CN101706274A - Device for automatically detecting nut loss of rail fastener system - Google Patents
Device for automatically detecting nut loss of rail fastener system Download PDFInfo
- Publication number
- CN101706274A CN101706274A CN200910253681A CN200910253681A CN101706274A CN 101706274 A CN101706274 A CN 101706274A CN 200910253681 A CN200910253681 A CN 200910253681A CN 200910253681 A CN200910253681 A CN 200910253681A CN 101706274 A CN101706274 A CN 101706274A
- Authority
- CN
- China
- Prior art keywords
- nut
- image
- disappearance
- software module
- fastener system
- 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
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a device for automatically detecting nut loss of a rail fastener system, comprising a vision collecting device, a GPS locator, an illumination device and a computer system, wherein nut illumination is added for the illumination device, and the computer system is provided with a video data storage software module, a display software module and a lost nut identifying and positioning software module. The executing steps are as follows: the video data storage software module receives and stores the position information of the device obtained by the GPS locator and continuous video images containing the fastener system nut obtained by the vision collecting device, and records the corresponding time value obtained by the video image and the position data; the lost nut identifying and positioning software module carries out pretreatment, sub-image cutting, feature extraction, feature classification and position calculation to the obtained video image to identify the position the nut loss; and the display software module displays and prints the image and position information of the lost nut. In the invention, the device moves along with the train during operation so as to automatically detect and position the nut loss of the rail fastener system.
Description
Technical field
Patent of the present invention relates to a kind of device for automatically detecting nut loss of rail fastener system, particularly a kind of device for automatically detecting nut loss of rail fastener system based on computer vision.
Background technology
The line maintenance maintenance has vital role for the operate as normal and the safe operation of the subway and the railway system.The railway of countries in the world and urban track traffic department all pay much attention to line maintenance work, have formulated detailed plan and strict regulations.One of important process of line maintenance maintenance is to check whether the fastener system nut lacks, and whether buckling piece is loosening.The effect of fastener system nut, railway spike and fastener is rail and road pillow to be reached closely effectively connect, and is the important accessory of railway and subway line.In the reality, maintenance is not in place owing to installing, the vibration of train driving and people be for reason such as stealing, and circuit upper fastener system nut may lack, and this travels to train safe and causes a hidden trouble.
For a long time, the main manual inspection of maintenance force and the method for range estimation of relying on judged circuit abnormal condition such as whether having road pillow damage, rail abrasion and fastener system nut loss in the line maintenance.Part foreign railway company has also relied on the experience maintenance personal to watch the video recording of circuit road surface, thereby has judged whether that road pillow, rail and fastener system nut need repairing, and wherein video recording is to take record by the video camera that is installed on the train that travels.The method required time of this hand inspection circuit rail, road pillow and fastener system nut is long, labour intensity is big, efficient is low, loss is high.
Computer vision is to replace the organs of vision as the input sensitive means with various imaging systems, replaces brain to finish by computing machine and handles and explanation.The final goal of computer vision is to make to calculate function and resemble the people by visual observation and understand the world, and has the ability of autonomous judgement and identification.Since nearly two, 30 years, computer vision technique is progressively from the experimental study practical stage of marching toward.At present, computer vision system is used very extensive at detection range.Based on the detection method of computer vision technique, has the efficient height, cost is low and advantage such as good reliability, is the important development direction of Non-Destructive Testing.Utilizing the Computer Vision Recognition method to replace the artificial visual inspection, is the new trend of railway and subway line maintenance.
Find through literature search prior art, not about the utility model and the patent of invention of the automatic detection device of nut loss of rail fastener system, have only external small part scholar that the Automatic Measurement Technique based on the fastener system nut loss of computer vision has been carried out preliminary research.(Mazzeo et al., Pattern Recognition Letters, 2004,25:669-677 such as Mazzeo; Mazzeo et al., Proceedings of the 2004 IEEE Intelligent TransportationSystems Conference, 417-422; Mazzeo et al., Proceedings of the 2003 IEEEInternational Symposium on Intelligent Control, 636-641) studied and utilize pivot analysis, wavelet transformation and nerual network technique that the track circuit video image is handled, thereby detected the disappearance of fastener system nut automatically.At nearest document (Ruvo et al., Proceedings of the7th international Workshop on Computer Architecture for Machine Perception, 2005, l-6; Marino et al., IEEE Transactions on Systems, Man, andCybemetics, Part C, 2007) in, the researchist has introduced the fastener system nut loss pick-up unit based on the FPGA exploitation, used aforementioned neural network scheduling algorithm, experimental result shows that it has certain real-time.Above-mentioned researchist utilizes computer vision to lack nut and detects, though obtained initial achievements, has the following disadvantages:
(1) it utilizes neural network to carry out the method for tagsort, makes the classification identification result be absorbed in local optimum easily, and generally needs large sample, and training result is also unstable, makes the applicability of this visual identifying system and functional reliability have much room for improvement;
(2) position of disappearance nut is based in the video image spacing of fastener system nut number and adjacent two nuts and calculates, and the nut geographic position resultant error that this computing method obtain is bigger.
Summary of the invention
The objective of the invention is to overcome the deficiencies in the prior art, a kind of automatic detection device of nut loss of rail fastener system is provided, make its system architecture simple, detect and accurate positioning, be used to replace or the manual inspection of auxiliary rail fastener system nut.
For realizing purpose of the present invention, the invention provides a kind of automatic detection device of nut loss of rail fastener system, this automatic detection device comprises: vision collecting device, GPS steady arm, lighting device and computer system.This disappearance nut automatic detection device is installed on train bottom, when train is advanced, rail both sides fastener system nut video image is gathered, is stored, to the identification of disappearance nut and location by computer system online or off-line finish.
Vision collecting device of the present invention is realized gathering the continuous videos image that comprises each fastener system nut, and is sent the video image that is obtained to computer system.
Lighting device is used to increase the illumination of fastener system nut, thereby improves the video image quality that is obtained.
The GPS steady arm is determined each residing geographic position of moment of vision collecting device, and sends each moment corresponding geographical location information to computer system.
Be provided with video data storing software module, software for display module and disappearance nut identification positioning software module in the computer system, and carry out following steps:
A) continuous videos that comprises the fastener system nut that video data storing software module receives and storage is sent by the vision collecting device, and write down each video image time corresponding value;
B) video data storing software module receive and storage is sent by the GPS steady arm each the time engraving device geographical location information of living in, and write down each geographical location information time corresponding value;
C) disappearance nut identification positioning software module to video image carry out that image pre-service, subimage cut, feature extraction and tagsort, thereby finish the identification of disappearance nut, and write down the acquisition time value of the image of these disappearance nut correspondences;
D) disappearance nut identification positioning software module is according to acquisition time value and each moment corresponding geographical location information of the image of disappearance nut correspondence, the geographic position of calculating the disappearance nut, the location of realizing the disappearance nut;
E) the software for display module shows on request to the video of gathering, and gathers, shows and print the image and the geographical location information of disappearance nut.
Described disappearance nut identification positioning software module comprises that image pre-service submodule, subimage cut five functional submodules such as submodule, feature extraction submodule, tagsort submodule and disappearance nut location calculating sub module, and the concrete course of work is:
1) video image that reads from video data storing software module at first carries out pre-service such as filtering and noise reduction and image restoration by image pre-service submodule, and sends the video image after the pre-service to subimage and cut submodule;
2) to cut the purpose of submodule be to cut the as far as possible little subimage that comprises the fastener system nut to subimage, this processing procedure at first uses template matching method to determine to comprise the subimage of nut, adopts exhaustive search to determine first position of fastener system nut in video image; Predict the time that the fastener system nut on the pillow of next road occurs according to train speed then, so just can cut the subimage that obtains a nut from the corresponding video image, wherein train speed calculates according to geographic position data and time value;
3) the feature extraction submodule utilizes the image transformation algorithm that each width of cloth subimage that subimage cuts the submodule transmission is carried out eigentransformation, obtains the low dimensional feature vector of each width of cloth subimage, and sends it to tagsort submodule;
4) the tagsort submodule tagsort processing procedure of carrying out, adopt algorithm of support vector machine to carry out the tagsort of subimage, judge according to classification results whether the fastener system nut in the pairing subimage of each proper vector lacks, and the acquisition time that will lack the image of nut sends disappearance nut location calculating sub module to;
5) disappearance nut location calculating sub module is according to the time value of these disappearance nut images, from video data storing software module, search and calculate corresponding geographic position data, and, generate form and send the software for display module to after these time values and the position data storage.
The present invention is a kind of device for automatically detecting nut loss of rail fastener system, this automatic detection device is realized the automatic identification of fastener system nut loss according to the principle of computer vision, utilize the GPS steady arm to lack the location of nut, disappearance nut discrimination height, and have the simple and little characteristics of positioning error of locator meams, be a kind of disappearance nut automatic detection device of online or off-line.
Description of drawings
Fig. 1 is a structured flowchart of the present invention;
Fig. 2 is the connection diagram between each module of the present invention and the submodule.
Embodiment
As shown in Figure 1, the present invention includes four ingredients: vision collecting device, GPS steady arm 3, lighting device 4 and computer system 5.The vision collecting device comprises ccd image sensor 1 and image pick-up card 2.The vision collecting device is used to gather the continuous videos image of the fastener system nut that comprises rail both sides, train bottom, and sends the continuous videos image that is obtained to computer system 5.
GPS steady arm 3 is determined each residing geographic position of moment of vision collecting device according to the GPS positioning principle, geographic position data comprises longitude and latitude numerical value, and sending each geographical location information constantly in the computer system 5 video data storing software module 11, video data storing software module 11 also is stored in pairing time value when obtaining each geographical location information simultaneously.GPS steady arm 3 is connected communication by interfaces such as USB or RS-232 with computer system 5.
As shown in Figure 2, be provided with video data storing software module 11, software for display module 12 and disappearance nut identification positioning software module 13 in the computer system 5.The residing geographical location information of current device that video data storing software module 11 receives in real time and storage is obtained by GPS steady arm 3 of computer system 5, and the fastener system nut continuous videos image that obtains of vision collecting device, finish the storage of geographic position data, video image and corresponding time value.Steps such as disappearance nut identification positioning software module 13 cuts by the video image that is obtained being carried out pre-service, subimage, eigentransformation, tagsort and position calculation are finished automatic identification and location to the disappearance nut.Software for display module 12 promptly can show the continuous videos image that is obtained in real time, also can show disappearance nut image and all disappearance nut location information reports that 13 processing of disappearance nut identification positioning software module obtain.
When apparatus of the present invention are installed, the optical axis of ccd image sensor 1 is vertical as far as possible with the rail subgrade plane, and be in directly over the fastener system nut. because each road pillow generally is equipped with four fastener nuts, therefore the present invention's camera lens enlargement factor that four ccd image sensor .CCD imageing sensors 1 need be installed side by side in the train bottom is appropriately chosen according to the distance of bottom fastener system nut and imageing sensor. when train is advanced, ccd image sensor 1 is realized gathering the continuous videos image that comprises the fastener system nut, and sends the continuous videos image that is obtained to computer system 5. by image pick-up card 2
The high-speed CCD imageing sensor that the vision collecting device apolegamy time shutter is short as far as possible when making apparatus of the present invention work like this, allows the train high-speed travel.Except that computer system platform adopted Windows XP, video data storing software module 11 of the present invention, software for display module 12 and disappearance nut identification positioning software module 13 all adopted Visual C++ software programming to realize.
As shown in Figure 2, disappearance nut identification positioning software module 13 comprises that image pre-service submodule 6, subimage cut submodule 7, feature extraction submodule 8, tagsort submodule 9 and disappearance nut location calculating sub module 10.Each submodule obtains image or data from last module respectively, and by image or data are handled, sends image or data after handling to next module.
Each software module and each submodule under the computer system 5 further describe as follows:
1) video data storing software module 11.Ccd image sensor 1 is gathered required video image, and process image pick-up card 2 sends video data storing software module 11 to, on the other hand GPS steady arm 3 also the cycle send the geographical location information data of current times to video data storing software module 11, video data storing software module 11 receives and stores these vedio datas, geographic position data and corresponding time value, uses for software for display module 12 and disappearance nut identification positioning software module 13.
2) the software for display module 12.Software for display module 12 is used for the continuous videos image that display video data storing software module 11 is obtained, and also can show and print all the disappearance nut location information reports of disappearance nut identification positioning software module 13 outputs and the image of corresponding disappearance nut.
3) disappearance nut identification positioning software module 13.Video image and geographic position data that this module provides according to video data storing software module 11, the identification and the location of finishing the disappearance nut of online or off-line, it comprises that image pre-service submodule 6, subimage cut submodule 7, feature extraction submodule 8, tagsort submodule 9 and disappearance nut location calculating sub module 10.Image pre-service submodule 6 reads raw video image and carries out the image pre-service, cuts submodule 7 for subimage and uses; Subimage cuts submodule 7 and uses respective algorithms to determine the position of each fastener system nut in each two field picture of continuous videos, cuts the subimage that comprises the fastener system nut simultaneously from each two field picture, and determines the temporal information that each subimage obtains; Feature extraction submodule 8 application image mapping algorithms carry out eigentransformation to each width of cloth subimage that subimage cuts submodule 7 transmission, calculate the low dimensional feature vector of each subimage, use for tagsort submodule 9; Tagsort submodule 9 utilizes the individual features sorting technique, each low dimensional feature vector is classified, thereby whether the fastener system nut of discerning in the pairing subimage of each proper vector lacks, and the acquisition time that will lack the image of nut sends disappearance nut location calculating sub module 10 to; Disappearance nut location calculating sub module 10 is according to the time value of these disappearance nut images, from video data storing software module, search and calculate corresponding geographic position data, and, generate form and use for software for display module 12 with after these location storage.
A) image pre-service submodule 6. image pre-service submodules 6 are from video data storing software module 11, obtain original fastener system nut continuous videos image and carry out pre-service, for cutting submodule 7, subimage provides required image. because electronic equipments itself such as ccd image sensor l and image pick-up card 2 can be introduced picture noise, the main task of image pre-service submodule 6 comprises that the image format conversion with different-format becomes the gray level image form, and uses moving window on average to wait the image filtering denoise algorithm that image is carried out filtering and noise reduction.
B) subimage cuts submodule 7.The function that subimage cuts submodule 7 realizations is to determine the position of fastener system nut in the video image, and cuts the as far as possible little subimage that comprises the fastener system nut.This submodule adopts exhaustive search to determine the position of first fastener system nut in the video image based on template matching method, and wherein template matching method is used to determine to comprise the zonule of nut.After determining the time and position that first fastener system nut occurs, predict time and the position that pillow upper fastener system nut in next road occurs according to train speed and adjacent two roads pillow spacing, thereby in corresponding video image, cutting the subimage that obtains a nut.Remember that the time that n nut occurs is t
n, train present speed v
Tn, road pillow centreline spacing is constant L, then the computing formula of the time of n+1 nut appearance is:
t
n+1＝t
n+L/v
tn (1)
Train present speed v
Tn Cutting submodule 7 by subimage calculates according to geographic position data and time changing value.Suppose that the image right direction is the train speed direction, the setting video image is k frame/second, and v
TnBe designated as P=v with the ratio of k
Tn/ k, and establish n nut and appear at k for the first time
nOpen on the image, the range image right side is q along actual range, and n+1 nut appears at k for the first time
N+1Open on the image, then:
k
n+1＝k
n+[(L-q)/p] (2)
Wherein " [] " expression rounds downwards.The central point distance k of n+1 nut
N+1It is right along being p-((L-q) mod p) to open image, and mod represents the computing that rems.Range image upper edge distance is constant.Ex ante analysis obtains actual range and image pixel corresponding relation, can obtain q value and n+1 nut at k
N+1Open the particular location in the image.According to the position of fastener system nut, cut the subimage that comprises the fastener system nut, pixel is designated as n * m.The value of n and m and ccd image sensor and nut distance and ccd image sensor camera lens enlargement factor are relevant.
C) the feature extraction submodule 8.Feature extraction submodule 8 is used pivot analysis method (PrincipalComponents Analysis, PCA, or title principal component analysis (PCA)) extraction and is cut the subimage feature that comprises the fastener system nut that submodule 7 provides by subimage.Suppose in disappearance nut identification positioning software module 13 training process, adopt W spoke nut sample image (comprising the normal image of nut loss and nut) altogether, each image cuts submodule 7 by subimage and converts the gray level image that size is m * n pixel to, then use the matrix A of m * n to represent this image, the value of matrix respective element is the gray-scale value of image respective pixel point.The pivot analysis method is a kind of linear dimensionality reduction technology.Note N=m * n, the one-dimensional vector x that then every width of cloth image is N with a size
k=(a
1, a
2..., a
N) represent, k=1 wherein, 2 ..., W.As training set, its population covariance matrix is with this W width of cloth sample image:
Wherein u is all x
kMean vector,
If establish S
1Eigenwert and corresponding unit character vector be respectively λ
kAnd η
k, k=1,2 ..., W, then according to principal component analysis (PCA), the linear transformation from original image to the new feature space is y
k=D
Tx
k, D is proper vector η
kThe transformation matrix that constitutes (k=1,2 ..., W).Therefore, can from W eigenwert, select J (the eigenwert characteristic of correspondence vector of J≤W) (for for simplicity, directly choosing maximum haveing nothing to do organized), and, make it become the orthogonal basis in a certain new space with its orthogonalization.This J eigenwert is major component (pivot), and the coordinate coefficient of each width of cloth subimage under this new orthogonal basis is as the low-dimensional characteristic parameter of this subimage, and the tagsort that offers next step is handled use.
D) tagsort submodule 9. trains the low dimensional feature vector of 9 pairs of feature extraction submodules of tagsort submodule, 8 transmission that finish to classify, thereby judge whether the nut in the corresponding subimage lacks. tagsort submodule 9 will lack the pairing temporal information of nut and send disappearance nut location calculating sub module 10. in the training stage, tagsort submodule 9 uses support vector machine method that the feature of the nut sample image of feature extraction submodule 8 extractions is carried out classification based training, thereby being used for the nut loss identification of other non-sample images. support vector machine adopts structural risk minimization to improve the generalization ability of learning machine, it is the decision rule that obtains from less training sample, still can obtain a kind of sorting technique of little error to test set independently, basically solved and crossed problem concerning study, problems such as non-linear and dimension disaster problem and local convergence. support vector machine is devoted to seek a lineoid, so that belong to the not ipsilateral that the point (each point is corresponding with the major component of each width of cloth sample image) of different classification just in time is positioned at lineoid in the training set, to make these points far away as far as possible simultaneously, just make the class interval maximum apart from this lineoid. establishing the defeated people of training sample is z
i, i=1,2 ..., W, z
i∈ R
J, corresponding desired output is b
i∈+1 ,-1}, wherein+1 and-1 be respectively that sample zi is the classification logotype of the sample image characteristic parameter of the intact and nut loss of nut.The target of support vector machine is exactly according to structural risk minimization, to construct an objective function, thereby the intact of rail fastener system nut and disappearance two quasi-modes are correctly made a distinction as far as possible.Tagsort submodule 9 must correctly be selected kernel function according to the characteristics of fastener system nut image, to reach gratifying nut loss recognition effect.
E) disappearance nut location calculating sub module 10.Disappearance nut location calculating sub module 10 is according to the time value of the disappearance nut image of tagsort submodule 9 transmission, from video data storing software module 11, search and calculate corresponding geographic position data, and, generate form and send software for display module 12 to after these position data storages.
Through above processing, finally finish the automatic detection and the location of rail fastener system disappearance nut.
Claims (3)
1. device for automatically detecting nut loss of rail fastener system, comprise: vision collecting device, GPS steady arm (3), lighting device (4) and computer system (5), wherein computer system (5) comprises video data storing software module (11), software for display module (12) and disappearance nut identification positioning software module (13), it is characterized in that, being as the criterion shows the identification and the location of nut loss of rail fastener system really, and this computer system (5) is carried out following steps:
A) continuous videos that comprises the fastener system nut that video data storing software module (11) receives and storage is sent by the vision collecting device, and write down each video image time corresponding value;
B) video data storing software module (11) receive and storage is sent by GPS steady arm (3) each the time engraving device geographical location information of living in, and write down each geographical location information time corresponding value;
C) disappearance nut identification positioning software module (13) to video image carry out that image pre-service, subimage cut, feature extraction and tagsort, thereby finish the identification of disappearance nut, and write down the acquisition time value of the image of these disappearance nut correspondences;
D) disappearance nut identification positioning software module (13) is according to acquisition time value and each moment corresponding geographical location information of the image of disappearance nut correspondence, the geographic position of calculating the disappearance nut, the location of realizing the disappearance nut;
E) software for display module (12) shows on request to the video of gathering, and gathers, shows and print the image and the geographical location information of disappearance nut.
2. device for automatically detecting nut loss of rail fastener system according to claim 1, it is characterized in that, the subimage that described disappearance nut identification positioning software module (13) is carried out cuts processing procedure, purpose is to cut the as far as possible little subimage that comprises the fastener system nut, this processing procedure at first uses template matching method to determine to comprise the subimage of nut, adopts exhaustive search to determine first position of fastener system nut in video image; Predict the time that the fastener system nut on the pillow of next road occurs according to train speed then, so just can cut the subimage that obtains a nut from the corresponding video image, wherein train speed calculates according to geographic position data and the time value that GPS steady arm (3) provides.
3. device for automatically detecting nut loss of rail fastener system according to claim 1, it is characterized in that, the tagsort processing procedure that described disappearance nut identification positioning software module (13) is carried out, adopt algorithm of support vector machine to carry out the tagsort of subimage, judge according to classification results whether the fastener system nut in the pairing subimage of each proper vector lacks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102536811A CN101706274B (en) | 2009-12-02 | 2009-12-02 | Device for automatically detecting nut loss of rail fastener system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102536811A CN101706274B (en) | 2009-12-02 | 2009-12-02 | Device for automatically detecting nut loss of rail fastener system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101706274A true CN101706274A (en) | 2010-05-12 |
| CN101706274B CN101706274B (en) | 2012-06-27 |
Family
ID=42376512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102536811A Expired - Fee Related CN101706274B (en) | 2009-12-02 | 2009-12-02 | Device for automatically detecting nut loss of rail fastener system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101706274B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103103900A (en) * | 2011-11-10 | 2013-05-15 | 北京市劳动保护科学研究所 | Rail fastener loose detection method |
| CN104773626A (en) * | 2015-04-08 | 2015-07-15 | 重庆市特种设备检测研究院 | Safety state detection device for bolt of standard section of construction hoist |
| CN105403807A (en) * | 2015-09-29 | 2016-03-16 | 昆明理工大学 | Intelligent method for fault section recognition of three-segment cable mixed direct current power transmission line |
| CN106157316A (en) * | 2016-07-15 | 2016-11-23 | 成都唐源电气股份有限公司 | A kind of rail fastener location algorithm based on geometric match and device |
| CN108009574A (en) * | 2017-11-27 | 2018-05-08 | 成都明崛科技有限公司 | A kind of rail clip detection method |
| CN108345858A (en) * | 2018-02-11 | 2018-07-31 | 杭州鸿泉物联网技术股份有限公司 | A kind of vehicle load condition detection method and system |
| CN108468256A (en) * | 2018-02-06 | 2018-08-31 | 中车工业研究院有限公司 | A kind of railway intelligence fastener installation mechanical arm and its fastener installation method |
| CN109174661A (en) * | 2018-06-22 | 2019-01-11 | 襄阳元创汽车零部件实业有限公司 | A kind of vertical welding machine height of nut detection fail-safe system |
| CN114367459A (en) * | 2022-01-11 | 2022-04-19 | 宁波市全盛壳体有限公司 | Video identification detection method for automatic painting UV curing equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1396461A (en) * | 2001-07-12 | 2003-02-12 | 圣诠科技股份有限公司 | Automatic field investgation system combining digital dynamic image with GPS |
| CN101055178A (en) * | 2006-04-14 | 2007-10-17 | 雅音商行 | Positioning system for simultaneously displaying outer scene image and coordinate position map image |
-
2009
- 2009-12-02 CN CN2009102536811A patent/CN101706274B/en not_active Expired - Fee Related
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103103900B (en) * | 2011-11-10 | 2014-12-24 | 北京市劳动保护科学研究所 | Rail fastener loose detection method |
| CN103103900A (en) * | 2011-11-10 | 2013-05-15 | 北京市劳动保护科学研究所 | Rail fastener loose detection method |
| CN104773626B (en) * | 2015-04-08 | 2017-10-10 | 重庆市特种设备检测研究院 | A kind of building hoist standard knot bolt safe condition detection means |
| CN104773626A (en) * | 2015-04-08 | 2015-07-15 | 重庆市特种设备检测研究院 | Safety state detection device for bolt of standard section of construction hoist |
| CN105403807B (en) * | 2015-09-29 | 2018-11-27 | 昆明理工大学 | A kind of intelligent method of three sections of cables Hybrid HVDC line fault section identification |
| CN105403807A (en) * | 2015-09-29 | 2016-03-16 | 昆明理工大学 | Intelligent method for fault section recognition of three-segment cable mixed direct current power transmission line |
| CN106157316A (en) * | 2016-07-15 | 2016-11-23 | 成都唐源电气股份有限公司 | A kind of rail fastener location algorithm based on geometric match and device |
| CN108009574A (en) * | 2017-11-27 | 2018-05-08 | 成都明崛科技有限公司 | A kind of rail clip detection method |
| CN108009574B (en) * | 2017-11-27 | 2022-04-29 | 成都明崛科技有限公司 | Track fastener detection method |
| CN108468256A (en) * | 2018-02-06 | 2018-08-31 | 中车工业研究院有限公司 | A kind of railway intelligence fastener installation mechanical arm and its fastener installation method |
| CN108345858A (en) * | 2018-02-11 | 2018-07-31 | 杭州鸿泉物联网技术股份有限公司 | A kind of vehicle load condition detection method and system |
| CN109174661A (en) * | 2018-06-22 | 2019-01-11 | 襄阳元创汽车零部件实业有限公司 | A kind of vertical welding machine height of nut detection fail-safe system |
| CN109174661B (en) * | 2018-06-22 | 2021-07-20 | 襄阳元创汽车零部件实业有限公司 | Vertical welding machine nut height detection mistake proofing system |
| CN114367459A (en) * | 2022-01-11 | 2022-04-19 | 宁波市全盛壳体有限公司 | Video identification detection method for automatic painting UV curing equipment |
| CN114367459B (en) * | 2022-01-11 | 2024-03-08 | 宁波市全盛壳体有限公司 | Video identification and detection method for automatic painting UV curing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101706274B (en) | 2012-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101706274B (en) | Device for automatically detecting nut loss of rail fastener system | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN103500322B (en) | Automatic lane line identification method based on low latitude Aerial Images | |
| CN109658397A (en) | A kind of rail polling method and system | |
| CN103837087B (en) | Pantograph automatic testing method based on active shape model | |
| CN104239867B (en) | License plate locating method and system | |
| CN109716108A (en) | A kind of Asphalt Pavement Damage detection system based on binocular image analysis | |
| CN110473178A (en) | A kind of open defect detection method and system based on multiple light courcess fusion | |
| CN106127137A (en) | A kind of target detection recognizer based on 3D trajectory analysis | |
| CN103971097B (en) | Vehicle license plate recognition method and system based on multiscale stroke models | |
| CN106408015A (en) | Road fork identification and depth estimation method based on convolutional neural network | |
| CN102915432B (en) | A kind of vehicle-mounted microcomputer image/video data extraction method and device | |
| CN101493943B (en) | Particle filtering tracking method and tracking device | |
| CN106679567A (en) | Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision | |
| CN111179300A (en) | Method, apparatus, system, device and storage medium for obstacle detection | |
| CN101807352A (en) | Method for detecting parking stalls on basis of fuzzy pattern recognition | |
| CN105158257A (en) | Sliding plate measurement method and device | |
| CN101726498B (en) | Intelligent detector and method of copper strip surface quality on basis of vision bionics | |
| CN104156731A (en) | License plate recognition system based on artificial neural network and method | |
| CN103077526A (en) | Train abnormality detection method and system with deep detection function | |
| CN110503070A (en) | Traffic automation monitoring method based on Aerial Images object detection process technology | |
| CN106339657A (en) | Straw incineration monitoring method and device based on monitoring video | |
| CN110186375A (en) | Intelligent high-speed rail white body assemble welding feature detection device and detection method | |
| CN103745238A (en) | Pantograph identification method based on AdaBoost and active shape model | |
| CN111754460A (en) | Method, system and storage medium for automatically detecting gap of point switch |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120627 Termination date: 20121202 |