CN111833302A - Car number and case number identification association system - Google Patents
Car number and case number identification association system Download PDFInfo
- Publication number
- CN111833302A CN111833302A CN202010506780.2A CN202010506780A CN111833302A CN 111833302 A CN111833302 A CN 111833302A CN 202010506780 A CN202010506780 A CN 202010506780A CN 111833302 A CN111833302 A CN 111833302A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- container
- controller
- camera
- car
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/64—Devices characterised by the determination of the time taken to traverse a fixed distance
- G01P3/66—Devices characterised by the determination of the time taken to traverse a fixed distance using electric or magnetic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- 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
Abstract
The invention provides a train number and box number identification correlation system which comprises a camera, a vehicle detection sensor and a train number identification system, wherein the train number identification system is used for acquiring train number and train number information and transmitting the acquired train number and train number information to an upper computer, the camera is used for acquiring container images, the vehicle detection sensor is used for detecting the passing speed of a vehicle and transmitting the passing speed to a controller, the controller is used for generating a matched camera driving signal according to the train speed and controlling the camera to acquire the container images, the camera is used for transmitting the acquired container image data to the upper computer through Ethernet, the upper computer is used for analyzing the acquired container images, identifying the container numbers and box codes, correlating the identified container numbers with the train numbers and transmitting the container numbers and the train numbers to a monitoring center server through the network. The invention realizes the identification of the train number and the container number and the automatic association of the information.
Description
Technical Field
The invention relates to the technical field of cargo transportation, in particular to a vehicle number and case number identification association system.
Background
At present, the method for associating the box number and the car number of the molten iron intermodal container mainly adopts the steps that after a railway container truck arrives at a rail receiving station, an outworker carries out manual operation, and the container box number and the car number are recorded in an association mode on site. The existing operation mode has long operation time, greatly reduces the operation efficiency and cannot adapt to the operation mode of high-efficiency operation of the combined transportation of molten iron.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a train number and container number identification association system, which realizes the identification of train numbers and container numbers and the automatic association of information.
The invention is realized by the following steps: the invention discloses a train number and box number identification correlation system which comprises a camera, a vehicle detection sensor and a train number identification system, wherein the train number identification system is used for acquiring information of train numbers and transmitting the acquired information of the train numbers and the train numbers to an upper computer, the vehicle detection sensor is used for detecting vehicles coming in, the vehicle detection sensor is connected with the input end of a controller, the output end of the controller is connected with the camera, the camera is used for acquiring images of containers and transmitting the acquired image data of the containers to the upper computer, and the upper computer is used for analyzing the acquired images of the containers, identifying the container numbers and box codes and correlating the identified container numbers with train numbers.
The data of the box number identification and the car number identification are indexed according to the advancing sequence of the carriage, and the box number and the car number can be associated by corresponding the two data one by one.
And the upper computer associates the identified container number with the train number and transmits the association result to the monitoring center server through the network.
Furthermore, the car number identification system comprises a car number receiving and reading device, the car number receiving and reading device is used for sending radio frequency signals to the passive RFID volume label at the lower part of the carriage through a ground antenna, the ground antenna simultaneously receives the volume label signals and transmits the volume label signals to the car number receiving and reading device through a radio frequency cable, and the car number receiving and reading device transmits the volume label signals to the upper computer.
Furthermore, the vehicle detection sensor is used for detecting the passing speed of the vehicle and transmitting the passing speed to the controller, and the controller is used for controlling the sampling frequency of the camera according to the vehicle speed and collecting container images.
The system calculates the camera sampling frequency as k 1000/N according to the speed k m/s of the vehicle and the resolution of each line Nmm, and the system always keeps the image length of each vehicle consistent with the physical length no matter how the speed of the vehicle is, for example, a vehicle with a length of 12 meters always acquires 6000 lines, and the image resolution is always 2048 x 6000.
Further, the vehicle detection sensor employs a wheel sensor; each group of wheel sensors consists of at least two magnetic steels, wherein the first magnetic steel and the second magnetic steel are arranged at intervals and used for outputting signals to the controller when a vehicle passes through, and the controller calculates the speed of the vehicle according to the time when the same wheel passes through the first magnetic steel and the second magnetic steel.
The vehicle detection sensor comprises two groups of wheel sensors which respectively correspond to two vehicle incoming directions.
Further, the vehicle detection sensor comprises startup magnetic steel, the startup magnetic steel is used for generating a startup signal when a vehicle passes through and transmitting the startup signal to the controller, and the controller controls the camera to start to work after receiving the startup signal.
The number of the starting-up magnetic steels is two, and the two starting-up magnetic steels respectively correspond to two incoming vehicle directions.
The camera and the lighting equipment on the door frame are in a closed state in daily life, and only when the vehicle passes through the first magnetic steel, namely the starting magnetic steel, the starting signal is generated, and the camera and the lighting equipment are started to work.
Further, when the controller detects that the vehicle detection sensor does not respond within the set time, the controller determines that the vehicle has left, stops driving the camera, and completes the detection process of the train of vehicles.
Furthermore, the controller collects signals generated when a first wheel and a second wheel of each carriage pass through the same vehicle detection sensor, identifies each carriage according to the wheel base and provides a section control signal for the upper computer, the upper computer is used for splicing the image data collected on site, the image data is divided by combining the section control signals, a carriage picture of each carriage is generated, and the container number information of the carriage picture is identified.
The controller provides a section control signal for the system, and the system divides the image according to the section control signal, wherein the division mainly comprises the step of independently dividing and storing each compartment into one picture.
Because the system is a linear array camera, the collected images are spliced out by each line.
Further, the container number information of the carriage picture identified by the upper computer adopts a container character identification method based on deep learning analysis, and the method specifically comprises the following steps: the method comprises the steps of finishing preprocessing of images by carrying out graphic graying and edge detection processing on carriage images, carrying out connected domain analysis on the preprocessed images, realizing character segmentation and extraction, and then identifying characters by utilizing a deep learning model.
The method for recognizing the characters by utilizing the deep learning model specifically comprises the following steps: and carrying out deep learning on the container number image by adopting a deep learning algorithm, and using a learning result for identifying the container number.
Further, the system comprises a light intensity sensor and a lighting device, wherein the light intensity sensor is electrically connected with the input end of the controller, the output end of the controller is electrically connected with the lighting device, the light intensity sensor is used for detecting the ambient light intensity, when a vehicle comes and the ambient light intensity is lower than a set value, the lighting device is started by the controller, and the lighting device is automatically turned off when the vehicle leaves.
The system further comprises a portal frame, wherein the portal frame spans a railway and is provided with three laser integrated cameras, and the three laser integrated cameras are used for respectively acquiring images of the left side, the right side and the top of the carriage; the portal frame is further provided with two snapshot cameras, and the two snapshot cameras are used for respectively taking a snapshot of the tail of the carriage when the vehicle passes through in different directions.
The tail of the carriage is captured to identify the number of the container, and the tail of the carriage is mainly used as a supplement of a side camera. Because the container number is on six sides of the container, the patent only collects the number of the left side and the right side.
And a light supplementing light source of the snapshot machine is arranged above the first snapshot camera and the second snapshot camera.
The door frame is generally arranged in a railway section from a railway track connecting station to a port loading and unloading area, and the straight section is not less than 50 meters.
The invention has the following beneficial effects: in the process of molten iron intermodal transportation, in order to improve the efficiency problem of association of container box numbers and train numbers when containers are switched between a cargo ship and a railway train and meet the handing-over business of molten iron intermodal freight containers, 1 set of intelligent vehicle number and box number identification system is designed, the vehicle number identification system is used for collecting vehicle number and vehicle number information and transmitting the collected vehicle number and vehicle number information to an upper computer, the camera is used for collecting container images, the vehicle detection sensor is used for detecting the passing speed of a vehicle and transmitting the speed to a controller, the controller is used for generating matched camera driving signals according to the vehicle speed and controlling the camera to collect the container images, the camera is used for transmitting the collected container image data to the upper computer through Ethernet, the upper computer is used for analyzing the collected container images and identifying the container box numbers and box codes, the automatic association of train number and container number identification and information is carried out, the problem that the container can be fine is that the container does not fall to the ground in the process of transferring from a port ship to a railway wagon, manual intervention is not needed, and the association of the container number and the railway wagon number identification can be realized, so that the operation efficiency of container molten iron intermodal transportation is greatly improved, and the automatic entry of cargo information of container cargos in railway transportation can be met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a system structure diagram of a car number and box number identification association system according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of the train number and box number identification association system provided by the embodiment of the 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 and 2, the embodiment discloses a train number and box number identification association system, which includes a camera, a vehicle detection sensor and a train number identification system, wherein the train number identification system is used for collecting train number and train number information and transmitting the collected train number and train number information to an upper computer, the vehicle detection sensor is used for detecting the arrival of the vehicle (i.e. detecting the arrival direction of the vehicle through a portal or a camera), the vehicle detection sensor is electrically connected with an input end of a controller, an output end of the controller is electrically connected with the camera, the vehicle detection sensor is used for detecting the speed of the vehicle and transmitting the speed to the controller, the controller is used for controlling the sampling frequency of the camera according to the speed of the vehicle and collecting container images, the camera is used for transmitting the collected container image data to the upper computer through ethernet (such as gigabit ethernet), and the upper computer is used for analyzing the collected container images, and identifying the container number and the box code, associating the identified container number with the train number, and finally transmitting the container number and the train number to a monitoring center server through a network. The camera is connected with the upper computer through the switch.
The controller is matched with the camera scanning rate according to the driving speed, and the phenomenon that the picture is not stretched or compressed on the length of the vehicle is achieved.
The system of the embodiment calculates the sampling frequency k × 1000/2 of the camera according to the speed k m/s of the vehicle and the resolution of 2mm per line, and the system always keeps the image length of each vehicle consistent with the physical length no matter the speed of the vehicle, for example, a vehicle with a length of 12 meters always acquires 6000 lines, and the image resolution is always 2048 × 6000.
The controller continuously detects the passing speed of the wheels and generates a control signal for driving the camera; the car number identification system is started simultaneously and comprises a car number receiving and reading device, the car number receiving and reading device sends out radio frequency signals to a passive RFID label at the lower part of a carriage through a ground antenna, the ground antenna receives label signals simultaneously and transmits the label signals to the car number receiving and reading device through a radio frequency cable, the car number receiving and reading device transmits the label signals to an upper computer and is matched with a high-definition picture of a vehicle, the container number is identified and associated with the car number through a deep learning module, and finally the container number is transmitted to a monitoring center server through a network. This embodiment car number receiving and reading device is connected with the controller, and the controller passes through the switch and is connected with the host computer.
Further, when the controller detects that the vehicle detection sensor does not respond within the set time (the set time of the embodiment is 10 seconds), it is determined that the vehicle has left, the camera driving is stopped, and the detection process of the train of vehicles is completed.
Further, the vehicle detection sensor adopts wheel sensors, each group of wheel sensors is composed of at least two magnetic steels, wherein the first magnetic steel and the second magnetic steel are arranged at intervals along the longitudinal direction of the railway 8, when the vehicle 9 presses the magnetic steels, signals are generated, the controller collects the signals generated by the magnetic steels, and the vehicle speed is calculated according to the time when the same wheel passes through the first magnetic steel and the second magnetic steel. This patent is provided with two sets of wheel sensor, corresponds two directions of coming the car respectively. The first magnetic steel and the second magnetic steel are arranged on a railway below the gantry, and are longitudinally spaced by 1 m.
Furthermore, each group of wheel sensors further comprises startup magnetic steel, the startup magnetic steel is used for generating a startup signal when a vehicle passes through and transmitting the startup signal to the controller, and the controller controls the camera to start up after receiving the startup signal.
The camera and the lighting equipment on the door frame are in a closed state in daily life, and only when the vehicle passes through the first magnetic steel, namely the starting magnetic steel, the starting signal is generated, and the camera and the lighting equipment are started to work.
The starting magnetic steel is arranged on the railway 25m away from the gantry and serves as the starting magnetic steel.
The vehicle includes a multi-section cabin.
Further, the controller collects signals generated when a first wheel and a second wheel of each carriage pass through the same vehicle detection sensor, identifies each carriage according to the wheel base and provides a section control signal for the upper computer, the upper computer is used for receiving image data collected on site and splicing the image data, the image data is split by combining the section control signal, 4 complete high-definition pictures of the left, right, top and tail of each carriage are generated and transmitted into the image processing workstation, and the information of the container number of the container is automatically extracted and identified through the depth automatic detection container relevant information.
The images of the carriage are displayed in a panoramic three-view mode, and processing such as real-time slow playing, synchronous playing, playback, positioning, amplification, reduction and the like can be performed.
The wheel base can be judged by the first wheel and the second wheel of one carriage through the same magnetic steel, the carriage is judged to be one carriage according to the wheel base, the vehicle is divided into the carriages one by one, then information is sent to the controller, the controller provides a section control signal for the system, the system divides the image according to the section control signal, and the division mainly comprises the step of independently dividing and storing each carriage into one image.
Because the system is a linear array camera, the collected images are spliced out by each line.
The container character recognition method based on deep learning analysis of the graphic processing workstation recognizes the container number information, and specifically comprises the following steps: the method has the advantages that the preprocessing of the image is completed through the graphic graying and edge detection processing, the preprocessed image is analyzed in the connected domain, the character segmentation and extraction are realized, and then the character is recognized by utilizing the deep learning model.
The method for recognizing the characters by utilizing the deep learning model specifically comprises the following steps:
1) preprocessing the acquired image, including preprocessing the acquired image such as cutting, smoothing, sharpening, brightness adjustment, binarization and the like;
2) image dataset partitioning comprising: images of different vehicle types and different background environments are sorted and divided into a training set, a verification set and a test set;
3) model training, comprising: labeling a sample, labeling the position and the label of each box number character in the image, determining the number of iteration rounds, and training;
4) image recognition, comprising: calling the trained model to identify a new image;
5) and repeatedly verifying, including: and analyzing the recognition result, if the result is wrong, adding the image into the sample library, and retraining to generate a new model.
The vehicle-mounted illumination control system comprises an illumination sensor and an illumination device, wherein the illumination sensor is electrically connected with an input end of a controller, an output end of the controller is electrically connected with the illumination device, the illumination sensor is used for detecting ambient illumination, when a vehicle comes and the ambient illumination is lower than a set value, the controller starts the illumination device, and the illumination device is automatically turned off when the vehicle leaves.
The system further comprises a portal frame, wherein three laser integrated cameras are arranged on the portal frame and are used for respectively acquiring images of the left side, the right side and the top of the carriage; the portal frame is further provided with two snapshot cameras, and the two snapshot cameras are used for respectively taking a snapshot of the tail of the carriage when the vehicle passes through in different directions.
The tail of the carriage is captured to identify the number of the container, and the tail of the carriage is mainly used as a supplement of a side camera. Because the container number is on six sides of the container, the patent only collects the number of the left side and the right side.
The embodiment is characterized in that a steel structure truss, namely a portal frame, is erected across a detected line, and the span is determined according to the position of a field environment. The gantry 1 is generally arranged in a railway section from a railway track connecting station to a port loading and unloading area, and the straight section is not less than 50 meters. A first laser integrated camera 2 is arranged on the left side of the portal frame 1, a second laser integrated camera 3 is arranged on the right side of the portal frame, and a third laser integrated camera 4 is arranged on the top of the portal frame and is used for respectively acquiring high-definition images of the left side, the right side and the top of the carriage; the left side of portal is equipped with first high definition candid photograph camera 5, the right side of portal is equipped with second high definition candid photograph camera 6, starts different cameras respectively and candid photograph the carriage afterbody when the equidirectional passing. Three images in every section carriage are left side, right side, top respectively, installs two high definition video surveillance cameras additional simultaneously in the traffic direction, but automobile body, box and vehicle operation condition clearly see, provide vehicle, box omnidirectional image, video information from four angles. And a light supplementing light source 7 of the snapshot machine is arranged above the first snapshot camera and the second snapshot camera. The resolution of the laser integrated camera of the embodiment is as follows: 2048 pixels/row, 12 meters truck image minimum pixels 6000 × 2048. The system of the invention adopts the laser light source, shields the interference of sunlight and fog, reduces the interference influence among lamplight at night, and has uniform illumination.
The present invention analyzes a container image based on an OCR (optical character recognition) technique in image recognition to recognize a container number and a box type code (ISO number). The system is provided with an automatic train number recognition system, the train number is automatically matched with the train image, and the image can be superposed with information of the train type, the train number, the parking space and the container number.
The invention provides comprehensive inquiry according to train number, container number, date and the like; the image data of 4 angles of a specific vehicle can be determined according to the train number, the container number and the date and time. The system has the function of automatic data backup, ensures data safety, can record running logs for the system and provides a log retrieval function. And the invention also supports the video monitoring of the vehicle advancing direction.
In practical engineering application, a set of car number and box number identification association system monitoring equipment (including a camera, lighting equipment, a foundation, a portal frame, a power distribution unit, lightning protection grounding, car number identification and the like) can be arranged at a proper position in a railway section from a railway track connecting station to a port area, a server, an industrial personal computer, network transmission equipment and application software are arranged in a port area information machine room, and front-end acquisition equipment is connected with machine room system equipment through optical cables. 1 operation terminal is respectively arranged at a freight building and a port area monitoring center of a railway track connecting station, and system identification associated information and goods handover conditions are checked.
The implementation of this system can be fine solution container from harbour boats and ships to railway freight car transportation in-process, the container does not fall to the ground, does not need artificial intervention, alright realize that container case number and railway freight car number discernment are correlated with, improved container molten iron intermodal operation efficiency greatly to can satisfy the automatic type-in of cargo information of container goods in railway transportation. The system can adapt to various container loading modes such as open wagon, flat wagon, single layer, double layer, single row, combined row and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. The utility model provides a car number and case number discernment correlation system which characterized in that: including camera, vehicle detection sensor and train number identification system, train number identification system is used for gathering number of a car, number of a car information to number of a car, the number of a car information transfer that will gather gives the host computer, vehicle detection sensor is used for detecting the vehicle and comes the car, vehicle detection sensor is connected with the input of controller, and the output and the camera of controller are connected, the camera is used for gathering container image and with the transmission of the container image data who gathers to the host computer, the host computer is used for carrying out the analysis to the container image of gathering, discerns container box number and box code to the container box number that will discern is correlated with train number.
2. The system of claim 1, wherein: the car number identification system comprises a car number receiving and reading device, the car number receiving and reading device is used for sending radio frequency signals and transmitting the radio frequency signals to the passive RFID volume labels on the lower portion of the carriage through the ground antenna, the ground antenna receives the volume label signals simultaneously and transmits the volume label signals to the car number receiving and reading device through the radio frequency cable, and the car number receiving and reading device transmits the volume label signals to the upper computer.
3. The system of claim 1, wherein: the vehicle detection sensor is used for detecting the passing speed of a vehicle and transmitting the passing speed to the controller, and the controller is used for controlling the sampling frequency of the camera according to the speed of the vehicle and collecting images of the container.
4. The system of claim 1, wherein: the vehicle detection sensor adopts wheel sensors, each group of wheel sensors is composed of at least two pieces of magnetic steel, wherein the first magnetic steel and the second magnetic steel are arranged at intervals, the first magnetic steel and the second magnetic steel are used for outputting signals to the controller when a vehicle passes through, and the controller calculates the speed of the vehicle according to the time when the same wheel passes through the first magnetic steel and the second magnetic steel.
5. The system of claim 1, wherein: the vehicle detection sensor comprises startup magnetic steel, the startup magnetic steel is used for generating a startup signal when a vehicle passes through and transmitting the startup signal to the controller, and the controller controls the camera to start up after receiving the startup signal.
6. The system according to claim 1 or 5, characterized in that: including illuminance sensor and lighting apparatus, illuminance sensor is connected with the input electricity of controller, and the output and the lighting apparatus electricity of controller are connected, illuminance sensor is used for detecting ambient illuminance, and when coming car and ambient illuminance were less than the setting value, the controller started lighting apparatus, and self-closing lighting apparatus when the car left.
7. The system of claim 1, wherein: and when the controller detects that the vehicle detection sensor does not respond within the set time, judging that the vehicle leaves, stopping driving the camera, and finishing the detection process of the train of vehicles.
8. The system of claim 1, wherein: the controller gathers the signal that produces when the first wheel of every section carriage passes through same vehicle detection sensor with the second wheel, discerns every section carriage according to the wheel base to provide the segmentation control signal for the host computer, the host computer is used for splicing the image data of field collection, combines segmentation control signal to carry out vehicle image and cuts apart, generates the carriage picture of every section carriage, and discerns the container case number information of carriage picture.
9. The system of claim 8, wherein: the container character recognition method based on deep learning analysis is adopted by the container number information of the carriage picture recognized by the upper computer, and specifically comprises the following steps: the method comprises the steps of finishing preprocessing of images by carrying out graphic graying and edge detection processing on carriage images, carrying out connected domain analysis on the preprocessed images, realizing character segmentation and extraction, and then identifying characters by utilizing a deep learning model.
10. The system of claim 1, wherein: the system is characterized by further comprising a portal frame, wherein the portal frame spans a railway and is provided with three laser integrated cameras, and the three laser integrated cameras are used for respectively acquiring images of the left side, the right side and the top of the carriage; the portal frame is further provided with two snapshot cameras, and the two snapshot cameras are used for respectively taking a snapshot of the tail of the carriage when the vehicle passes through in different directions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506780.2A CN111833302A (en) | 2020-06-05 | 2020-06-05 | Car number and case number identification association system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506780.2A CN111833302A (en) | 2020-06-05 | 2020-06-05 | Car number and case number identification association system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111833302A true CN111833302A (en) | 2020-10-27 |
Family
ID=72899285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506780.2A Pending CN111833302A (en) | 2020-06-05 | 2020-06-05 | Car number and case number identification association system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111833302A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076838A (en) * | 2021-03-25 | 2021-07-06 | 中国铁路北京局集团有限公司北京科学技术研究所 | Method, system, equipment and storage medium for identifying marshalling sequence of railway container station box numbers |
| CN113378646A (en) * | 2021-05-18 | 2021-09-10 | 上海平奥供应链管理有限公司 | Freight train information identification system and identification method |
| CN114227892A (en) * | 2022-03-01 | 2022-03-25 | 深圳艾灵网络有限公司 | Concrete pouring system, control method, device and control equipment |
| CN114692795A (en) * | 2022-04-11 | 2022-07-01 | 郑州智辆电子科技有限公司 | Railway logistics park container number identification system |
| CN114758328A (en) * | 2022-04-07 | 2022-07-15 | 郑州智辆电子科技有限公司 | Railway vehicle number and container number matching method |
| CN114785945A (en) * | 2022-04-07 | 2022-07-22 | 郑州智辆电子科技有限公司 | Picture snapshot system and method based on railway vehicle axle counting |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101774390A (en) * | 2009-12-31 | 2010-07-14 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Automatic train identification system |
| CN103679221A (en) * | 2012-09-04 | 2014-03-26 | 苏州华兴致远电子科技有限公司 | Automatic equipment identification (AEI) method and AEI system |
| CN204305214U (en) * | 2014-12-03 | 2015-04-29 | 武汉利德测控技术股份有限公司 | Loading goods train state high-definition image system |
| CN106067023A (en) * | 2016-06-02 | 2016-11-02 | 北京国泰星云科技有限公司 | Container number based on image procossing and truck Train number recognition system and method |
| CN206292830U (en) * | 2016-12-26 | 2017-06-30 | 深圳市招科智控科技有限公司 | A kind of container number identifying system |
| CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
| CN109214338A (en) * | 2018-09-06 | 2019-01-15 | 中铁武汉勘察设计研究院有限公司 | A kind of haulage vehicle license number and container number interconnected system |
| CN109241971A (en) * | 2018-07-18 | 2019-01-18 | 东莞市诺丽电子科技有限公司 | A kind of municipal rail train car number identification system |
| CN109784272A (en) * | 2019-01-13 | 2019-05-21 | 南京邮电大学盐城大数据研究院有限公司 | A kind of container identifying system and container recognition methods |
| 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 |
-
2020
- 2020-06-05 CN CN202010506780.2A patent/CN111833302A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101774390A (en) * | 2009-12-31 | 2010-07-14 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Automatic train identification system |
| CN103679221A (en) * | 2012-09-04 | 2014-03-26 | 苏州华兴致远电子科技有限公司 | Automatic equipment identification (AEI) method and AEI system |
| CN204305214U (en) * | 2014-12-03 | 2015-04-29 | 武汉利德测控技术股份有限公司 | Loading goods train state high-definition image system |
| CN106067023A (en) * | 2016-06-02 | 2016-11-02 | 北京国泰星云科技有限公司 | Container number based on image procossing and truck Train number recognition system and method |
| CN206292830U (en) * | 2016-12-26 | 2017-06-30 | 深圳市招科智控科技有限公司 | A kind of container number identifying system |
| CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
| CN109241971A (en) * | 2018-07-18 | 2019-01-18 | 东莞市诺丽电子科技有限公司 | A kind of municipal rail train car number identification system |
| CN109214338A (en) * | 2018-09-06 | 2019-01-15 | 中铁武汉勘察设计研究院有限公司 | A kind of haulage vehicle license number and container number interconnected system |
| CN109784272A (en) * | 2019-01-13 | 2019-05-21 | 南京邮电大学盐城大数据研究院有限公司 | A kind of container identifying system and container recognition methods |
| 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 |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076838A (en) * | 2021-03-25 | 2021-07-06 | 中国铁路北京局集团有限公司北京科学技术研究所 | Method, system, equipment and storage medium for identifying marshalling sequence of railway container station box numbers |
| CN113378646A (en) * | 2021-05-18 | 2021-09-10 | 上海平奥供应链管理有限公司 | Freight train information identification system and identification method |
| CN114227892A (en) * | 2022-03-01 | 2022-03-25 | 深圳艾灵网络有限公司 | Concrete pouring system, control method, device and control equipment |
| CN114758328A (en) * | 2022-04-07 | 2022-07-15 | 郑州智辆电子科技有限公司 | Railway vehicle number and container number matching method |
| CN114785945A (en) * | 2022-04-07 | 2022-07-22 | 郑州智辆电子科技有限公司 | Picture snapshot system and method based on railway vehicle axle counting |
| CN114692795A (en) * | 2022-04-11 | 2022-07-01 | 郑州智辆电子科技有限公司 | Railway logistics park container number identification system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111833302A (en) | Car number and case number identification association system | |
| CN109878552B (en) | Foreign matter monitoring devices between track traffic platform door and train based on machine vision | |
| CN202793389U (en) | On-line routing inspection device for high-speed rail overhead line system | |
| CN111016932B (en) | Track inspection vehicle and detection method of energy-saving air rail system | |
| CN107380163A (en) | Automobile intelligent alarm forecasting system and its method based on magnetic navigation | |
| CN201846437U (en) | High-definition video monitoring system for truck loading state | |
| CN103679221A (en) | Automatic equipment identification (AEI) method and AEI system | |
| CN105913367A (en) | Public bus passenger flow volume detection system and method based on face identification and position positioning | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN104320613A (en) | Monitoring method, monitoring system and positioning system for maintenance operation of motor car | |
| CN113788051A (en) | Train on-station running state monitoring and analyzing system | |
| CN112733558A (en) | RFID-based luggage tracking system and method | |
| CN114998244A (en) | Intelligent track beam finger-shaped plate inspection system and method based on computer vision | |
| CN212302511U (en) | Car number and case number identification association system monitoring facilities | |
| CN113378646A (en) | Freight train information identification system and identification method | |
| CN208938331U (en) | Intelligent bayonet channel system | |
| CN115690061A (en) | Container terminal truck collection detection method based on vision | |
| CN109325911B (en) | Empty base rail detection method based on attention enhancement mechanism | |
| CN114067278A (en) | Railway freight goods inspection system and method thereof | |
| CN110738198A (en) | Railway coal transportation is lost and is spilt monitoring system | |
| JP2002344952A (en) | License plate recognition device and method | |
| CN108198164A (en) | A kind of detection device and method of cable tunnel cable integrity | |
| CN110524553B (en) | Intelligent image analysis system of railway goods inspection robot | |
| CN113205133B (en) | Tunnel water stain intelligent identification method based on multitask learning | |
| CN107831762A (en) | The path planning system and method for a kind of new-energy automobile |
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 |