice module by the main control module to send an alarm; and if the sliding is continued until the tail end of the last row is reached, namely the whole image is detected completely and no abnormal area is found, continuing to take the next image and repeating the detection.
When the high-definition image acquisition instruction is received: when the inspection device is initially installed and started, initial calibration of the inspection device is needed, firstly, a checkerboard calibration plate is manufactured, and then the manufactured checkerboard calibration plate is fixed in an overlapping area of fields of adjacent rotating positions of cameras in a camera group; calibrating the acquisition, respectively acquiring images in the fixed areas of the chessboard pattern calibration plate, selecting a first image suitable for splicing, determining the overlapped view field in the image, calculating the rotation angle according to the determined overlapped view field when the turntable steering engine rotates, taking a second image after the turntable steering engine rotates in place, determining the overlapped view field in the image, recalculating the rotation angle, continuously rotating to take off one image, rotating the focusing steering engine when the turntable steering engine rotates in place, comparing the images according to the definition of the image shot by the camera, and stopping at the clearest position of the image; calculating a homography matrix, preprocessing the collected images, detecting corner points, calculating a homography matrix H through corner point coordinates of the two images, calculating a pixel focal length f of the camera set and a matrix H x M after translation transformation through H, calculating image coordinates after perspective transformation, thereby obtaining a translation vector L, and storing the parameters in a high-definition imaging module.
After the high-definition imaging assembly receives an image acquisition instruction, a turntable steering engine in the high-definition imaging assembly is rotated to a shooting position through a position during initial calibration, and pixels of a camera set on the focusing steering engine in the high-definition imaging assembly are adjusted; firstly, setting the number N of a picture to be acquired by a camera group in a high-definition imaging assembly so that a program can enter the next step after the acquisition is finished, if N =8, continuously detecting whether the number of the picture to be acquired reaches a preset value 8 by a high-definition imaging module in the picture acquisition process, and if not, continuously acquiring by the camera group until the detection of a high-definition camera module reaches the preset value; in the image collecting process, in order to reduce accumulated errors caused by constraint among a plurality of images, the collected images are subjected to cylindrical projection transformation preprocessing by using a pixel focal length f obtained by calibration, then the original images are covered after being deburred by using a bilinear interpolation method until image collecting is finished, a high-definition imaging module directly reads an image sequence subjected to projection transformation and deburring, perspective transformation is performed by using a translation transformation matrix H x M obtained in calibration, images are spliced by using a translation vector L obtained in calibration, finally image fusion is performed to process gaps among the spliced images to obtain spliced images, and the finished spliced images are output to a server connected with a high-definition camera device through the high-definition imaging module so as to be convenient for subsequent operation.
The scope of the present invention includes, but is not limited to, the above embodiments, and the present invention is defined by the appended claims, and any alterations, modifications, and improvements that may occur to those skilled in the art are all within the scope of the present invention.
Claims (5)
1. The method for omnibearing real-time monitoring by using the tunnel inspection robot is characterized by comprising the following steps of: step 1, sending an instruction: after the tunnel inspection robot is started, self-inspection is started, a main control module in an inspection module sends a motion instruction to a motion module, and sends a foreign matter detection instruction, an illegal snapshot instruction, a water seepage detection instruction and a high-definition image acquisition instruction to a monitoring module; step 2, after the tunnel inspection robot receives the instruction, the motion module receives the motion instruction and then drives the tunnel inspection robot to run along the track laid in the tunnel, and each module starts to act to complete all-dimensional real-time monitoring in the tunnel: (1) when a foreign matter detection monitoring instruction is received, the 3D laser radar monitors the passing lower road surface and acquires original point cloud data in the road surface environment; carrying out pose transformation and clustering segmentation on the collected original point cloud data, filtering the point cloud data outside the edge of the road surface to obtain point cloud data only with road surface information, analyzing the point cloud data, and making different responses by identifying different data models, when the data model at the identification position is an automobile, the 3D laser radar transmits the identified automobile model to model data which is trained in a deep learning module in advance, the 3D laser radar continuously tracks the running speed of the automobile, when the speed of all the automobiles in the detection area is lower than 3-6 km/h, the abnormal condition of the detection area is judged to be traffic jam, an alarm switch in the monitoring module is triggered, meanwhile, the monitoring module sends an alarm signal to a main control module, the main control module controls a communication module to send the alarm signal to a background control end and send a play signal to a voice module, playing early warning voice, shooting foreign object points by a cradle head, and waiting for related personnel to conduct traffic guidance or field processing;
(2) when an illegal snapshot monitoring instruction is received, the snapshot machine judges whether a scanned vehicle accords with overspeed, illegal lane change, overtaking and illegal parking parameters through built-in defined parameters, if so, information is fed back to a processing module in the main snapshot machine, the processing module processes the information and then sends the processed information to a main control module, the main control module controls the snapshot machine and a pan-tilt head to work, the snapshot machine takes a snapshot of illegal photos, and the pan-tilt head starts to record illegal video evidence;
(3) when a water seepage detection instruction is received, a thermal imager in a thermal imaging device continuously acquires images of passing walls when acting along with an inspection robot, the acquired infrared images are converted into gray level images, binarization processing is carried out to establish gray level threshold blocks, the threshold blocks slide line by line, when sliding to a certain position to detect abnormality, multi-neighborhood sliding is carried out to judge whether the detection is false detection, if the neighborhood abnormal value of the abnormal region reaches a preset parameter value, the phenomenon of water seepage is judged to exist at the position, a signal is sent to a main control module, and the main control module sends an alarm by sending an instruction to an operation end and a voice module; if the sliding is continued until the tail end of the last row is reached, namely the whole image is detected completely and no abnormal area is found, continuing to take the next image and repeating the detection;
(4) when a high-definition image acquisition instruction is received: when the inspection device is initially installed and started, the inspection device is initially calibrated, images are respectively collected in areas fixed by a chessboard grid calibration plate, a first image suitable for splicing is selected, overlapped view fields in the image are determined, when a turntable steering engine rotates, the rotation angle is calculated according to the determined overlapped view fields, a second image is taken after the rotation is in place, the overlapped view fields in the image are determined, the rotation angle is recalculated, a next image is continuously rotated, the collected images are preprocessed and then detected, a homography matrix H is calculated through corner point coordinates of the two images, the pixel focal length f of a camera set and a matrix H M after translation transformation are calculated through H, the image coordinates after perspective transformation are calculated, translation vectors L are obtained and stored in a high-definition imaging module, and after a high-definition imaging component receives an image collecting instruction, the high-definition imaging module directly reads the image sequence after projection transformation and deburring, performs perspective transformation and translation vector L splicing images obtained during calibration by using a translation transformation matrix H x M obtained during calibration, and outputs the images after fusion processing and splicing the gaps between the images to the server through the high-definition imaging module.
2. The method for omnibearing real-time monitoring by using the tunnel inspection robot according to claim 1, wherein the step 2 of making different responses by identifying different data models further comprises: A. when the identified data model is a bicycle or a pedestrian, the model data is directly judged as a foreign matter after being compared, an alarm switch in a monitoring module is triggered, the monitoring module sends an alarm signal to a main control module, the main control module controls a communication module to send the alarm signal to a background control end, and sends a play signal to a voice module to play an early warning voice, or remotely shouts through the voice module to remind the person or the rider to leave, and the alarm is turned off after the person or the rider leaves; B. when the data model at the identification position is an undefined object, the 3D laser radar transmits the undefined object model to model data trained in a deep learning module in advance, the 3D laser radar continuously tracks the speed of the undefined object, when the speed is lower than a set threshold value, the speed is judged as a foreign object, the threshold value period is 0-5 km/h, when the detected foreign object is the undefined object, a pan-tilt camera is automatically rotated according to the position of the undefined object, the foreign object point is shot, a remote control end looks up details of the foreign object according to the shooting condition, if the foreign object is a small object and does not cause large influence on traffic, the remote alarm is turned off, and the inspection device continues to inspect along the guide rail; if the foreign matter is a large object, the potential safety hazard is judged to exist, the traffic is seriously affected, the alarm is continuously given out, treating personnel are dispatched to the site to be treated, and the alarm is closed after the treatment is finished.
3. The method for omnibearing real-time monitoring of the inspection robot through the tunnel according to claim 1, wherein the inspection module comprises a main control module, a voice module, a communication module, a power supply module, a motion module, a monitoring module and a holder.
4. The method for omnibearing real-time monitoring by using the tunnel inspection robot according to claim 1, wherein the monitoring module comprises a 3D laser radar, a thermal external imaging device, a high-definition imaging component and a snapshot machine.
5. The method for omnibearing real-time monitoring by using the tunnel inspection robot according to claim 1, wherein the executing of the foreign matter detection command comprises the following steps: collecting monitoring data: monitoring the passing lower road surface by the 3D laser radar, and acquiring original point cloud data in a road surface environment; analyzing the monitoring condition; processing the original point cloud data obtained in the second step, obtaining a data model, judging whether abnormal information exists or not, and confirming the abnormal information condition; and the polling result responds: and responding according to the abnormal information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910099459.4A CN109688388B (en) | 2019-01-31 | 2019-01-31 | All-dimensional real-time monitoring method using tunnel inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910099459.4A CN109688388B (en) | 2019-01-31 | 2019-01-31 | All-dimensional real-time monitoring method using tunnel inspection robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109688388A CN109688388A (en) | 2019-04-26 |
| CN109688388B true CN109688388B (en) | 2021-06-25 |
Family
ID=66195402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910099459.4A Active CN109688388B (en) | 2019-01-31 | 2019-01-31 | All-dimensional real-time monitoring method using tunnel inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109688388B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110278417B (en) * | 2019-07-25 | 2021-04-16 | 上海莫吉娜智能信息科技有限公司 | Monitoring equipment rapid positioning method and system based on millimeter wave radar |
| CN110400468B (en) * | 2019-08-27 | 2021-08-31 | 诠航科技有限公司 | Low-speed in long tunnel is with clapping system |
| CN110847972B (en) * | 2019-11-26 | 2021-12-17 | 成都轨道建设管理有限公司 | Tunnel safety detection early warning system for subway construction |
| CN113012436B (en) * | 2019-12-18 | 2022-08-26 | 杭州海康威视数字技术股份有限公司 | Road monitoring method and device and electronic equipment |
| CN111785084A (en) * | 2020-05-27 | 2020-10-16 | 诠航科技有限公司 | Tunnel patrol machine |
| CN111785079A (en) * | 2020-05-27 | 2020-10-16 | 诠航科技有限公司 | Traffic early warning system based on tunnel patrol machine |
| CN111785081A (en) * | 2020-05-27 | 2020-10-16 | 诠航科技有限公司 | Guard bar patrol machine |
| CN111785080A (en) * | 2020-05-27 | 2020-10-16 | 诠航科技有限公司 | Intelligent traffic early warning system and early warning method |
| CN112367478A (en) * | 2020-09-09 | 2021-02-12 | 北京潞电电气设备有限公司 | Tunnel robot panoramic image processing method and device |
| CN112330938B (en) * | 2020-09-09 | 2022-12-16 | 北京潞电电气设备有限公司 | Traffic tunnel removes patrols and examines robot |
| CN112330930A (en) * | 2020-09-09 | 2021-02-05 | 北京潞电电气设备有限公司 | Urban tunnel traffic monitoring method, system and platform |
| CN114187676A (en) * | 2021-12-02 | 2022-03-15 | 智慧起源机器人(苏州)有限公司 | Inspection method, device, equipment, system and storage medium |
| CN115273474B (en) * | 2022-08-02 | 2023-04-18 | 浙江安易信科技有限公司 | RPA patrols and examines robot and patrols and examines management system based on artificial intelligence |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014173442A1 (en) * | 2013-04-24 | 2014-10-30 | Schöttler Markus | Apparatus and method for optically detecting flow movements in liquid and/or gaseous media |
| CN103309324A (en) * | 2013-06-05 | 2013-09-18 | 广州供电局有限公司 | Mobile tunnel environment inspection equipment |
| CN104809758B (en) * | 2015-05-08 | 2018-11-23 | 山东康威通信技术股份有限公司 | Live tunnel inspection and apparatus control method based on three-dimensional live roaming technology |
| CN106572325A (en) * | 2015-10-13 | 2017-04-19 | 上海宝信软件股份有限公司 | Virtual-reality-technology-based tunnel monitoring equipment inspection system |
| CN205721367U (en) * | 2016-05-03 | 2016-11-23 | 袁孝红 | Electric power tunnel intelligent inspection robot |
| CN106050309B (en) * | 2016-08-09 | 2018-07-13 | 北京铁路局北京科学技术研究所 | Object monitor and alarm system and method are fallen in tunnel |
| CN106679813A (en) * | 2016-11-21 | 2017-05-17 | 深圳供电局有限公司 | Intelligent detection system for tunnel power equipment |
| CN206195232U (en) * | 2016-11-21 | 2017-05-24 | 深圳供电局有限公司 | Tunnel intelligence is hung rail and is patrolled and examined monitored control system of robot |
| CN107202793A (en) * | 2017-05-16 | 2017-09-26 | 镇江市建科工程质量检测中心有限公司 | A kind of detecting system and method for detecting external wall mass defect |
| CN107703559A (en) * | 2017-09-07 | 2018-02-16 | 国网浙江省电力公司宁波供电公司 | Seep water infrared detecting device for a kind of cable tunnel |
| CN108107444B (en) * | 2017-12-28 | 2021-12-14 | 国网黑龙江省电力有限公司检修公司 | Transformer substation foreign matter identification method based on laser data |
| CN108248635B (en) * | 2018-02-05 | 2019-03-22 | 刘春梅 | A kind of intelligent checking system for rail tunnel |
-
2019
- 2019-01-31 CN CN201910099459.4A patent/CN109688388B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109688388A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109688388B (en) | All-dimensional real-time monitoring method using tunnel inspection robot | |
| JP4984915B2 (en) | Imaging apparatus, imaging system, and imaging method | |
| CN103366569B (en) | The method and system of real-time grasp shoot traffic violation vehicle | |
| CN109949594B (en) | Real-time traffic light identification method | |
| CN106647776B (en) | Method and device for judging lane changing trend of vehicle and computer storage medium | |
| CN106652551A (en) | Parking stall detection method and device | |
| CN101789177B (en) | Device and method for detecting and tracking vehicles crossing and pressing the yellow line and for capturing vehicle information | |
| KR101671428B1 (en) | Intelligent Monitoring System For Violation Vehicles in crossroads | |
| CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
| CN101964145A (en) | Automatic license plate recognition method and system | |
| CN104157143B (en) | Parking offense detection system and detection method thereof | |
| CN103523014A (en) | In-vehicle apparatus | |
| CN104506804A (en) | Device and method for monitoring abnormal behavior of motor vehicle on expressway | |
| CN106297314A (en) | A kind of drive in the wrong direction or the detection method of line ball vehicle behavior, device and a kind of ball machine | |
| CN105654734A (en) | Data processing method and device for vehicle violations | |
| CN107831760A (en) | Robot barrier thing processing system and method | |
| CN104036640A (en) | Panoramic image acquisition device and panoramic image acquisition method | |
| CN106203272A (en) | The method and apparatus determining the movement of movable objects | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN111738203B (en) | Platform pedestrian line crossing detection method based on automatic line marking area | |
| CN104361753A (en) | Method and device for obtaining evidences of rule and regulation breaking of vehicles not running in alternating mode | |
| CN103646544A (en) | Vehicle-behavior analysis and identification method based on holder and camera device | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN111145569A (en) | Road monitoring and vehicle running control method and device and vehicle-road cooperative system | |
| CN104658261A (en) | Detection and monitoring system of cart lane occupation on expressway |
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 | ||
| CB02 | Change of applicant information |
Address after: Jiangshan Zhen Xia Shi Cun, Yinzhou District, Ningbo City, Zhejiang Province, 315000 Applicant after: Quanhang Technology Co.,Ltd. Address before: 315000 Jinxi Road, Nordic Industrial Zone, Zhenhai District, Ningbo City, Zhejiang Province Applicant before: NINGBO QUANHANG MACHINERY TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |