CN110909745A - Train disinfection channel identification system - Google Patents
Train disinfection channel identification system Download PDFInfo
- Publication number
- CN110909745A CN110909745A CN201911343555.5A CN201911343555A CN110909745A CN 110909745 A CN110909745 A CN 110909745A CN 201911343555 A CN201911343555 A CN 201911343555A CN 110909745 A CN110909745 A CN 110909745A
- Authority
- CN
- China
- Prior art keywords
- text
- identification
- algorithm
- train
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004659 sterilization and disinfection Methods 0.000 title claims abstract description 11
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 7
- 230000000712 assembly Effects 0.000 claims description 2
- 238000000429 assembly Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of video identification, and discloses a train disinfection channel identification system, which comprises the following steps: acquiring video information: a large amount of field videos are obtained in real time through a video component, and a large amount of key frame modules are extracted from the field videos; text positioning: carrying out text positioning by using a CTPN algorithm and an RNN algorithm; text recognition: after text detection is finished, the image text is recognized by using deep learning technologies such as CTPN, CTC, CNN and RNN, and the like, and the data of the number of carriages, containers and the like of the current train are calculated according to the recognized result; and outputting a result: inputting the identified information into a monitoring platform; the invention is matched with the high-speed camera image intelligent capture and identification algorithm, redesigns and realizes the identification algorithm, respectively captures and identifies the railway port car body code, the plate car code and the container code, improves the identification precision and efficiency of the system, and solves the problems of low identification rate and poor effect of the prior identification technology.
Description
Technical Field
The invention relates to the technical field of video identification, in particular to a train disinfection channel identification system.
Background
The existing coding recognition technology is applied to motor vehicles and road gates in a very mature manner, for the motor vehicles, the vehicles at the vehicle gates are captured in real time by a high-definition camera within 10 meters away from the camera, and the images are analyzed to obtain the license plates, the printing fonts of the license plate codes are relatively regular and clear, and the motion tracks of the license plates face the direction of the camera.
The train codes at the railway port are arranged on the side face of a train body and are divided into the train body codes, the plate car codes, the container codes and the like according to different types of mounted carriages, the moving direction is lateral displacement, and an identification system identifies the train body codes, the plate car codes, the container codes and the like. When the train speed per hour is less than or equal to 40Km/h, each character is segmented and preprocessed by positioning the video acquisition effective frame, then the split font is identified by an identification algorithm, and finally the identification result is corrected, so that the identification rate is ensured to be more than 95%.
Disclosure of Invention
Technical problem to be solved
The invention aims to provide a train disinfection channel identification system which has the advantages of improving the identification precision and efficiency of the system and reducing the requirement on the environment, and solves the problem of difficult train information identification.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: train disinfection passageway identification system includes the following steps:
step 1: acquiring video information: a large amount of field videos are obtained in real time through a video component, and a large amount of key frame modules are extracted from the field videos;
step 2: text positioning: carrying out text positioning by using a CTPN algorithm and an RNN algorithm;
and step 3: text recognition: after the text detection is finished, the image text is recognized by using deep learning technologies such as CTPN, CTC, CNN and RNN, and the like, and the data such as the number of carriages, containers and the like of the current train are calculated according to the recognized result;
and 4, step 4: and outputting a result: and inputting the identified information into the monitoring platform for the platform side to call and view.
Preferably, 2-3 video assemblies are respectively installed on each lane of the wide track and the standard track and are connected to the background processing server and stored through a special cable.
Advantageous effects
Compared with the prior art, the train disinfection channel identification system provided by the invention has the following beneficial effects:
by the arrangement of the train disinfection channel identification system, the problems of low train code identification rate, poor effect and the like of the existing identification technology are solved.
Drawings
FIG. 1 is a simplified diagram of the identification system workflow of the present invention;
FIG. 2 is a schematic diagram of the operation of the recognition system 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.
Referring to fig. 1-2, the train disinfection passage identification system includes the following steps:
step 1: acquiring video information: a large amount of field videos are obtained in real time through a video component, and a large amount of key frame modules are extracted from the field videos;
step 2: text positioning: carrying out text positioning by using a CTPN algorithm and an RNN algorithm;
and step 3: text recognition: after the text detection is finished, the image text is recognized by using deep learning technologies such as CTPN, CTC, CNN and RNN, and the like, and the data such as the number of carriages, containers and the like of the current train are calculated according to the recognized result;
and 4, step 4: and outputting a result: and inputting the identified information into the monitoring platform for the platform side to call and view.
Referring to fig. 1-2, the video modules are respectively installed with 2-3 video modules on each lane of the wide track and the standard track, and are connected to the background processing server and stored through a dedicated cable.
The working principle is as follows: a large amount of field videos are obtained in real time through a video component, and a large amount of key frame modules are extracted from the field videos; text positioning: the CTPN algorithm and the RNN algorithm are used for text positioning, and the CTPN algorithm comprises the following specific steps: 1. firstly, the feature map is obtained by the first 5 Conv stages of VGG16, and the size is W × H × C; 2. using 3 × 3 sliding window to extract features on the feature map obtained in the previous step, and using the features to predict a plurality of anchors, wherein the anchor definition is the same as that in the previous fast-rcnn, namely helping us define the target candidate area; 3. inputting the features obtained in the last step into a bidirectional LSTM, outputting a W256 result, and inputting the result into a 512-dimensional full connection layer (FC); 4. finally, the output obtained by classification or regression is mainly divided into three parts, namely 2k vertical coordinates from top to bottom according to the upper graph, wherein the coordinates represent the height of the selection frame and the coordinates of the y axis of the center; 2k scores, which represents the category information of k anchors and indicates whether the anchors are characters or not; k side-redefinition indicates the horizontal offset of the selection box. The horizontal width of anchor is all 16 pixels constant, that is, the unit of the minimum selection box of our differential is 16 pixels "; 5. using an algorithm of text construction, combining the elongated rectangles obtained by us into a sequence box of the text; text recognition: after the text detection is finished, the image text is recognized by using deep learning technologies such as CTPN, CTC, CNN and RNN, and the like, and the data such as the number of carriages, containers and the like of the current train are calculated according to the recognized result; and outputting a result: and inputting the identified information into the monitoring platform for the platform side to call and view.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (2)
1. Train disinfection passageway identification system, its characterized in that: the method comprises the following steps:
step 1: acquiring video information: a large amount of field videos are obtained in real time through a video component, and a large amount of key frame modules are extracted from the field videos;
step 2: text positioning: carrying out text positioning by using a CTPN algorithm and an RNN algorithm;
and step 3: text recognition: after the text detection is finished, the image text is recognized by using deep learning technologies such as CTPN, CTC, CNN and RNN, and the like, and the data such as the number of carriages, containers and the like of the current train are calculated according to the recognized result;
and 4, step 4: and outputting a result: and inputting the identified information into the monitoring platform for the platform side to call and view.
2. The train disinfection lane identification system of claim 1, wherein: the video assembly is respectively provided with 2-3 video assemblies on each lane of the wide rail and the standard rail and is connected to a background processing server and stored through a special cable.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343555.5A CN110909745A (en) | 2019-12-24 | 2019-12-24 | Train disinfection channel identification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343555.5A CN110909745A (en) | 2019-12-24 | 2019-12-24 | Train disinfection channel identification system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110909745A true CN110909745A (en) | 2020-03-24 |
Family
ID=69827303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911343555.5A Pending CN110909745A (en) | 2019-12-24 | 2019-12-24 | Train disinfection channel identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110909745A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111738681A (en) * | 2020-06-17 | 2020-10-02 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN113371035A (en) * | 2021-08-16 | 2021-09-10 | 山东矩阵软件工程股份有限公司 | Train information identification method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679452A (en) * | 2017-08-28 | 2018-02-09 | 中国电子科技集团公司第二十八研究所 | Goods train license number real-time identifying system based on convolutional neural networks under big data |
CN110378332A (en) * | 2019-06-14 | 2019-10-25 | 上海咪啰信息科技有限公司 | A kind of container terminal case number (CN) and Train number recognition method and system |
CN110472633A (en) * | 2019-08-15 | 2019-11-19 | 南京拓控信息科技股份有限公司 | A kind of detection of train license number and recognition methods based on deep learning |
-
2019
- 2019-12-24 CN CN201911343555.5A patent/CN110909745A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679452A (en) * | 2017-08-28 | 2018-02-09 | 中国电子科技集团公司第二十八研究所 | Goods train license number real-time identifying system based on convolutional neural networks under big data |
CN110378332A (en) * | 2019-06-14 | 2019-10-25 | 上海咪啰信息科技有限公司 | A kind of container terminal case number (CN) and Train number recognition method and system |
CN110472633A (en) * | 2019-08-15 | 2019-11-19 | 南京拓控信息科技股份有限公司 | A kind of detection of train license number and recognition methods based on deep learning |
Non-Patent Citations (1)
Title |
---|
ZHI TIAN 等: ""Detecting Text in Natural Image with Connectionist Text Proposal Network"", 《ARXIV:1609.03605V1》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111738681A (en) * | 2020-06-17 | 2020-10-02 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN111738681B (en) * | 2020-06-17 | 2021-09-03 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN113371035A (en) * | 2021-08-16 | 2021-09-10 | 山东矩阵软件工程股份有限公司 | Train information identification method and system |
CN113371035B (en) * | 2021-08-16 | 2021-11-23 | 山东矩阵软件工程股份有限公司 | Train information identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8509486B2 (en) | Vehicle license plate recognition method and system thereof | |
CN109637151B (en) | Method for identifying illegal driving of emergency lane on highway | |
CN100452110C (en) | Automobile video frequency discrimination speed-testing method | |
CN110378332A (en) | A kind of container terminal case number (CN) and Train number recognition method and system | |
Wu et al. | Detection of bird nests in overhead catenary system images for high-speed rail | |
CN109325404A (en) | A kind of demographic method under public transport scene | |
CN105005771A (en) | Method for detecting full line of lane based on optical flow point locus statistics | |
CN103268489A (en) | Motor vehicle plate identification method based on sliding window searching | |
CN104700072A (en) | Lane line historical frame recognition method | |
CN110909745A (en) | Train disinfection channel identification system | |
CN102759347A (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 | |
CN111008574A (en) | Key person track analysis method based on body shape recognition technology | |
CN106023076A (en) | Splicing method for panoramic graph and method for detecting defect state of guard railing of high-speed railway | |
CN115861383B (en) | Pedestrian track prediction device and method for multi-information fusion in crowded space | |
CN113487561B (en) | Pantograph foreign matter detection method and device based on gray gradient abnormal voting | |
CN112907597A (en) | Railway track line detection method based on deep convolutional neural network | |
CN117409039B (en) | Wheel track relative displacement calculation method based on virtual point tracking network | |
CN113537007B (en) | Non-staff intrusion detection and alarm method and device applied to railway platform | |
CN113343960A (en) | Method for estimating and early warning passenger flow retained in subway station in real time | |
CN117612117A (en) | Roadside near weed segmentation method, system and medium based on vehicle-mounted recorder | |
CN110287897B (en) | Rail train visual positioning system based on deep learning | |
CN202854837U (en) | Vehicle lane mark line detection device | |
Gondhalekar et al. | Vehicle License Plate Recognition Using Neural Networks | |
CN103955685A (en) | Edge tracing digital recognition method | |
CN114066895B (en) | Detection method and device for pantograph slide plate |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200423 Address after: 401147 8th floor, Zone D, Neptune technology building, No. 62, Xingguang Avenue, Yubei District, Chongqing Applicant after: Ubiquitous network technology (Chongqing) Co., Ltd Address before: No. 6, South Beijing Road, Xinshi District, Urumqi, Xinjiang Uygur Autonomous Region Applicant before: Xinjiang Jiuzhou fumigation and disinfection Co., Ltd |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |